{"metadata":{"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"widgets":{"application/vnd.jupyter.widget-state+json":{"state":{"02fe8717a4174559b29d090c46116c2d":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"03f0f01f7c7f43f1b85d0e2bdff06d9a":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"061b756217a249749200246514290335":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"06d33df4d6744e26ae0037159f71c384":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"LabelModel","state":{"layout":"IPY_MODEL_270b73c4145d4f6f8ee6da27320f4f9e","style":"IPY_MODEL_eeffc7c179324bc1b1e3d5906d436929"}},"06f30db6bb1b47f8ad238b88cd9d4c1c":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"07405e55b9a643879d1d398434f27cfe":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"091e4ffed6354178b87ac9aa2a4209e2":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_d5126feb65a84bf783aa3284e376584e","style":"IPY_MODEL_bbc9a503bcde4d1ebeff8398d56103d2","value":" 4882/4884 [01:02<00:00, 79.03it/s]"}},"0933dd87781e4431a8f04ab5b65e3a22":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"0b2fc8732aed4a599824830267af2f73":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"0c9e0276e3514a0597f1f31b7872d9ee":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"0cf766e3112c4ee0985496009562e4aa":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_54deeee9b5b44412b904c2f47b533a77","max":1,"style":"IPY_MODEL_b5a921221b104d6ca418d56c5276a121"}},"112b6346380e42e1801d61eee0de9026":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"140ad88ae7994469a3b1c7f01870f9d1":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"14fc82d4c6b8459b81b4d7d09e98e903":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"1544aa3d209d42d8a12ab9f1fd0ad099":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"15bdfecbe1f6473abc87d1e80f4ca6f1":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"17a54d28655e4691b9c52b0ed404d3d7":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"17b144777f214073b2828a7ea0b50ef1":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_dfe735036baf4b9c846db77d23020db5","max":4884,"style":"IPY_MODEL_50998d280c2f4c4183beb25609e59c82","value":4884}},"186e913ca7684366a17d4557ca0ec308":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"195763d98e914c908cf7cd344a634e5a":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"1976e03c78e2441fab5e2c7921ddd9e3":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_4c0ac39781ec4c4f86b841d399eb4a45","style":"IPY_MODEL_46ce40b8284d49c0a4286157844fa134","value":" 611/611 [02:16<00:00, 4.72it/s]"}},"1a06a20e4f0b48a0804383ab0a9a1bfe":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"1ab2af883837482b954e1bbe20c26966":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_9032768dcf2449bf8952b32889de4215","style":"IPY_MODEL_c0f322f5999c4440b1a691347113772b","value":"[valid]: 100%"}},"1b07e1114fc343569a52f66c9d826fb2":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"1da955485f914bad8183d3dbd92ed407":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HBoxModel","state":{"children":["IPY_MODEL_f32e62905f264f4faef84608247bf38f","IPY_MODEL_ab32ce4c072747a7be743029028cd59f","IPY_MODEL_4c85565caefd4a8293c0382a873d4844"],"layout":"IPY_MODEL_8639778685754dd48bf26533df357753"}},"1dee12ab1c3747b7ac4f0c3b180e6211":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_cba7cc09798a4184b9d038f1adddc995","style":"IPY_MODEL_0c9e0276e3514a0597f1f31b7872d9ee","value":" 4882/4884 [01:12<00:00, 71.93it/s]"}},"1e3b6bac7ecd41848626b564fef4623e":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_195763d98e914c908cf7cd344a634e5a","style":"IPY_MODEL_d3318e85bcd948adbf9d570b8dfb561c","value":" 611/611 [01:41<00:00, 6.19it/s]"}},"1fd9c512d9824aa6b9e2301a8a526263":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"20b4961ee51342e98dc0e7dc920f980d":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"20c00ba41907414f8472daa151d580e2":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"22f299428e2b482e9f7fe90fbb4527a8":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_8e98a27dbc974de49bdac906f104ede7","max":4884,"style":"IPY_MODEL_2cd29b22c2474ba4a2e892a463b9b8e9","value":4884}},"2317dc59e31847d1b67a44a6d7dde5a1":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"23220efd32d14e129a9e4c9e9d723fb0":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"2355887aaba540e19dcccfc3d778e89c":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"25e7c11eb60a424699ccef04bc3d7b66":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"270b73c4145d4f6f8ee6da27320f4f9e":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"27fdc5c0761b4459a0cfe9c6c8ade0bb":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_20b4961ee51342e98dc0e7dc920f980d","style":"IPY_MODEL_2921a4e2d33f4335b9f4cb46d289f52b","value":"[valid]: 100%"}},"28984a5809054bcf83950dd5a03082f8":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"2921a4e2d33f4335b9f4cb46d289f52b":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"293f145d85de4c53a4ffe148a04c65f3":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"295ee76c7cc744f7860b27ea58c96e29":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"2c18e73d89fa46d19633c059430ea609":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"2c90df9a4e1b4f3480ed6348a80879d0":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_2c18e73d89fa46d19633c059430ea609","style":"IPY_MODEL_9d895b5f9b3345bb8ee48906fb57a60f","value":"[train]: 100%"}},"2cd29b22c2474ba4a2e892a463b9b8e9":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"2d3869eba94a4d18bddba3dfce1cecbf":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"2decc01d2a2446bd88b0dfecc61cf9d4":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"2e925960ed12472db35195134647c046":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"30eaa95ca7a24837b81d4890d597b449":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"30fa31ec8f6b4e83a30d3b3103db9e36":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_4fc482d2ad1e469286db6875e7df2720","style":"IPY_MODEL_2d3869eba94a4d18bddba3dfce1cecbf","value":"[train]: 100%"}},"35495808e600467bbe02a9f2dc767da7":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_5ed5653ab8b34fe291247ca1552b8c23","max":611,"style":"IPY_MODEL_e0f6759dddc44440b520e67fa7e38f82","value":611}},"361a6767bb0d449799781aa85ff1fd89":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"LabelModel","state":{"layout":"IPY_MODEL_57bbec94c7134ca58678038923f51b93","style":"IPY_MODEL_e9644fd5104649f5ae01a6683c2c0a70"}},"36a905e637684084be11e9b842532c75":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"37b322e318c14ea88b6d70de68ce650b":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"381431430f30483b8d779e5bac901eb6":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"387eab9a2013484185e404497b2e7cda":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_423b6c7ab21e47128ea8badc0a50d385","max":1,"style":"IPY_MODEL_186e913ca7684366a17d4557ca0ec308"}},"38c38e2d21b9490e8a5d05d78b495259":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"39cc77d0541e44ad9a7690de505eafae":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"3bcdfe3e1c4d47d58f7a600903e248a5":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_5f278ac36e0247ffa67f1d7423e5752f","max":611,"style":"IPY_MODEL_b8f7b440e8be467db07ee8649834972e","value":611}},"423b6c7ab21e47128ea8badc0a50d385":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"42c7926a934842fda6dd3a9ecf01aa13":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_28984a5809054bcf83950dd5a03082f8","max":4884,"style":"IPY_MODEL_80d0f5a240d145d5ac49a50ff0bacbaf","value":4884}},"438846f3b01740e2a8977b7ca346ef5a":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_b6848109aa194c878ad2dc0b873ba70b","style":"IPY_MODEL_b1f73d56731745c383dec77892f3e84a","value":" 4882/4884 [01:09<00:00, 63.73it/s]"}},"43c030e0da7f45759fd2cf2c02fc203b":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"43d9ba117c7c4320af778d545fee5a96":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_4bf473847b8c4cd384b1c20da59c70a7","style":"IPY_MODEL_fbb6c4535a954480b189532142f2e0b6","value":"[valid]: 100%"}},"44bb2ee826b042a99f92fd00626ab63b":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"44c1825ca9ab4d19b5d3d062a96b9a59":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"44e12afca69545afb862d70aff9ef183":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"45ab25fe097a4833b30514cfbe7cdb87":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_39cc77d0541e44ad9a7690de505eafae","max":4884,"style":"IPY_MODEL_4c7660b2d5274ea9aeb007ec38b08541","value":4884}},"46ba6f3704dd4bd3a289f95c93fe25de":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"46ce40b8284d49c0a4286157844fa134":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"4868eac352e54bb0af4b2b3d13d79822":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_5b1c2abcc8ac4aafba1d5b58a8b0ccef","style":"IPY_MODEL_ab7268b858214d9ba296ac5e3ac14228","value":" 4882/4884 [01:03<00:00, 70.05it/s]"}},"48ab02a7d319440785559f990ae5b2b0":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_f786420c6b5a4649aa257f6bad91b251","max":4884,"style":"IPY_MODEL_dbadece046f44a37984bdce97aae92fa","value":4884}},"4943b7235e014c5cb2b42448fe613f98":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_ea23b4838454451e94855bc2f9df9ae2","style":"IPY_MODEL_2decc01d2a2446bd88b0dfecc61cf9d4","value":"[train]: 100%"}},"4bbaa725987a4626895cf10f76579ddb":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"4bf473847b8c4cd384b1c20da59c70a7":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"4c0ac39781ec4c4f86b841d399eb4a45":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"4c7660b2d5274ea9aeb007ec38b08541":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"4c85565caefd4a8293c0382a873d4844":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_30eaa95ca7a24837b81d4890d597b449","style":"IPY_MODEL_a908addfc91247cc9c7a513306ab5ae2","value":" 3/3 [00:02<00:00, 1.33it/s]"}},"4d8f3078c4a64d22b9e4c4640d8ae220":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"4dcbcfb7d85d4d88904f79c3736634d1":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"4e294638bebc477b8205aa112f00f373":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"4ee1217c36c4446bacd591970580e38e":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"4fc482d2ad1e469286db6875e7df2720":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"503771bbda2440019a7b08a8edbf050e":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"50998d280c2f4c4183beb25609e59c82":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"518084d9c98848e3afda881660683879":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_f0e3f458d71a4c73bcb62cf074d8de3a","style":"IPY_MODEL_a7068f3f3de240b7a9ef686e0deedc61","value":"[train]: 100%"}},"5444055d667d4c8996e3c9fd9d7ec541":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_1544aa3d209d42d8a12ab9f1fd0ad099","style":"IPY_MODEL_36a905e637684084be11e9b842532c75","value":" 611/611 [01:42<00:00, 6.31it/s]"}},"54deeee9b5b44412b904c2f47b533a77":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"56c1b090c5694b9e8d71201e9d19d3a0":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"57bbec94c7134ca58678038923f51b93":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"57ef677b81f74d5385c2fea49bba0285":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"58fd4f425514402fbde832abd73f1869":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_cbca16677b8c49358921b3ff84da79a2","style":"IPY_MODEL_b01e37f2b0e046c393ac80fcfd3aeb0d","value":" 611/611 [02:18<00:00, 4.52it/s]"}},"5b1c2abcc8ac4aafba1d5b58a8b0ccef":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"5c04fab07c3d4ae99a4420153d688a24":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"5d7a48a9beee46c6842c5753c6d81b57":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_25e7c11eb60a424699ccef04bc3d7b66","style":"IPY_MODEL_061b756217a249749200246514290335","value":" 611/611 [02:10<00:00, 4.64it/s]"}},"5ed5653ab8b34fe291247ca1552b8c23":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"5f278ac36e0247ffa67f1d7423e5752f":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"60a1b70fdb77407c845ba795f89917b1":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_d1a822fe66064867b2adc415034c0b2e","style":"IPY_MODEL_293f145d85de4c53a4ffe148a04c65f3","value":" 611/611 [02:04<00:00, 4.93it/s]"}},"60c90539ee3b4a288abff3ec430a2efd":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"694a7df59f9f49f494fb1cccb7255d28":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"6c0a0ab62016423e87e3be098ff0fee2":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_7d20bc72263b49889a8ed0960f2a72c2","style":"IPY_MODEL_57ef677b81f74d5385c2fea49bba0285","value":"[valid]: 100%"}},"6c0ce36a3d2942ae83e880a3dbbd5146":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"6ed44b5ef88a43ee9960850b5b2f639d":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_4d8f3078c4a64d22b9e4c4640d8ae220","style":"IPY_MODEL_37b322e318c14ea88b6d70de68ce650b","value":"[valid]: 100%"}},"720a038eb12f4d0f8772699490108086":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"74df4d778ade494e83a9d820bab4d21e":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_a122834936c74f7d8808eae90b90e6b0","style":"IPY_MODEL_17a54d28655e4691b9c52b0ed404d3d7","value":" 611/611 [02:07<00:00, 4.86it/s]"}},"77a51de5ed554142938a71537d953ddd":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"7a4fa6bb9e49409fb94a72c12e47ef90":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"7b22364d13a943f38ac4408c3b288cd0":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"7d20bc72263b49889a8ed0960f2a72c2":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"7d70b14ed6ce4aa3a121a068b8f1efe1":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"7ec941a5f1bf4fc3a7a24e6140e1baba":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"7f98c349285a4565a69192e822fefb20":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"800857501aae421da256a358023132db":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_f4501d9766c8492d85304660e21701af","style":"IPY_MODEL_afa75fc3d8f64540a1ed05bf9f3a57ee","value":" 611/611 [01:44<00:00, 5.73it/s]"}},"80d0f5a240d145d5ac49a50ff0bacbaf":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"81795ad89f3146529e854ec3482d54eb":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_23220efd32d14e129a9e4c9e9d723fb0","style":"IPY_MODEL_f54b89fa9d8842588061271b06db177a","value":"[train]: 100%"}},"84f8fe6a67ae446d8547656cba64ad3c":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"8639778685754dd48bf26533df357753":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"89916767fc9d4e3da97dcb3cae03cfdb":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_46ba6f3704dd4bd3a289f95c93fe25de","style":"IPY_MODEL_44e12afca69545afb862d70aff9ef183","value":"[valid]: 100%"}},"8d3a77d9e5884eba8999539de9a5855e":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_112b6346380e42e1801d61eee0de9026","style":"IPY_MODEL_ac5576f180334e8da6eca075e9aa6713","value":" 4884/4884 [01:08<00:00, 71.12it/s]"}},"8e403d0f73914f7ea15f30936a4866c9":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_b23f085cae76428fab55f364a4093133","style":"IPY_MODEL_c1635ad889c2486b839924e8bb5127f4","value":" 4879/4884 [01:11<00:00, 67.53it/s]"}},"8e98a27dbc974de49bdac906f104ede7":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"9032768dcf2449bf8952b32889de4215":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"90352f76a5394be6842e3a035f140039":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_43c030e0da7f45759fd2cf2c02fc203b","style":"IPY_MODEL_694a7df59f9f49f494fb1cccb7255d28","value":"[valid]: 100%"}},"917dc73e097848ee89338fa8054ed91c":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_4ee1217c36c4446bacd591970580e38e","style":"IPY_MODEL_d62d26349f7a49eda837a5de838ae11f","value":"[train]: 100%"}},"92d9f6900c2a4a4d84be052ee834290f":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_295ee76c7cc744f7860b27ea58c96e29","style":"IPY_MODEL_9a466cb881e64fabb33c1468c4ce9e65","value":" 4876/4884 [01:05<00:00, 74.61it/s]"}},"96c372e7cad3495c807278ccfab0420b":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_4dcbcfb7d85d4d88904f79c3736634d1","style":"IPY_MODEL_7a4fa6bb9e49409fb94a72c12e47ef90","value":" 4882/4884 [01:02<00:00, 81.43it/s]"}},"9811e50e70e94ef89eb7868308b84597":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"9884e44b9bcf42c58cb9c15bacc0e24e":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"989af5b761774d3f8af0f49dd721c775":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_07405e55b9a643879d1d398434f27cfe","style":"IPY_MODEL_15bdfecbe1f6473abc87d1e80f4ca6f1","value":" 611/611 [02:18<00:00, 4.69it/s]"}},"9a466cb881e64fabb33c1468c4ce9e65":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"9a9c04550e264b049c571cc4c039794f":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_a9fbb173f3614b5fa4bd47a3a7251166","style":"IPY_MODEL_56c1b090c5694b9e8d71201e9d19d3a0","value":"[valid]: 100%"}},"9d895b5f9b3345bb8ee48906fb57a60f":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"9f150db6f159483cb1ead4246f44fec7":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"a122834936c74f7d8808eae90b90e6b0":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"a441d284a49b44afa153c5295c2fa29b":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"a6ce0fe7f84a426c848889b12709fdb7":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_af6c8bec8dd5408cb3ba7ad9124b0af5","max":4884,"style":"IPY_MODEL_c0f6dcd6daeb47f8ba04625fbee2f985","value":4884}},"a7068f3f3de240b7a9ef686e0deedc61":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"a8d2030528da49d08d5d388a9c3e8457":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_a9540922c2254105bc151affce8ee221","style":"IPY_MODEL_1b07e1114fc343569a52f66c9d826fb2","value":"[valid]: 100%"}},"a908addfc91247cc9c7a513306ab5ae2":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"a9540922c2254105bc151affce8ee221":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"a9fbb173f3614b5fa4bd47a3a7251166":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"ab32ce4c072747a7be743029028cd59f":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"bar_style":"success","layout":"IPY_MODEL_9811e50e70e94ef89eb7868308b84597","max":3,"style":"IPY_MODEL_ea9aeb3a4e1142eebb5411c393f964cc","value":3}},"ab7268b858214d9ba296ac5e3ac14228":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"ac5576f180334e8da6eca075e9aa6713":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"acfcba84b6134c029bebeb4ec0ac1da9":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_03f0f01f7c7f43f1b85d0e2bdff06d9a","style":"IPY_MODEL_b84da86552d04eb3bb1d5f12ecc00b64","value":"[train]: 100%"}},"adf0fd9a368640c58cc1b387b9734b07":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"ae88f84d0d8741f9951fbbc5087fb264":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"aefed2992a594d398031fd9237a6bfae":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"af6c8bec8dd5408cb3ba7ad9124b0af5":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"afa75fc3d8f64540a1ed05bf9f3a57ee":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"b01e37f2b0e046c393ac80fcfd3aeb0d":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"b1f73d56731745c383dec77892f3e84a":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"b23f085cae76428fab55f364a4093133":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"b2cc8b8759614bc28f89582a5778a495":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"b5a921221b104d6ca418d56c5276a121":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"b6848109aa194c878ad2dc0b873ba70b":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"b786738430b840d2b11005b2fc97c09c":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"b84da86552d04eb3bb1d5f12ecc00b64":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"b8f7b440e8be467db07ee8649834972e":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"baf56bc36f2441b8b9a86c6da3b4324e":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_02fe8717a4174559b29d090c46116c2d","max":611,"style":"IPY_MODEL_bbd67d5315a047048fee7dfdba370f92","value":611}},"bafdf2ed70b44a4682e45a86cd0543f0":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_6c0ce36a3d2942ae83e880a3dbbd5146","style":"IPY_MODEL_720a038eb12f4d0f8772699490108086","value":" 4883/4884 [01:07<00:00, 71.73it/s]"}},"bbc9a503bcde4d1ebeff8398d56103d2":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"bbd67d5315a047048fee7dfdba370f92":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"bc9e24e42c6c4f45be3b1840edf16302":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_20c00ba41907414f8472daa151d580e2","style":"IPY_MODEL_d1c53938c299455d83c5ec6b9c0d4b23","value":" 4883/4884 [01:09<00:00, 57.23it/s]"}},"be452a144d5942418154485e84d6a4d7":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"beead1b8336c4bc590a6eb2be3aa66eb":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"bf3e6d4ef4164401897268c25432c216":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_14fc82d4c6b8459b81b4d7d09e98e903","style":"IPY_MODEL_38c38e2d21b9490e8a5d05d78b495259","value":"[train]: 100%"}},"c0f322f5999c4440b1a691347113772b":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"c0f6dcd6daeb47f8ba04625fbee2f985":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"c1635ad889c2486b839924e8bb5127f4":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"c53857add44a43279ffc790f9f274ae2":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"c8e8b3c9405c4420a2110aa1359c9659":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"cba7cc09798a4184b9d038f1adddc995":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"cbca16677b8c49358921b3ff84da79a2":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"ccbd13fce37a4274bb023c093fcab63b":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"d1a5559fe40e49139ad784eb33d90951":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"d1a822fe66064867b2adc415034c0b2e":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"d1c53938c299455d83c5ec6b9c0d4b23":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"d3318e85bcd948adbf9d570b8dfb561c":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"d5126feb65a84bf783aa3284e376584e":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"d62d26349f7a49eda837a5de838ae11f":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"d789837d080a4fa0a96ef26f4cce271a":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_7d70b14ed6ce4aa3a121a068b8f1efe1","max":611,"style":"IPY_MODEL_2e925960ed12472db35195134647c046","value":611}},"d85f714070f9404396e18a116c73bd28":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_c53857add44a43279ffc790f9f274ae2","max":611,"style":"IPY_MODEL_1a06a20e4f0b48a0804383ab0a9a1bfe","value":611}},"db4fea4177a849669ce9c996948a0fcf":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"dbadece046f44a37984bdce97aae92fa":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"dc5cdf2bb09a46c4be8a1541421b7bb3":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"dd67c9fc37b7436f8ebf2066bdfdba8d":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"df964b59d36c4639ba229411334bd664":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_77a51de5ed554142938a71537d953ddd","max":611,"style":"IPY_MODEL_503771bbda2440019a7b08a8edbf050e","value":611}},"dfe735036baf4b9c846db77d23020db5":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"e04b35fe1a8a4ebe90626a3082eb03d0":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_2355887aaba540e19dcccfc3d778e89c","style":"IPY_MODEL_140ad88ae7994469a3b1c7f01870f9d1","value":"[train]: 100%"}},"e0f6759dddc44440b520e67fa7e38f82":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"e1362fd7d8724156802ebf87ac83a5af":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"e4b0e19e9414447e999eb9a960884749":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_0b2fc8732aed4a599824830267af2f73","max":4884,"style":"IPY_MODEL_db4fea4177a849669ce9c996948a0fcf","value":4884}},"e9099c2b53d54f1486487fb6e1a00c63":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_beead1b8336c4bc590a6eb2be3aa66eb","max":611,"style":"IPY_MODEL_ae88f84d0d8741f9951fbbc5087fb264","value":611}},"e9644fd5104649f5ae01a6683c2c0a70":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"LabelStyleModel","state":{"description_width":"","font_family":null,"font_size":null,"font_style":null,"font_variant":null,"font_weight":null,"text_color":null,"text_decoration":null}},"ea23b4838454451e94855bc2f9df9ae2":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"ea9aeb3a4e1142eebb5411c393f964cc":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"eb12e34ce6d64b26931615dce154a83b":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"VBoxModel","state":{"children":["IPY_MODEL_361a6767bb0d449799781aa85ff1fd89","IPY_MODEL_387eab9a2013484185e404497b2e7cda"],"layout":"IPY_MODEL_4bbaa725987a4626895cf10f76579ddb"}},"eef8a7cbffa94d1380cda46aa7b14492":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"eeffc7c179324bc1b1e3d5906d436929":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"LabelStyleModel","state":{"description_width":"","font_family":null,"font_size":null,"font_style":null,"font_variant":null,"font_weight":null,"text_color":null,"text_decoration":null}},"f01eefc17443457cbe3b3521e047932f":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_adf0fd9a368640c58cc1b387b9734b07","max":611,"style":"IPY_MODEL_5c04fab07c3d4ae99a4420153d688a24","value":611}},"f0e3f458d71a4c73bcb62cf074d8de3a":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"f123cab305424f96a57b4b0006f516d2":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"f32e62905f264f4faef84608247bf38f":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_f7b6764a6cdd49d798c443a96fd821fd","style":"IPY_MODEL_9884e44b9bcf42c58cb9c15bacc0e24e","value":"100%"}},"f447f181f9994ce0bc9d536c53fb40a9":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_be452a144d5942418154485e84d6a4d7","max":4884,"style":"IPY_MODEL_eef8a7cbffa94d1380cda46aa7b14492","value":4884}},"f4501d9766c8492d85304660e21701af":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"f54b89fa9d8842588061271b06db177a":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"f6bfedd312e247baaa84dc076c6cf884":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_0933dd87781e4431a8f04ab5b65e3a22","max":4884,"style":"IPY_MODEL_f70a45910a8342ff84e28c0553566e91","value":4884}},"f70a45910a8342ff84e28c0553566e91":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"description_width":""}},"f786420c6b5a4649aa257f6bad91b251":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"f7b6764a6cdd49d798c443a96fd821fd":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{}},"f9601e5efd654022aa04ec39769782aa":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"fbb6c4535a954480b189532142f2e0b6":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"description_width":"","font_size":null,"text_color":null}},"fc26e7a1d1e542caadf42eb3b3db292d":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"VBoxModel","state":{"children":["IPY_MODEL_06d33df4d6744e26ae0037159f71c384","IPY_MODEL_0cf766e3112c4ee0985496009562e4aa"],"layout":"IPY_MODEL_84f8fe6a67ae446d8547656cba64ad3c"}},"fca15a52cee2466ca29a1cbd55528a9d":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_7b22364d13a943f38ac4408c3b288cd0","max":4884,"style":"IPY_MODEL_aefed2992a594d398031fd9237a6bfae","value":4884}},"fd379b98f80d45c9a509cd67371b8da1":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"layout":"IPY_MODEL_1fd9c512d9824aa6b9e2301a8a526263","max":611,"style":"IPY_MODEL_b2cc8b8759614bc28f89582a5778a495","value":611}},"fdb29577e8b045419e8906cb2fcd3755":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"visibility":"hidden"}},"ffdb4e5e92ff4b9a87e5f63a16179773":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"layout":"IPY_MODEL_06f30db6bb1b47f8ad238b88cd9d4c1c","style":"IPY_MODEL_2317dc59e31847d1b67a44a6d7dde5a1","value":"[valid]: 100%"}}},"version_major":2,"version_minor":0}},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":70203,"databundleVersionId":8068726,"sourceType":"competition"},{"sourceId":8108072,"sourceType":"datasetVersion","datasetId":4789213},{"sourceId":8319412,"sourceType":"datasetVersion","datasetId":4941521}],"dockerImageVersionId":30698,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"use focal loss","metadata":{}},{"cell_type":"markdown","source":"exp0010 → exp0011\n\n重複しているファイルを消して学習をする\n\nexp0011 → exp0012\n\naugmentation test
\naug_spec_mixupを導入し、50%の確率で適用するかしないか","metadata":{}},{"cell_type":"markdown","source":"- eca_nfnet_l0 (2 stages training; Start LR 1e-3)\r- \nconvnext_small_fb_in22k_ft_in1k_384 (2 stages training; Start LR 1e-4\n- \r\nconvnextv2_tiny_fcmae_ft_in22k_in1k_384 (1 stage training; Start LR 1e-4)","metadata":{}},{"cell_type":"markdown","source":"exp1011 specmix upの実験","metadata":{}},{"cell_type":"markdown","source":"exp1018 oversampling","metadata":{}},{"cell_type":"markdown","source":"exp1019 augmentation test","metadata":{}},{"cell_type":"code","source":"KAGGLE = True\n\nisTrain = False\nisInference = True\n\nif isTrain == False and isInference == True:\n newDir = False\nelse:\n newDir = True","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:02:41.721260Z","iopub.execute_input":"2024-05-25T08:02:41.722202Z","iopub.status.idle":"2024-05-25T08:02:41.771269Z","shell.execute_reply.started":"2024-05-25T08:02:41.722161Z","shell.execute_reply":"2024-05-25T08:02:41.770247Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(newDir)","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:02:41.773242Z","iopub.execute_input":"2024-05-25T08:02:41.773881Z","iopub.status.idle":"2024-05-25T08:02:41.779046Z","shell.execute_reply.started":"2024-05-25T08:02:41.773842Z","shell.execute_reply":"2024-05-25T08:02:41.777300Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if KAGGLE == True:\n !pip install /kaggle/input/onnxruntime/humanfriendly-10.0-py2.py3-none-any.whl --no-index --find-links /kaggle/input/onnxruntime\n !pip install /kaggle/input/onnxruntime/coloredlogs-15.0.1-py2.py3-none-any.whl --no-index --find-links /kaggle/input/onnxruntime\n !pip install /kaggle/input/onnxruntime/onnxruntime-1.17.3-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl --no-index --find-links /kaggle/input/onnxruntime","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:02:41.780358Z","iopub.execute_input":"2024-05-25T08:02:41.780695Z","iopub.status.idle":"2024-05-25T08:03:11.490010Z","shell.execute_reply.started":"2024-05-25T08:02:41.780653Z","shell.execute_reply":"2024-05-25T08:03:11.482232Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport gc\nimport sys\nimport glob\nimport time\nimport shutil\nimport random\nimport warnings\nwarnings.simplefilter(\"ignore\")\n\nimport wandb\n\nimport numpy as np\nimport pandas as pd\nfrom sklearn.model_selection import KFold, GroupKFold, StratifiedGroupKFold\n\nfrom tqdm.notebook import tqdm\n\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\nfrom torch.cuda import amp\nimport torch\nprint(f\"pytorch version is {torch.__version__}\")\nimport torch.nn as nn\nfrom torch.cuda import amp\n\nimport torchvision\nfrom torchvision.transforms import v2 as transforms\n\nimport librosa\nimport torchaudio\nimport torchaudio.transforms as audioT\n\nif KAGGLE == False:\n import nnAudio\n from nnAudio import features\n import albumentations\n from audiomentations import Compose, SpecCompose, OneOf, AddGaussianNoise, AddColorNoise\n from audiomentations import TimeStretch, PitchShift, Shift, SpecFrequencyMask, TimeMask\n from audiomentations import Gain, GainTransition\n from torcheval.metrics.functional import multiclass_auroc, multiclass_f1_score, multiclass_precision, multiclass_recall, multilabel_accuracy\nif KAGGLE == False:\n from adan_pytorch import Adan\nimport timm","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.492549Z","iopub.status.idle":"2024-05-25T08:03:11.493361Z","shell.execute_reply.started":"2024-05-25T08:03:11.493134Z","shell.execute_reply":"2024-05-25T08:03:11.493156Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"timm.list_models(\"*ec*\")","metadata":{"scrolled":true,"execution":{"iopub.status.busy":"2024-05-25T08:03:11.494575Z","iopub.status.idle":"2024-05-25T08:03:11.495237Z","shell.execute_reply.started":"2024-05-25T08:03:11.495027Z","shell.execute_reply":"2024-05-25T08:03:11.495047Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"## decide name\nif KAGGLE == False:\n if isTrain == True:\n name = sorted(glob.glob(\"exp1*.ipynb\"))[-1][:-6]\n print(f\"filename is {name}\")\n else:\n name = \"exp1057\"\n print(f\"filename is {name}\")\nelse:\n name = \"exp1057\"\n name = f'bird2024{name}'\n print(f\"filename is {name}\")\ntrial = \"trial1\"\np_name = f\"BirdCLEF_cv_ver2\"\n","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.496404Z","iopub.status.idle":"2024-05-25T08:03:11.497148Z","shell.execute_reply.started":"2024-05-25T08:03:11.496929Z","shell.execute_reply":"2024-05-25T08:03:11.496951Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class config:\n if KAGGLE:\n dir = \"/kaggle/input/birdclef-2024/\"\n else:\n dir = \"/mnt/d/kaggle/birdclef-2024/\"\n\n # wave_path = \"/mnt/d/kaggle/birdclef-2024/original_waves/second_30/\"\n wave_path = \"original_waves/second_30/\"\n\n # model_name = 'eca_nfnet_l0'\n model_name = 'tf_efficientnet_b0'\n\n pool_type = 'avg'\n\n \n train_duration = 30 ##学習に使うデータの秒数\n slice_duration = 5 ##実際にSTFTをして食わせるデータのサイズ\n\n test_duration = 5\n\n train_drop_duration = 1\n \n ###spectrogram parameters\n sr = 32000\n fmin = 20\n fmax = 15000\n\n n_mels = 128\n n_fft = n_mels*8\n size_x = 512\n \n hop_length = int(sr*slice_duration / size_x)\n test_hop_length = int(sr*test_duration / size_x)\n \n bins_per_octave = 12\n\n nfolds = 5\n inference_folds = [4]\n \n enable_amp = True\n train_batchsize = 32\n valid_batchsize = 1\n\n # loss_type = \"BCEWithLogitsLoss\"\n loss_type = \"BCEFocalLoss\"\n\n lr = 1.0e-03 #for tf_efficientnet_b0\n # lr = 1.0e-04 #for movilenet\n # lr = 1.0e-05 #for movilenet\n\n optimizer='adan'\n # optimizer='adamW'\n weight_decay = 1.0e-02\n es_patience = 5\n deterministic = True\n enable_amp = True\n\n max_epoch = 9\n aug_epoch = 6\n \n\n useSecondary =True\n secondary_label_value = 0.5\n oversample =False\n oversample_threthold = 60\n \n seed = 42\n\n wandb = True\n\n ###augmentation flags\n aug_noise = 0.\n aug_gain = 0.0\n aug_wave_pitchshift = 0.0#効果はあるので入れたいが、重いので実験中は使わない\n aug_wave_shift = 0.\n\n aug_spec_xymasking = 0.\n aug_spec_coarsedrop = 0.\n aug_spec_hflip = 0.\n\n ##mixup param\n aug_wave_mixup = 1.0\n aug_spec_mixup = 0.0\n aug_spec_mixup_prob = 0.5 #specmixup++をさせる確率\n alpha=0.95\n\n smoothing_value = 0.0\n # spec_mix_mask_percent = 20\n \ncfg = config()\n\ndevice = torch.device('cuda:0') if torch.cuda.is_available() else torch.device('cpu')\n\n\n# device = torch.device('cpu')\n\nprint(device)","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.498453Z","iopub.status.idle":"2024-05-25T08:03:11.499136Z","shell.execute_reply.started":"2024-05-25T08:03:11.498894Z","shell.execute_reply":"2024-05-25T08:03:11.498921Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## augmentation tools","metadata":{}},{"cell_type":"code","source":"#https://iver56.github.io/audiomentations/waveform_transforms/add_color_noise/","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.500526Z","iopub.status.idle":"2024-05-25T08:03:11.500982Z","shell.execute_reply.started":"2024-05-25T08:03:11.500776Z","shell.execute_reply":"2024-05-25T08:03:11.500795Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if isTrain== True:\n\n normal_augment = Compose([\n OneOf([\n Gain(min_gain_in_db=-15, max_gain_in_db=15, p=1.0),\n GainTransition(min_gain_in_db=-24.0, max_gain_in_db=6.0,\n min_duration=0.2, max_duration=6.0, p=1.0)\n ], p=cfg.aug_gain),\n \n OneOf([\n AddGaussianNoise(p=1),\n AddColorNoise(p=1, min_snr_db=5, max_snr_db=20, min_f_decay=-3.01, max_f_decay=-3.01)\n ],p=cfg.aug_noise),\n # OneOf([\n # AddGaussianNoise(min_amplitude=0.001, max_amplitude=0.002, p=1),\n # AddColorNoise(p=1, max_f_decay=-3.01, min_snr_db=5, max_snr_db=20, n_fft=cfg.n_fft)\n # ],p=cfg.aug_noise),\n \n PitchShift(min_semitones=-1, max_semitones=1, p=cfg.aug_wave_pitchshift),\n Shift(p=cfg.aug_wave_shift)\n ])\n alb_transform = [\n ### num_masks_x=1, num_masks_y=1 will change\n albumentations.XYMasking(num_masks_x=2, num_masks_y=1, \n mask_x_length=cfg.size_x//30, mask_y_length=cfg.n_mels//30,\n fill_value=0, mask_fill_value=0, p=cfg.aug_spec_xymasking),\n albumentations.CoarseDropout(fill_value=0, min_holes=20, max_holes=50, p=cfg.aug_spec_coarsedrop),\n albumentations.HorizontalFlip(p=cfg.aug_spec_hflip) \n ]\n albumentations_augment = albumentations.Compose(alb_transform)","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.502823Z","iopub.status.idle":"2024-05-25T08:03:11.503258Z","shell.execute_reply.started":"2024-05-25T08:03:11.503053Z","shell.execute_reply":"2024-05-25T08:03:11.503072Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def mixup(data, targets, alpha, mode=\"same_wave\"):\n \n if mode == \"same_wave\":\n data = torch.tensor(data)\n indices = torch.randperm(data.size(0))\n shuffled_data = data[indices]\n # shuffled_targets = targets[indices]\n #print(indices)\n lam = np.random.beta(alpha, alpha)\n #print(lam)\n new_data = data * lam + shuffled_data * (1 - lam)\n # new_targets = targets * lam + shuffled_targets * (1 - lam)\n return new_data.numpy()\n \n elif mode == \"other_wave\":\n indices = torch.randperm(data.size(0))\n shuffled_data = data[indices]\n shuffled_targets = targets[indices]\n \n lam = np.random.beta(alpha, alpha)\n new_data = data * lam + shuffled_data * (1 - lam)\n new_targets = targets * lam + shuffled_targets * (1 - lam)\n \n return new_data, new_targets","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.505234Z","iopub.status.idle":"2024-05-25T08:03:11.506059Z","shell.execute_reply.started":"2024-05-25T08:03:11.505809Z","shell.execute_reply":"2024-05-25T08:03:11.505844Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if isTrain== True:\n spec_xymasking = albumentations.XYMasking(num_masks_x=2, num_masks_y=1, \n mask_x_length=cfg.size_x // 10, mask_y_length=cfg.n_mels // 10,\n fill_value=0, mask_fill_value=0, p=1)\n\ndef spec_mixup(data, targets):\n type = data.dtype\n\n indices = torch.randperm(data.size(0))\n # print(indices)\n shuffled_data = data[indices]\n shuffled_targets = targets[indices]\n\n ##masking\n data = np.array(data)\n data_transposed = np.transpose(data, (2, 3, 1, 0))\n data_transposed = spec_xymasking(image=data_transposed)[\"image\"]\n data_transposed = np.transpose(data_transposed, (3, 2, 0, 1)) \n\n ##masking した場所を取り出す\n diff = data - data_transposed\n mask = (diff != 0).astype(int)\n\n ##mask箇所を、ほかのデータから取り出す\n shuffled_data_masked = (shuffled_data * mask)\n\n ##mixup\n new_data = torch.tensor(data_transposed, dtype=type) + torch.tensor(shuffled_data_masked, dtype=type)\n\n #lamはmask量で決める\n # print(data.size(0))\n lam = mask.sum() / len(data) / (cfg.n_mels*cfg.size_x)\n # print(lam)\n new_targets = targets * (1-lam) + shuffled_targets *lam\n\n return new_data, new_targets","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.508395Z","iopub.status.idle":"2024-05-25T08:03:11.508979Z","shell.execute_reply.started":"2024-05-25T08:03:11.508733Z","shell.execute_reply":"2024-05-25T08:03:11.508756Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"spec_layer = torchaudio.transforms.MelSpectrogram(\n sample_rate=cfg.sr, hop_length=cfg.hop_length, n_fft=cfg.n_fft,\n n_mels=cfg.n_mels,f_min=cfg.fmin,f_max=cfg.fmax,mel_scale='slaney',center=True, pad_mode='reflect'\n # normalized=True\n).to(device)\n\nvalid_spec_layer = torchaudio.transforms.MelSpectrogram(\n sample_rate=cfg.sr, hop_length=cfg.test_hop_length, n_fft=cfg.n_fft,\n n_mels=cfg.n_mels,f_min=cfg.fmin,f_max=cfg.fmax,mel_scale='slaney',center=True, pad_mode='reflect'\n # normalized=True\n).to(device)\n\ntest_spec_layer = torchaudio.transforms.MelSpectrogram(\n sample_rate=cfg.sr, hop_length=cfg.test_hop_length, n_fft=cfg.n_fft,\n n_mels=cfg.n_mels,f_min=cfg.fmin,f_max=cfg.fmax,mel_scale='slaney',center=True, pad_mode='reflect'\n # normalized=True\n).cpu()","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.511256Z","iopub.status.idle":"2024-05-25T08:03:11.512017Z","shell.execute_reply.started":"2024-05-25T08:03:11.511517Z","shell.execute_reply":"2024-05-25T08:03:11.511535Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(newDir)","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.514373Z","iopub.status.idle":"2024-05-25T08:03:11.514931Z","shell.execute_reply.started":"2024-05-25T08:03:11.514701Z","shell.execute_reply":"2024-05-25T08:03:11.514722Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if KAGGLE == False:\n if cfg.wandb == True:\n wandb.login(key=\"1def2aa62f171b4a95415cc2ad76b5eb1bb37b41\")\n\n if newDir == True:\n new_dir_path_recursive = f\"{name}/checkpoint\"\n \n os.makedirs(new_dir_path_recursive, exist_ok=True)\n shutil.rmtree(new_dir_path_recursive)\n os.makedirs(new_dir_path_recursive, exist_ok=True)","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.517197Z","iopub.status.idle":"2024-05-25T08:03:11.517951Z","shell.execute_reply.started":"2024-05-25T08:03:11.517722Z","shell.execute_reply":"2024-05-25T08:03:11.517743Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"---","metadata":{}},{"cell_type":"markdown","source":"# csv preprocessing","metadata":{}},{"cell_type":"code","source":"sample_submission = pd.read_csv(cfg.dir+\"sample_submission.csv\")\nLABELS = list(sample_submission.set_index(\"row_id\").columns)\nLABELS[:5]","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.519127Z","iopub.status.idle":"2024-05-25T08:03:11.520019Z","shell.execute_reply.started":"2024-05-25T08:03:11.519775Z","shell.execute_reply":"2024-05-25T08:03:11.519802Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample_submission","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.521472Z","iopub.status.idle":"2024-05-25T08:03:11.521927Z","shell.execute_reply.started":"2024-05-25T08:03:11.521723Z","shell.execute_reply":"2024-05-25T08:03:11.521741Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# if isTrain:\nif KAGGLE == False:\n train_csv = pd.read_csv(cfg.dir+\"train_eda.csv\")\n train_csv[\"fileID\"] = train_csv[\"filename\"].map(lambda x:x.split(\"/\")[1][:-4])\n train_csv.head(2)\nelse:\n train_csv = pd.read_csv(cfg.dir+\"train_metadata.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.523273Z","iopub.status.idle":"2024-05-25T08:03:11.523738Z","shell.execute_reply.started":"2024-05-25T08:03:11.523503Z","shell.execute_reply":"2024-05-25T08:03:11.523520Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import ast\ntrain_csv['new_target'] = train_csv['primary_label'] + ' ' + train_csv['secondary_labels'].map(lambda x: ' '.join(ast.literal_eval(x)))\ntrain_csv['len_new_target'] =train_csv['new_target'].map(lambda x: len(x.split()))\ntrain_csv[\"len_new_target\"].value_counts().plot(kind=\"bar\", figsize=(4,2))","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.525086Z","iopub.status.idle":"2024-05-25T08:03:11.525517Z","shell.execute_reply.started":"2024-05-25T08:03:11.525306Z","shell.execute_reply":"2024-05-25T08:03:11.525324Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_csv[\"filename_tmp\"] = train_csv[\"filename\"].map(lambda x:x.split(\"/\")[1][:-4])","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.527103Z","iopub.status.idle":"2024-05-25T08:03:11.527777Z","shell.execute_reply.started":"2024-05-25T08:03:11.527481Z","shell.execute_reply":"2024-05-25T08:03:11.527502Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"duplicated_filenames = train_csv[\"filename_tmp\"].value_counts()[train_csv[\"filename_tmp\"].value_counts() > 1].index","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.528956Z","iopub.status.idle":"2024-05-25T08:03:11.529392Z","shell.execute_reply.started":"2024-05-25T08:03:11.529188Z","shell.execute_reply":"2024-05-25T08:03:11.529206Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"duplicated_filenames","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.530866Z","iopub.status.idle":"2024-05-25T08:03:11.531297Z","shell.execute_reply.started":"2024-05-25T08:03:11.531075Z","shell.execute_reply":"2024-05-25T08:03:11.531091Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_csv = train_csv[~train_csv[\"filename_tmp\"].isin(duplicated_filenames)]\ntrain_csv = train_csv.reset_index(drop=True)","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.532877Z","iopub.status.idle":"2024-05-25T08:03:11.533300Z","shell.execute_reply.started":"2024-05-25T08:03:11.533088Z","shell.execute_reply":"2024-05-25T08:03:11.533104Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Dataset","metadata":{}},{"cell_type":"code","source":"class BirdCLEF_Dataset(torch.utils.data.Dataset):\n def __init__(self, df, augmentation=False, mode='train'):\n if mode == 'train':\n self.df = df.reset_index(drop=True)\n elif mode == 'valid':\n self.df = df.reset_index(drop=True)\n else:\n self.df = df\n self.mode = mode\n self.augmentation = augmentation\n \n def __len__(self):\n return len(self.df)\n\n def normalize(self, x):\n valid_values = x[x != float('-inf')]\n mean_value = np.mean(valid_values)\n x[x == float('-inf')] = mean_value\n # x[x == float('-inf')] = 0\n\n x = x - x.min()\n x = x / x.max()\n return x\n\n def wave_tile_and_cutoff(self, data):\n ### ---PREPROCESS wave length to train duration & slice duration-----\n drop_duration = cfg.sr*cfg.train_drop_duration\n use_duration = cfg.sr*cfg.train_duration\n \n if len(data[0]) > drop_duration: #最初の1秒を捨てる\n data = data[:,drop_duration:]\n\n if len(data[0]) < use_duration: #30秒に満たない場合はタイルする\n iter = 1 + (use_duration) // len(data[0])\n data = np.tile(data, (1, iter))\n\n data = data[:,:use_duration]\n return data\n\n def label_smoothing(self, idx, target):\n \n secondary_target = target * cfg.secondary_label_value\n \n out_of_target_noise_intensity = cfg.smoothing_value/(len(LABELS)-1) #該当label以外に、smootiong_valueを分散させる\n out_of_target_noise_array = torch.ones(target.shape) * out_of_target_noise_intensity\n \n secondary_target_with_noise = secondary_target + out_of_target_noise_array\n secondary_target_with_noise = torch.clip(secondary_target_with_noise, min=0, max=cfg.secondary_label_value)\n \n primary_target = np.isin(LABELS, self.df.loc[idx, \"primary_label\"]).astype(int)\n primary_target = torch.tensor(primary_target, dtype=torch.float32)\n\n primary_and_secondary_target_with_noise = primary_target + secondary_target_with_noise\n new_target = torch.clip(primary_and_secondary_target_with_noise, min=0, max=1)\n \n new_target = new_target - primary_target * cfg.smoothing_value\n \n return new_target\n\n \n def __getitem__(self, idx):\n\n if self.mode == 'train':\n\n ### ------------------READ DATA ------------------------------------\n if cfg.useSecondary == True:\n target = np.isin(LABELS, self.df.loc[idx, \"new_target\"].split()).astype(int)\n else:\n target = np.isin(LABELS, self.df.loc[idx, \"primary_label\"].split()).astype(int)\n target = torch.tensor(target, dtype=torch.float32)\n ### ------------------label smoothing --------------------------\n target = self.label_smoothing(idx, target)\n \n fileID = self.df.loc[idx, 'fileID'] #filename : ****/****.ogg\n \n path = f\"{cfg.wave_path}{fileID}.npy\"\n wave = np.load(path)\n ### -----------------------------------------------------------------\n\n # ---PREPROCESS wave length to train duration & slice duration-------\n wave = self.wave_tile_and_cutoff(data=wave)\n\n \n input_duration = cfg.sr * cfg.slice_duration\n # middle_shift = cfg.sr * cfg.train_duration // 2 \n \n if self.augmentation == True:\n ### ------------------wave time mixup --------------------------\n if cfg.aug_wave_mixup > np.random.random(): #同じwave内でmixupをする\n #train_duration -> slice_duration\n wave_reshape = wave.reshape(-1, input_duration)\n wave = mixup(data=wave_reshape, targets=target, alpha=cfg.alpha, mode=\"same_wave\")\n wave = wave[:1,:]\n else:\n wave = wave[:, :input_duration]\n \n ### ------------------wave augmentation ------------------------\n wave = normal_augment(samples=wave, sample_rate=cfg.sr)\n\n ### ------------------MAKE SPECTROGRAM -------------------------\n wave = torch.tensor(wave).to(device)\n mel_spec = spec_layer(wave)\n mel_spec = np.array(mel_spec.cpu())\n\n mel_spec = np.log(mel_spec)\n for i in range(len(mel_spec)):\n mel_spec[i] = self.normalize(mel_spec[i])\n mel_spec = torch.tensor(mel_spec)\n mel_spec = mel_spec[:,:,:cfg.size_x]\n\n ### ------------------spec augmentation ------------------------\n mel_spec = np.array(mel_spec.cpu())\n mel_spec = np.transpose(mel_spec, (1, 2, 0)) \n mel_spec = albumentations_augment(image=mel_spec)[\"image\"]\n mel_spec = np.transpose(mel_spec, (2, 0, 1))\n\n # ### ------------------label smoothing --------------------------\n # target = self.label_smoothing(idx, target)\n \n else:\n wave = wave[:, :input_duration]\n \n ### ------------------MAKE SPECTROGRAM -------------------------\n wave = torch.tensor(wave).to(device)\n mel_spec = spec_layer(wave)\n mel_spec = np.array(mel_spec.cpu())\n\n mel_spec = np.log(mel_spec)\n\n for i in range(len(mel_spec)):\n mel_spec[i] = self.normalize(mel_spec[i])\n \n\n mel_spec = torch.tensor(mel_spec)\n mel_spec = mel_spec[:,:,:cfg.size_x]\n\n \n mel_spec = torch.tensor(mel_spec)\n\n \n return mel_spec, target\n\n elif self.mode == 'valid':\n \n ### ------------------READ DATA ------------------------------------\n if cfg.useSecondary == True:\n target = np.isin(LABELS, self.df.loc[idx, \"new_target\"].split()).astype(int)\n else:\n target = np.isin(LABELS, self.df.loc[idx, \"primary_target\"].split()).astype(int)\n target = torch.tensor(target, dtype=torch.float32)\n \n fileID = self.df.loc[idx, 'fileID'] #filename : ****/****.ogg\n \n path = f\"{cfg.wave_path}{fileID}.npy\"\n wave = np.load(path)\n ### -----------------------------------------------------------------\n\n # ---PREPROCESS wave length to train duration & slice duration-------\n wave = self.wave_tile_and_cutoff(data=wave)\n\n input_duration = cfg.sr*cfg.test_duration\n wave_reshape = wave.reshape(-1, input_duration)\n\n wave_reshape = torch.tensor(wave_reshape).to(device)\n mel_specs = valid_spec_layer(wave_reshape)\n mel_specs = mel_specs.cpu().numpy()\n\n mel_specs = np.log(mel_specs)\n for i in range(len(mel_specs)):\n mel_specs[i] = self.normalize(mel_specs[i])\n mel_specs = torch.tensor(mel_specs)\n \n mel_specs = mel_specs[:,:,:cfg.size_x]\n\n targets = torch.tile(target, dims=(mel_specs.shape[0],1))\n return mel_specs, targets\n\n ###---------------------------------------------------------------------------------------------------------------------\n elif self.mode == 'test':\n\n filepath = self.df[idx]\n wave, _ = torchaudio.load(filepath)\n wave = wave[:,:60*4*32000]\n\n wave_reshaped = wave.reshape(-1, 1, cfg.test_duration*cfg.sr)\n \n mel_spec = test_spec_layer(wave_reshaped)\n mel_spec = np.log(mel_spec)\n\n mel_spec = np.array(mel_spec)\n #mel_spec = self.normalize(mel_spec)\n for i in range(len(mel_spec)):\n mel_spec[i] = self.normalize(mel_spec[i])\n mel_spec = torch.tensor(mel_spec)\n\n mel_spec = mel_spec[:,:,:cfg.size_x]\n return mel_spec\n\n elif self.mode == 'clean':\n\n filepath = self.df[idx]\n wave, _ = torchaudio.load(filepath)\n\n wave = wave[:, :6*cfg.test_duration*cfg.sr]\n\n chunk_length = len(wave[0]) // (cfg.test_duration*cfg.sr)\n \n wave = wave[:,:chunk_length*cfg.test_duration*cfg.sr]\n\n wave_reshaped = wave.reshape(-1, 1, cfg.test_duration*cfg.sr)\n \n mel_spec = test_spec_layer(wave_reshaped)\n mel_spec = np.log(mel_spec)\n\n mel_spec = np.array(mel_spec)\n for i in range(len(mel_spec)):\n mel_spec[i] = self.normalize(mel_spec[i])\n mel_spec = torch.tensor(mel_spec)\n\n return mel_spec, filepath","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.536338Z","iopub.status.idle":"2024-05-25T08:03:11.537503Z","shell.execute_reply.started":"2024-05-25T08:03:11.537159Z","shell.execute_reply":"2024-05-25T08:03:11.537196Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if isTrain:\n print(\"train data\")\n dataset = BirdCLEF_Dataset(df=train_csv, augmentation=True, mode=\"train\")\n data, target = dataset[270]\n fig, ax = plt.subplots(figsize=(6,4))\n plt.imshow(data[0], cmap=\"jet\", origin=\"lower\")\n plt.show()\n \n print(\"validation data\")\n dataset = BirdCLEF_Dataset(df=train_csv, augmentation=True, mode=\"valid\")\n data, target = dataset[270]\n fig, axes = plt.subplots(figsize=(12,8), nrows=len(data), tight_layout=True)\n for idx, ax in enumerate(axes.ravel()):\n ax.imshow(data[idx], cmap=\"jet\", origin=\"lower\")","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.539232Z","iopub.status.idle":"2024-05-25T08:03:11.539765Z","shell.execute_reply.started":"2024-05-25T08:03:11.539511Z","shell.execute_reply":"2024-05-25T08:03:11.539531Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#break","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.541245Z","iopub.status.idle":"2024-05-25T08:03:11.542112Z","shell.execute_reply.started":"2024-05-25T08:03:11.541787Z","shell.execute_reply":"2024-05-25T08:03:11.541814Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model","metadata":{}},{"cell_type":"markdown","source":"## poolings","metadata":{}},{"cell_type":"code","source":"# class GeM(torch.nn.Module):\n# def __init__(self, p=3, eps=1e-6):\n# super(GeM, self).__init__()\n# self.p = torch.nn.Parameter(torch.ones(1) * p)\n# self.eps = eps\n\n# def forward(self, x):\n# bs, ch, h, w = x.shape\n# x = torch.nn.functional.avg_pool2d(x.clamp(min=self.eps).pow(self.p), (x.size(-2), x.size(-1))).pow(1.0 / self.p)\n# x = x.view(bs, ch)\n# return x","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.544025Z","iopub.status.idle":"2024-05-25T08:03:11.544580Z","shell.execute_reply.started":"2024-05-25T08:03:11.544301Z","shell.execute_reply":"2024-05-25T08:03:11.544324Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### simple efficientnet SEDmodel","metadata":{}},{"cell_type":"code","source":"class BirdModel(torch.nn.Module):\n def __init__(self, model_name, pretrained, in_channels, num_classes, pool=\"default\"):\n super().__init__()\n\n self.pool = pool\n self.normalize = transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])\n \n if pool == \"default\":\n self.backbone = timm.create_model(\n model_name=model_name, pretrained=pretrained,\n num_classes=0, in_chans=3)\n else:\n self.backbone = timm.create_model(\n model_name=model_name, pretrained=pretrained,\n num_classes=0, in_chans=3, global_pool=\"\")\n\n in_features = self.backbone.num_features\n\n\n # self.pooling = torch.nn.MaxPool2d()\n # self.pooling = torch.nn.AvgPool2d()\n self.max_pooling = torch.nn.Sequential(torch.nn.AdaptiveMaxPool2d(1),\n torch.nn.Flatten(start_dim=1, end_dim=-1))\n self.avg_pooling = torch.nn.Sequential(torch.nn.AdaptiveAvgPool2d(1),\n torch.nn.Flatten(start_dim=1, end_dim=-1))\n self.both_pooling_neck = torch.nn.Sequential(torch.nn.BatchNorm1d(2*in_features),\n torch.nn.Linear(in_features=2*in_features, out_features=in_features))\n \n self.head = torch.nn.Sequential(\n torch.nn.BatchNorm1d(in_features),\n torch.nn.Linear(in_features=in_features, out_features=256),\n torch.nn.Hardswish(inplace=True),torch.nn.Dropout(0.1),\n torch.nn.Linear(in_features=256, out_features=len(LABELS)) \n )\n\n\n\n self.active = torch.nn.Sigmoid()\n def forward(self, x):\n x = x.expand(-1, 3, -1, -1)\n x = self.normalize(x)\n x = self.backbone(x)\n\n if self.pool == \"max\":\n x = self.max_pooling(x)\n elif self.pool == \"avg\":\n x = self.avg_pooling(x)\n elif self.pool == \"both\":\n x_max = self.max_pooling(x)\n x_avg = self.avg_pooling(x)\n x = x_max + x_avg\n # x = torch.cat([x_max, x_avg], dim=1)\n # x = self.both_pooling_neck(x)\n \n x = self.head(x)\n # x = self.active(x)\n return x","metadata":{"execution":{"iopub.status.busy":"2024-05-25T08:03:11.546026Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# if isTrain:\n# model = BirdModel(model_name=cfg.model_name, pretrained=True, in_channels=3, num_classes=len(LABELS)).to(device)\n# inp = torch.rand([4, 1, 256, 401])\n# tmp = model.forward(inp.to(device))\n# print(tmp.shape)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### PANNs","metadata":{}},{"cell_type":"code","source":"# class PANNsCNN14Att(nn.Module):\n# def __init__(self, sample_rate: int, window_size: int, hop_size: int,\n# mel_bins: int, fmin: int, fmax: int, classes_num: int):\n# super().__init__()\n\n# self.spec_layer = nnAudio.features.MelSpectrogram(\n# sr=cfg.sr, hop_length=cfg.hop_length, fmin=cfg.fmin, fmax=cfg.fmax, \n# n_fft=cfg.n_fft, n_mels=cfg.n_mels, \n# window='hann',center=True, pad_mode='reflect', trainable_mel=True, trainable_STFT=True).cuda()\n \n# self.cqt_layer = nnAudio.features.CQT(\n# sr=cfg.sr, hop_length=cfg.hop_length, fmin=cfg.fmin, fmax=cfg.fmax,\n# bins_per_octave=cfg.bins_per_octave, \n# window='hann', pad_mode='reflect', trainable=True).cuda()\n \n# self.backbone = timm.create_model(\n# model_name=model_name, pretrained=pretrained,\n# num_classes=len(LABELS), in_chans=1)\n \n\n# # Spec augmenter\n# self.spec_augmenter = SpecAugmentation(\n# time_drop_width=64,\n# time_stripes_num=2,\n# freq_drop_width=8,\n# freq_stripes_num=2)\n\n# self.bn0 = nn.BatchNorm2d(mel_bins)\n\n# self.conv_block1 = ConvBlock(in_channels=1, out_channels=64)\n# self.conv_block2 = ConvBlock(in_channels=64, out_channels=128)\n# self.conv_block3 = ConvBlock(in_channels=128, out_channels=256)\n# self.conv_block4 = ConvBlock(in_channels=256, out_channels=512)\n# self.conv_block5 = ConvBlock(in_channels=512, out_channels=1024)\n# self.conv_block6 = ConvBlock(in_channels=1024, out_channels=2048)\n\n# self.fc1 = nn.Linear(2048, 2048, bias=True)\n# self.att_block = AttBlock(2048, classes_num, activation='sigmoid')\n\n# self.init_weight()\n\n# def init_weight(self):\n# init_bn(self.bn0)\n# init_layer(self.fc1)\n \n# def cnn_feature_extractor(self, x):\n# x = self.conv_block1(x, pool_size=(2, 2), pool_type='avg')\n# x = F.dropout(x, p=0.2, training=self.training)\n# x = self.conv_block2(x, pool_size=(2, 2), pool_type='avg')\n# x = F.dropout(x, p=0.2, training=self.training)\n# x = self.conv_block3(x, pool_size=(2, 2), pool_type='avg')\n# x = F.dropout(x, p=0.2, training=self.training)\n# x = self.conv_block4(x, pool_size=(2, 2), pool_type='avg')\n# x = F.dropout(x, p=0.2, training=self.training)\n# x = self.conv_block5(x, pool_size=(2, 2), pool_type='avg')\n# x = F.dropout(x, p=0.2, training=self.training)\n# x = self.conv_block6(x, pool_size=(1, 1), pool_type='avg')\n# x = F.dropout(x, p=0.2, training=self.training)\n# return x\n \n# def preprocess(self, input, mixup_lambda=None):\n# # t1 = time.time()\n# x = self.spectrogram_extractor(input) # (batch_size, 1, time_steps, freq_bins)\n# x = self.logmel_extractor(x) # (batch_size, 1, time_steps, mel_bins)\n\n# frames_num = x.shape[2]\n\n# x = x.transpose(1, 3)\n# x = self.bn0(x)\n# x = x.transpose(1, 3)\n\n# if self.training:\n# x = self.spec_augmenter(x)\n\n# # Mixup on spectrogram\n# if self.training and mixup_lambda is not None:\n# x = do_mixup(x, mixup_lambda)\n# return x, frames_num\n \n\n# def forward(self, input, mixup_lambda=None):\n# \"\"\"\n# Input: (batch_size, data_length)\"\"\"\n# x, frames_num = self.preprocess(input, mixup_lambda=mixup_lambda)\n\n# # Output shape (batch size, channels, time, frequency)\n# x = self.cnn_feature_extractor(x)\n \n# # Aggregate in frequency axis\n# x = torch.mean(x, dim=3)\n\n# x1 = F.max_pool1d(x, kernel_size=3, stride=1, padding=1)\n# x2 = F.avg_pool1d(x, kernel_size=3, stride=1, padding=1)\n# x = x1 + x2\n\n# x = F.dropout(x, p=0.5, training=self.training)\n# x = x.transpose(1, 2)\n# x = F.relu_(self.fc1(x))\n# x = x.transpose(1, 2)\n# x = F.dropout(x, p=0.5, training=self.training)\n\n# (clipwise_output, norm_att, segmentwise_output) = self.att_block(x)\n# segmentwise_output = segmentwise_output.transpose(1, 2)\n\n# # Get framewise output\n# framewise_output = interpolate(segmentwise_output,\n# self.interpolate_ratio)\n# framewise_output = pad_framewise_output(framewise_output, frames_num)\n\n# output_dict = {\n# 'framewise_output': framewise_output,\n# 'clipwise_output': clipwise_output\n# }\n\n# return output_dict","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# get fold","metadata":{}},{"cell_type":"code","source":"# if isTrain:\nfrom sklearn.model_selection import KFold, StratifiedKFold, GroupKFold\nskf = StratifiedKFold(n_splits=cfg.nfolds, shuffle=True, random_state=cfg.seed)\nfor fold, (train_index, valid_index) in enumerate(skf.split(train_csv, train_csv['primary_label'])):\n train_csv.loc[valid_index, 'fold'] = int(fold)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if isTrain:\n train_csv.groupby(\"fold\", as_index=False)[\"primary_label\"].value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Trainer Utils","metadata":{}},{"cell_type":"markdown","source":"## set seed function","metadata":{}},{"cell_type":"code","source":"def set_random_seed(seed: int = 42, deterministic: bool = False):\n \"\"\"Set seeds\"\"\"\n random.seed(seed)\n np.random.seed(seed)\n os.environ[\"PYTHONHASHSEED\"] = str(seed)\n torch.manual_seed(seed)\n torch.cuda.manual_seed(seed) # type: ignore\n torch.backends.cudnn.deterministic = deterministic # type: ignore","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## INIT","metadata":{}},{"cell_type":"markdown","source":"### Loss","metadata":{}},{"cell_type":"code","source":"class BCEFocalLoss(nn.Module):\n def __init__(self, alpha=0.25, gamma=2.0):\n super().__init__()\n self.alpha = alpha\n self.gamma = gamma\n\n def forward(self, preds, targets):\n bce_loss = nn.BCEWithLogitsLoss(reduction='none')(preds, targets)\n probas = torch.sigmoid(preds)\n\n \n\n tmp = targets * self.alpha * (1. - probas)**self.gamma * bce_loss\n smp = (1. - targets) * probas**self.gamma * bce_loss\n \n loss = tmp + smp\n loss = loss.mean()\n return loss","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def initialization():\n model = BirdModel(model_name=cfg.model_name, pretrained=True, in_channels=3, num_classes=len(LABELS), pool=cfg.pool_type)\n \n if cfg.optimizer=='adan':\n optimizer = Adan(model.parameters(), lr=cfg.lr, betas=(0.02, 0.08, 0.01), weight_decay=cfg.weight_decay)\n else:\n optimizer = torch.optim.AdamW(params=model.parameters(), lr=cfg.lr, weight_decay=cfg.weight_decay)\n \n scheduler = torch.optim.lr_scheduler.OneCycleLR(\n optimizer=optimizer, epochs=cfg.max_epoch,\n pct_start=0.0, steps_per_epoch=len(train_dataloader),\n max_lr=cfg.lr, div_factor=25, final_div_factor=4.0e-01\n )\n \n scaler = amp.GradScaler(enabled=cfg.enable_amp)\n if cfg.loss_type == \"BCEWithLogitsLoss\":\n loss_func = torch.nn.BCEWithLogitsLoss()\n elif cfg.loss_type == \"BCEFocalLoss\":\n loss_func = BCEFocalLoss(alpha=1)\n \n \n \n # loss_func = torch.nn.CrossEntropyLoss()\n # loss_func = torch.nn.BCELoss()\n\n return model.to(device), optimizer, scheduler, scaler, loss_func.to(device)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn import metrics\nfrom sklearn.metrics import mean_squared_error, roc_auc_score","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## trainer function","metadata":{}},{"cell_type":"code","source":"def train_one_loop(model, optimizer, scaler, scheduler, dataloader, loss_fn):\n trainloss = 0; model.train()\n\n count = 0\n for idx, (data, label) in enumerate(tqdm(dataloader,leave=False ,desc=\"[train]\")):\n # label = label.reshape(-1, len(LABELS))\n \n data, label = data.to(device), label.to(device)\n \n optimizer.zero_grad()\n with amp.autocast(cfg.enable_amp, dtype=torch.bfloat16):\n # with amp.autocast(cfg.enable_amp):\n pred = model.forward(data)\n loss = loss_fn(pred, label)\n\n scaler.scale(loss).backward()\n scaler.step(optimizer)\n scaler.update()\n\n scheduler.step()\n \n trainloss += loss.item()\n # print(idx, loss.item())\n # if cfg.wandb == True:\n # wandb.log({f\"train_loss\": loss.item(), f\"lr\":scheduler.get_lr()[0]})\n del data, label, loss\n count += 1\n # if count == 300:\n # break\n trainloss /= len(dataloader)\n if cfg.wandb == True:\n wandb.log({f\"train_loss\": trainloss, f\"lr\":scheduler.get_lr()[0]})\n return model, optimizer, scaler, scheduler, trainloss\n\n\ndef mixup_one_loop(model, optimizer, scaler, scheduler, dataloader, loss_fn):\n trainloss = 0; model.train()\n\n count = 0\n for idx, (data, label) in enumerate(tqdm(dataloader,leave=False ,desc=\"[train]\")):\n if np.random.random()>cfg.aug_spec_mixup_prob:\n data, label = mixup(data=data, targets=label, alpha=cfg.alpha, mode=\"other_wave\")\n else:\n data, label = spec_mixup(data=data, targets=label)\n data, label = data.to(device), label.to(device)\n \n optimizer.zero_grad()\n with amp.autocast(cfg.enable_amp, dtype=torch.bfloat16):\n # with amp.autocast(cfg.enable_amp):\n pred = model.forward(data)\n loss = loss_fn(pred, label)\n\n scaler.scale(loss).backward()\n scaler.step(optimizer)\n scaler.update()\n\n scheduler.step()\n \n trainloss += loss.item()\n # print(idx, loss.item())\n # if cfg.wandb == True:\n # wandb.log({f\"lr\":scheduler.get_lr()[0]})\n del data, label, loss\n count += 1\n # if count == 300:\n # break\n trainloss /= len(dataloader)\n if cfg.wandb == True:\n wandb.log({f\"train_loss\": trainloss, f\"lr\":scheduler.get_lr()[0]})\n return model, optimizer, scaler, scheduler, trainloss\n\n\ndef evaluate_validation(model, dataloader, loss_fn):\n validloss=0\n model.eval()\n\n preds, trues, targets = [], [], []\n \n for idx, (data, label) in enumerate(tqdm(dataloader,leave=False ,desc=\"[valid]\")):\n # label = label.reshape(-1, len(LABELS))\n\n d = data[0].unsqueeze(1)\n label = label[0]\n \n d = d.to(device)\n # with amp.autocast(cfg.enable_amp):\n pred = model.forward(d)\n\n preds.extend(pred.detach().cpu())\n trues.extend(label)\n targets.extend(label.argmax(axis=1))\n \n #======================== metrics ========================#\n # y_preds = torch.stack(preds)\n t = torch.stack(preds)\n t = torch.sigmoid(t)\n targets = torch.tensor(targets)\n y_trues = torch.stack(trues)\n\n\n validloss = loss_fn(torch.stack(preds), torch.stack(trues))\n # # print(idx, loss)\n # # wandb.log({\"valid_loss\": loss})\n\n # validloss /= len(dataloader)\n \n # sk_f1 = metrics.f1_score(np.array(y_trues), np.array(t), average=\"micro\")\n sk_f1_30 = metrics.f1_score(np.array(y_trues), np.array(t) > 0.30, average=\"micro\")\n sk_f1_50 = metrics.f1_score(np.array(y_trues), np.array(t) > 0.50, average=\"micro\")\n \n auc = multiclass_auroc(input=t, target=targets, num_classes=len(LABELS),\n average=\"macro\").item()\n\n # auc_micro = multiclass_auroc(input=t, target=targets, num_classes=len(LABELS),\n # average=\"none\").item()\n\n prec = multiclass_precision(input=t, target=targets, num_classes=len(LABELS),\n average=\"macro\").item()\n # rec = multiclass_recall(input=t, target=targets, num_classes=len(LABELS),\n # average=\"macro\").item()\n \n # acc = multilabel_accuracy(input=t, target=targets).item()\n\n f1 = multiclass_f1_score(input=t, target=torch.tensor(targets), num_classes=len(LABELS),\n average=\"micro\").item()\n\n f1_macro = multiclass_f1_score(input=t, target=torch.tensor(targets), num_classes=len(LABELS),\n average=\"macro\").item()\n\n t_03 = (t>0.3).int()\n t_03 = torch.tensor(t_03, dtype=torch.int64)\n f1_03 = multiclass_f1_score(input=t_03, target=torch.tensor(targets), num_classes=len(LABELS), \n average=\"micro\").item()\n\n t_05 = (t>0.5).int()\n t_05 = torch.tensor(t_05, dtype=torch.int64)\n f1_05 = multiclass_f1_score(input=t_05, target=torch.tensor(targets), num_classes=len(LABELS), \n average=\"micro\").item()\n\n if cfg.wandb == True:\n wandb.log({f\"valid_loss\": validloss,\n f\"AUC\":auc,\n # \"auc_micro\":auc_micro,\n \"precision\":prec, \n # \"recall\":rec, \n # \"accuracy\":acc,\n f\"F1\":f1,\n \"F1_macro\":f1_macro,\n f\"F1 30%\":f1_03,\n f\"F1 50%\":f1_05})\n return validloss, auc, f1, f1_03, f1_05, sk_f1_30, sk_f1_50","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## training","metadata":{}},{"cell_type":"code","source":"if isTrain == True:\n tmp_params = dict(vars(config))\n del tmp_params['__module__'],tmp_params['__dict__'],tmp_params['__weakref__'],tmp_params['__doc__']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# cfg.wandb = False","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### oversampling","metadata":{}},{"cell_type":"code","source":"def get_oversampled_df(df):\n \n new_df = [df]\n\n low_sample_birds = df[\"primary_label\"].value_counts()[df[\"primary_label\"].value_counts() < cfg.oversample_threthold].index\n for bird in low_sample_birds:\n tmp = df[df[\"primary_label\"] == bird]\n data_num = len(tmp)\n \n tiles = 1 + cfg.oversample_threthold // data_num\n \n tile_df = []\n for i in range(tiles):\n tile_df.append(tmp)\n \n tiled_df = pd.concat(tile_df)\n piece = tiled_df[data_num:cfg.oversample_threthold]\n new_df.append(piece)\n \n return pd.concat(new_df)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### in train","metadata":{}},{"cell_type":"code","source":"if isTrain == True:\n set_random_seed(seed=42)\n \n \n if cfg.wandb == True:\n wandb.init(project=p_name, name=f\"{name}\",\n config=tmp_params)\n \n # for fold in range(cfg.nfolds):\n for fold in cfg.inference_folds:\n train_ = train_csv.loc[train_csv[\"fold\"]!=fold]\n\n if cfg.oversample == True:\n train = get_oversampled_df(df=train_)\n else:\n train = train_\n \n augme_dataset = BirdCLEF_Dataset(df=train, augmentation=True, mode='train')\n augme_dataloader = torch.utils.data.DataLoader(dataset=augme_dataset, batch_size=cfg.train_batchsize, shuffle=True)\n\n train_dataset = BirdCLEF_Dataset(df=train, augmentation=False, mode='train')\n train_dataloader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=cfg.train_batchsize, shuffle=True)\n \n valid = train_csv.loc[train_csv[\"fold\"]==fold]\n valid_dataset = BirdCLEF_Dataset(df=valid, augmentation=False, mode='valid')\n valid_dataloader = torch.utils.data.DataLoader(dataset=valid_dataset, batch_size=cfg.valid_batchsize, shuffle=False)\n \n model, optimizer, scheduler, scaler, loss_func = initialization()\n \n \n best_f1 = 0\n best_auc = 0\n best_loss = 1.00000\n for e in range(cfg.max_epoch):\n start_time = time.time()\n if e < cfg.aug_epoch:\n if cfg.aug_spec_mixup > np.random.random():\n model, optimizer, scaler, shcheduler, train_loss = mixup_one_loop(model=model,optimizer=optimizer,scaler=scaler, \n scheduler=scheduler,dataloader=augme_dataloader, loss_fn=loss_func)\n else:\n model, optimizer, scaler, shcheduler, train_loss = train_one_loop(model=model,optimizer=optimizer,scaler=scaler, \n scheduler=scheduler,dataloader=augme_dataloader, loss_fn=loss_func)\n\n else:\n model, optimizer, scaler, shcheduler, train_loss = train_one_loop(model=model,optimizer=optimizer,scaler=scaler, \n scheduler=scheduler,dataloader=train_dataloader, loss_fn=loss_func)\n \n valid_loss, auc, f1, f1_03, f1_05, sk_f1_30, sk_f1_50 = evaluate_validation(model=model, dataloader=valid_dataloader, loss_fn=loss_func)\n # print(f\"epoch {e} , train_loss is {train_loss}, valid_loss is {valid_loss}\")\n \n if best_loss > valid_loss:\n end_time = time.time()\n print(f\"[epoch {str(e).zfill(2)}] AUC{auc: .4f}, F1{f1: .4f}, F1_03{f1_03: .4f}, F1_05{f1_05: .4f}\")\n print(f\"[epoch {str(e).zfill(2)}] SKF1_03{sk_f1_30: .4f}, SKF1_05{sk_f1_50: .4f}\")\n print(f\"[epoch {str(e).zfill(2)}] valid_loss {valid_loss: .6f}\")\n print(f\"[epoch {str(e).zfill(2)}] update loss {best_loss: .6f} --> {valid_loss: .6f} {(end_time - start_time): .1f}[s]\")\n print(f\"[epoch {str(e).zfill(2)}] update auc score {best_auc: .6f} --> {auc: .6f} {(end_time - start_time): .1f}[s]\")\n model_name = f'{name}/checkpoint/fold_{fold}_snapshot_epoch_{str(e).zfill(2)}.pth'\n best_model = model\n best_loss = valid_loss\n best_auc = auc\n best_f1 = f1\n else:\n end_time = time.time()\n print(f\"[epoch {str(e).zfill(2)}] NOT update loss {best_loss: .6f} <-- {valid_loss: .6f} {(end_time - start_time): .1f}[s]\")\n print(f\"[epoch {str(e).zfill(2)}] NOT update score {best_auc: .6f} <-- {auc: .6f} {(end_time - start_time): .1f}[s]\")\n\n if cfg.wandb == True:\n wandb.log({f\"best_loss\": best_loss,\n f\"best_f1\": best_f1,\n f\"best_auc\":best_auc})\n\n torch.save(best_model.state_dict(), model_name)\n \n del model, best_model\n gc.collect()\n torch.cuda.empty_cache()\n print(\"--\")\n # break","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# simple cv","metadata":{}},{"cell_type":"code","source":"# if isTrain == True:\n# print(f\"fold cv : {cross_validation.values()}\")\n# print(f\"cv : {round (torch.tensor(list(cross_validation.values())).mean().item(), 5 ) }\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# inference","metadata":{}},{"cell_type":"markdown","source":"## load models","metadata":{}},{"cell_type":"code","source":"models = dict()\nmodels_names = dict()\n# for fold in range(cfg.nfolds):\nfor fold in cfg.inference_folds:\n if KAGGLE == True:\n bestmodel_path = sorted(glob.glob(f\"/kaggle/input/{name}/checkpoint/fold_{fold}*.pth\"))[-1]\n else:\n bestmodel_path = sorted(glob.glob(f\"{name}/checkpoint/fold_{fold}*.pth\"))[-1]\n print(bestmodel_path)\n model = BirdModel(model_name=cfg.model_name, pretrained=False, in_channels=1, num_classes=len(LABELS))\n model.load_state_dict(torch.load(bestmodel_path, map_location=torch.device('cpu')))\n model = model.eval()\n models[fold] = model\n\n models_names[fold] = bestmodel_path.split(\".\")[0]+\".onnx\"\n print(models_names[fold])","metadata":{"scrolled":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if KAGGLE == True:\n test_audio_dir = f\"{cfg.dir}test_soundscapes/\"\n file_list = glob.glob(test_audio_dir+\"*.ogg\")\n file_list = sorted(file_list)\n\nif KAGGLE == False:\n test_audio_dir = f\"{cfg.dir}unlabeled_soundscapes/\"\n file_list = glob.glob(test_audio_dir+\"*.ogg\")\n file_list = sorted(file_list)[:3]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_dataset = BirdCLEF_Dataset(df=file_list, mode=\"test\")\ntest_dataloader = torch.utils.data.DataLoader(dataset=test_dataset, \n batch_size=1, \n shuffle=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if KAGGLE == False:\n print(test_dataset[0].shape)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# ONNX","metadata":{}},{"cell_type":"markdown","source":"## set onnx config","metadata":{}},{"cell_type":"code","source":"input_tensor = torch.randn((48, 1, cfg.n_mels, cfg.size_x+1)) # input shape\noutput_names=['output']\ninput_names=[\"x\"]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## export onnx model","metadata":{}},{"cell_type":"code","source":"if KAGGLE == False:\n # for fold in range(cfg.nfolds):\n for fold in cfg.inference_folds:\n torch.onnx.export(model=models[fold].eval(),args=(input_tensor), \n input_names=input_names, output_names=output_names,f=models_names[fold])\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## model convert from pytorch to onnx","metadata":{}},{"cell_type":"code","source":"import onnx\nimport onnxruntime as ort","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# models_names = []\nmodels_names = dict()\n# for fold in range(cfg.nfolds):\nfor fold in cfg.inference_folds:\n if KAGGLE == True:\n onnxmodel_path = sorted(glob.glob(f\"/kaggle/input/{name}/checkpoint/fold_{fold}*.onnx\"))[-1]\n else:\n onnxmodel_path = sorted(glob.glob(f\"{name}/checkpoint/fold_{fold}*.onnx\"))[-1]\n print(onnxmodel_path)\n# models_names.append(onnxmodel_path)\n models_names[fold] = onnxmodel_path","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"onnx_sessions = dict()\n# for fold in range(cfg.nfolds):\nfor fold in cfg.inference_folds:\n\n onnx_model = onnx.load(models_names[fold])\n onnx_model_graph = onnx_model.graph\n onnx_session = ort.InferenceSession(onnx_model.SerializeToString())\n\n onnx_sessions[fold] = onnx_session","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# outputs = onnx_session.run(output_names, {input_names[0]: test_dataset[0].numpy()})[0]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"start_time = time.time()\n\npredictions = []\nfor data in tqdm(test_dataloader):\n \n preds = []\n \n# for fold, session in enumerate(onnx_sessions):\n for fold in cfg.inference_folds:\n session = onnx_sessions[fold]\n pred = session.run(output_names, {input_names[0]: data[0].numpy()})[0]\n \n #pred = torch.sigmoid(torch.tensor(pred))\n pred = torch.tensor(pred)\n preds.append(pred)\n preds_per_batch = torch.stack(preds, axis=0).mean(axis=0)\n pred = torch.sigmoid(preds_per_batch)\n \n predictions.extend(preds_per_batch)\n \nif len(predictions)>0:\n predictions = torch.stack(predictions)\nelse:\n predictions = predictions\nend_time = time.time()\nuse_time = end_time - start_time","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(f\"{cfg.inference_folds}fold + 3ogg is {round(use_time,1)}[s]\")\nprint(f\"{cfg.inference_folds}fold + 1,100ogg is {round(1100*use_time/3,1)}[s], {round(1100*use_time/3/60,1)}[m]\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# # fold_mean = np.zeros(predictions_dict[0].shape)\n# fold_mean = []\n# for key in predictions_dict.keys():\n# fold_mean.append(predictions_dict[key])\n# fold_mean = np.mean(fold_mean, axis=0)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"bird_cols = sample_submission.columns[1:]\ndf = pd.DataFrame(columns=['row_id']+list(bird_cols))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"row_list = []\nfor file in file_list:\n dataname = file.split(\"/\")[-1][:-4]\n for i in range(int(4*60/5)):\n row = f\"{dataname}_{(i+1)*5}\"\n row_list.append(row)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df['row_id'] = row_list","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if len(predictions) < 1:\n pass\nelse:\n df[bird_cols] = predictions","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.head() ","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.to_csv(\"submission.csv\", index=False) ","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df[:48].set_index(\"row_id\").max().T.plot(kind=\"bar\", figsize=(24,4))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if KAGGLE == False:\n def get_fold_data(fold):\n \n valid = train_csv.loc[train_csv[\"fold\"]==fold]\n filelist = [f\"{cfg.dir}train_audio/{name}\" for name in valid[\"filename\"]]\n \n clearn_dataset = BirdCLEF_Dataset(df=filelist, augmentation=False, mode='clean')\n return clearn_dataset, valid","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if KAGGLE == False:\n def predict_and_visualize(data_index):\n use_fold = 4\n c_dataset, df = get_fold_data(fold=use_fold)\n model = models[use_fold].to(device)\n \n prediction = model.forward(c_dataset[data_index][0].to(device)).cpu().detach()\n prediction = torch.sigmoid(prediction)\n \n df_index = df.index[data_index]\n true_labels = df.loc[df_index, \"new_target\"].split()\n true_guide_pos = [LABELS.index(l)+0.5 for l in true_labels]\n \n fig, ax = plt.subplots(figsize=(24, 1.5))\n sns.heatmap(prediction, cmap=\"jet\", vmin=0, vmax=1)\n ax.set_xticks(np.arange(0,182))\n ax.set_xticklabels(LABELS, fontsize=8)\n \n ax.set_yticks(np.arange(0,prediction.shape[0]))\n ax.set_yticklabels(np.arange(1,1+prediction.shape[0])*5)\n \n for pos in true_guide_pos:\n ax.axvline(x=pos, color=\"red\", ls=\"--\", lw=0.9)\n \n plt.xticks(ticks=np.arange(0,182), labels=LABELS, color='black') # 元の設定を保持\n plt.title(c_dataset[data_index][1])\n plt.show()\n\n return prediction","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if KAGGLE == False:\n\n N = len(train_csv.loc[train_csv[\"fold\"]==fold])//30\n print(N)\n \n predict_and_visualize(data_index=0)\n predict_and_visualize(data_index=1)\n predict_and_visualize(data_index=2)\n predict_and_visualize(data_index=3)\n predict_and_visualize(data_index=4)\n\n\n for i in range(N):\n try:\n predict_and_visualize(data_index=i*30)\n except:\n pass","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"scrolled":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if KAGGLE == False:\n model.eval().cuda();\n \n preds, trues, targets = [], [], []\n for idx, (data, label) in enumerate(tqdm(valid_dataloader, leave=False ,desc=\"[valid]\")):\n data = data.to(device)\n label = label[0]\n # with amp.autocast(cfg.enable_amp):\n pred = model.forward(data[0].unsqueeze(1))\n \n preds.extend(pred.detach().cpu())\n trues.extend(label)\n targets.extend(label.argmax(axis=1))\n\n t = torch.stack(preds)\n targets = torch.tensor(targets)\n\n auc = multiclass_auroc(input=torch.sigmoid(t), target=targets, num_classes=len(LABELS),\n average=None)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if KAGGLE == False:\n train_[\"primary_label\"].value_counts().sort_index().plot(kind=\"bar\", figsize=(20,4))\n plt.scatter(x=LABELS, y=auc*100, color=\"r\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if KAGGLE == False:\n train[\"primary_label\"].value_counts().sort_index().plot(kind=\"bar\", figsize=(20,4))\n plt.scatter(x=LABELS, y=auc*100, color=\"r\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if KAGGLE == False:\n valid[\"primary_label\"].value_counts().sort_index().plot(kind=\"bar\", figsize=(20,4))\n plt.scatter(x=LABELS, y=auc*100, color=\"r\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"if KAGGLE == False:\n fig, axes = plt.subplots(figsize=(24,62), ncols=6, nrows=31, tight_layout=True)\n \n axs = axes.ravel()\n\n LABELS_COUNT = train_csv[\"primary_label\"].value_counts().sort_index().to_numpy()\n LABELS_OCCUPY = train_csv[\"primary_label\"].value_counts(normalize=True).sort_index().to_numpy()\n \n oof_predictions = torch.sigmoid(torch.stack(preds))\n oof_predictions = pd.DataFrame(oof_predictions, columns=LABELS)\n \n oof_predictions.head()\n \n oof_trues = torch.stack(trues)\n oof_trues = pd.DataFrame(oof_trues, columns=LABELS)\n \n oof_trues.head()\n LABEL_df = pd.DataFrame([LABELS,LABELS_COUNT]).T\n LABEL_df.columns = [\"name\", \"count\"]\n LABEL_df = LABEL_df.sort_values(\"count\").reset_index(drop=True)\n iter = len(LABEL_df)\n \n for idx in range(iter):\n ax = axs[idx]\n \n l = LABEL_df.loc[idx, \"name\"]\n count = LABEL_df.loc[idx, \"count\"]\n \n tmp = pd.concat([oof_trues[f\"{l}\"], oof_predictions[f\"{l}\"]], axis=1)\n tmp.columns = [\"label\", f\"{l}_prob\"]\n \n tmp[\"10_label\"] = (10*tmp[\"label\"]).astype(int)\n \n sns.boxplot(tmp, x=f\"{l}_prob\", y=\"10_label\",orient=\"h\", width=0.5, ax=ax)\n ax.set(title=f\"{l}_{count}\", xlim=(0,1))\n \n\n \n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}