{"metadata":{"colab":{"provenance":[]},"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"language_info":{"name":"python","version":"3.10.14","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":{"f9f990310b124fb58c460653f923b478":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_2b4c8c1e98bb404bbcc26792f36ea580","IPY_MODEL_b8d16616402c45069c46e3085c52e280","IPY_MODEL_90bc5e68a45946e58f001d6110f02aef"],"layout":"IPY_MODEL_951b39c56a0b4ccd9eebc3689afe4e87"}},"2b4c8c1e98bb404bbcc26792f36ea580":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_f4b11bbd15fe4ddc997454950417767f","placeholder":"​","style":"IPY_MODEL_3e6d76f9c1bb4525a252755092b8c57e","value":"preprocessor_config.json: 100%"}},"b8d16616402c45069c46e3085c52e280":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_320042c467644681bec3f507d3bebb19","max":538,"min":0,"orientation":"horizontal","style":"IPY_MODEL_3c7aae3b84e84c1b9e989ac0a133544f","value":538}},"90bc5e68a45946e58f001d6110f02aef":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_8f38d6d2890044fba381cf221faa647c","placeholder":"​","style":"IPY_MODEL_74272e7feba94e2885fa31a420e5547f","value":" 538/538 [00:00<00:00, 11.0kB/s]"}},"951b39c56a0b4ccd9eebc3689afe4e87":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"f4b11bbd15fe4ddc997454950417767f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"3e6d76f9c1bb4525a252755092b8c57e":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"320042c467644681bec3f507d3bebb19":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"3c7aae3b84e84c1b9e989ac0a133544f":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"8f38d6d2890044fba381cf221faa647c":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"74272e7feba94e2885fa31a420e5547f":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"d0417ff41db2462e8cdb7df4b98bcfed":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_f558ea8c8ba442d2ae3f4dd2688aa79b","IPY_MODEL_4ce2f9fb3fb14986a7033a33fb8ef91e","IPY_MODEL_8bb6a9f14f6e4f8792c366ca6dd0d5ed"],"layout":"IPY_MODEL_eff7293842bb4cb0a24c567790f0b424"}},"f558ea8c8ba442d2ae3f4dd2688aa79b":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_6a22ecb94fb34d569c9823a5226991c2","placeholder":"​","style":"IPY_MODEL_0d4c319249324793b9e7ccdcf141c329","value":"config.json: 100%"}},"4ce2f9fb3fb14986a7033a33fb8ef91e":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_dddff6405aca4175aaf77d869e560003","max":82540,"min":0,"orientation":"horizontal","style":"IPY_MODEL_0dab7134797146ffa9d314d7d31cc5f6","value":82540}},"8bb6a9f14f6e4f8792c366ca6dd0d5ed":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_2be723d7127d4ab387b100dd8c905b67","placeholder":"​","style":"IPY_MODEL_4279a5fec34c41fe98987e2bdcae02db","value":" 82.5k/82.5k [00:00<00:00, 1.29MB/s]"}},"eff7293842bb4cb0a24c567790f0b424":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"6a22ecb94fb34d569c9823a5226991c2":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"0d4c319249324793b9e7ccdcf141c329":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"dddff6405aca4175aaf77d869e560003":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"0dab7134797146ffa9d314d7d31cc5f6":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"2be723d7127d4ab387b100dd8c905b67":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"4279a5fec34c41fe98987e2bdcae02db":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"2d7d5fd88b514644a796313081162f63":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_3ea2691bc13044d796579717967105b5","IPY_MODEL_617710233c0d4b1e9bb47a0222f7fd94","IPY_MODEL_68e31cc3131b44868208fcf3ccbc91f1"],"layout":"IPY_MODEL_ca452027ae9d4c29b2f4f36c1500e708"}},"3ea2691bc13044d796579717967105b5":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_19b0e1bfeefa4a8882c402f044be11c9","placeholder":"​","style":"IPY_MODEL_e5ed8e6a92dc4616a9923d7c5fb0e6cc","value":"model.safetensors: 100%"}},"617710233c0d4b1e9bb47a0222f7fd94":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_38dd3a5c37d94b588bf5c20bce78ec40","max":866052064,"min":0,"orientation":"horizontal","style":"IPY_MODEL_6731a35d8cfe4f5ebc4b94ff26d78dde","value":866052064}},"68e31cc3131b44868208fcf3ccbc91f1":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_f356bbf3c5834e1191e9a984cf60582c","placeholder":"​","style":"IPY_MODEL_e64ee29bb16d45be86fdc690c19d4f94","value":" 866M/866M [00:12<00:00, 71.6MB/s]"}},"ca452027ae9d4c29b2f4f36c1500e708":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"19b0e1bfeefa4a8882c402f044be11c9":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"e5ed8e6a92dc4616a9923d7c5fb0e6cc":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"38dd3a5c37d94b588bf5c20bce78ec40":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"6731a35d8cfe4f5ebc4b94ff26d78dde":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"f356bbf3c5834e1191e9a984cf60582c":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"e64ee29bb16d45be86fdc690c19d4f94":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"c7dcd70a6572439098fc8c63313a8b37":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_77598a53d168401c820e0f9aaeedf31d","IPY_MODEL_52cf5616aa2148a7b7512a243731f8f6","IPY_MODEL_a7045ec35b934020a792caafefa08522"],"layout":"IPY_MODEL_e11539e2516242378a722d513dd4dcf5"}},"77598a53d168401c820e0f9aaeedf31d":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_c69b36d90b4e42b1abc2915dea91b44d","placeholder":"​","style":"IPY_MODEL_30ddae8d0922403e8c6c0cf737f491fd","value":"  2%"}},"52cf5616aa2148a7b7512a243731f8f6":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"danger","description":"","description_tooltip":null,"layout":"IPY_MODEL_fba4ffa0f237459497993e01b46e4ae2","max":958,"min":0,"orientation":"horizontal","style":"IPY_MODEL_847bc5f4340d4053a5ece6fffc519f64","value":16}},"a7045ec35b934020a792caafefa08522":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_4190cc29c2cd460c9e94113c9844ea78","placeholder":"​","style":"IPY_MODEL_a22293b721ef4d788bd6c1ad7cbe45a2","value":" 16/958 [10:10<9:33:38, 36.54s/it]"}},"e11539e2516242378a722d513dd4dcf5":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"c69b36d90b4e42b1abc2915dea91b44d":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"30ddae8d0922403e8c6c0cf737f491fd":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"fba4ffa0f237459497993e01b46e4ae2":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"847bc5f4340d4053a5ece6fffc519f64":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"4190cc29c2cd460c9e94113c9844ea78":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a22293b721ef4d788bd6c1ad7cbe45a2":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}}}},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":86142,"databundleVersionId":9786425,"sourceType":"competition"}],"dockerImageVersionId":30787,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"!pip install evaluate","metadata":{"id":"g9hXf4Hz51ig","outputId":"8ac45382-fe30-43c3-a637-4cabd1b0e25b","execution":{"iopub.status.busy":"2024-10-10T17:40:23.614853Z","iopub.execute_input":"2024-10-10T17:40:23.615557Z","iopub.status.idle":"2024-10-10T17:40:36.608581Z","shell.execute_reply.started":"2024-10-10T17:40:23.615515Z","shell.execute_reply":"2024-10-10T17:40:36.607392Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import json\nimport torch\nimport datasets\nimport requests\nimport evaluate\nimport numpy as np\nimport huggingface_hub\nfrom PIL import Image\nimport albumentations as A\nfrom tqdm.auto import tqdm\nimport matplotlib.pyplot as plt\nfrom typing import Tuple, Any\nfrom dataclasses import dataclass\nfrom datasets import load_dataset\nimport matplotlib.patches as mpatches\nfrom huggingface_hub import hf_hub_download\nfrom torch.utils.data import Dataset, DataLoader\nfrom transformers import (\n Mask2FormerImageProcessor,\n AutoImageProcessor,\n Mask2FormerForUniversalSegmentation,\n)\n\ntorch.manual_seed(42)","metadata":{"id":"F2Oi8CF655JL","outputId":"6d1c434f-e432-4890-8154-1bb390709c3b"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os","metadata":{"execution":{"iopub.status.busy":"2024-10-10T17:41:03.349098Z","iopub.execute_input":"2024-10-10T17:41:03.349779Z","iopub.status.idle":"2024-10-10T17:41:03.354241Z","shell.execute_reply.started":"2024-10-10T17:41:03.349731Z","shell.execute_reply":"2024-10-10T17:41:03.353279Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_folder=\"/kaggle/input/iitg-ai-overnight-hackathon-2024/dataset/dataset/train\"\ntrain_path = []\n\nfor root, dirs, files in os.walk(train_folder):\n for file in files:\n train_path.append(os.path.join(root, file))","metadata":{"execution":{"iopub.status.busy":"2024-10-10T17:41:03.517186Z","iopub.execute_input":"2024-10-10T17:41:03.517804Z","iopub.status.idle":"2024-10-10T17:41:05.286009Z","shell.execute_reply.started":"2024-10-10T17:41:03.517769Z","shell.execute_reply":"2024-10-10T17:41:05.285235Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"mask_path = []\nfor image_path in train_path:\n mask_file = image_path.replace('leftImg8bit.jpg', 'gtFine_labellevel3Ids.png') \n mask_file =mask_file.replace('train', 'labels') \n mask_path.append(mask_file)","metadata":{"execution":{"iopub.status.busy":"2024-10-10T17:41:09.023990Z","iopub.execute_input":"2024-10-10T17:41:09.024804Z","iopub.status.idle":"2024-10-10T17:41:09.036213Z","shell.execute_reply.started":"2024-10-10T17:41:09.024763Z","shell.execute_reply":"2024-10-10T17:41:09.035344Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"combined_tuples = [(train_path[i], mask_path[i]) for i in range(len(train_path))]\nimport pandas as pd\ndf= pd.DataFrame(combined_tuples)","metadata":{"execution":{"iopub.status.busy":"2024-10-10T17:41:32.712051Z","iopub.execute_input":"2024-10-10T17:41:32.713144Z","iopub.status.idle":"2024-10-10T17:41:33.641147Z","shell.execute_reply.started":"2024-10-10T17:41:32.713099Z","shell.execute_reply":"2024-10-10T17:41:33.640363Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df=df.rename(columns={0:\"image\", 1:\"mask\"})","metadata":{"execution":{"iopub.status.busy":"2024-10-10T17:54:12.244756Z","iopub.execute_input":"2024-10-10T17:54:12.245127Z","iopub.status.idle":"2024-10-10T17:54:12.251001Z","shell.execute_reply.started":"2024-10-10T17:54:12.245089Z","shell.execute_reply":"2024-10-10T17:54:12.249918Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Label:\n def __init__(self, name, id, csId, csTrainId, level4id, level3Id, category, level2Id, level1Id, hasInstances, ignoreInEval, color):\n self.name = name\n self.id = id\n self.csId = csId\n self.csTrainId = csTrainId\n self.level4id = level4id\n self.level3Id = level3Id\n self.category = category\n self.level2Id = level2Id\n self.level1Id = level1Id\n self.hasInstances = hasInstances\n self.ignoreInEval = ignoreInEval\n self.color = color\n\n# Your label definitions here (from your provided list)\n\nlabels_details = [\n # name id csId csTrainId level4id level3Id category level2Id level1Id hasInstances ignoreInEval color\n Label( 'road' , 0 , 7 , 0 , 0 , 0 , 'drivable' , 0 , 0 , False , False , (128, 64,128) ),\n Label( 'parking' , 1 , 9 , 255 , 1 , 1 , 'drivable' , 1 , 0 , False , False , (250,170,160) ),\n Label( 'drivable fallback' , 2 , 255 , 255 , 2 , 1 , 'drivable' , 1 , 0 , False , False , ( 81, 0, 81) ),\n Label( 'sidewalk' , 3 , 8 , 1 , 3 , 2 , 'non-drivable' , 2 , 1 , False , False , (244, 35,232) ),\n Label( 'rail track' , 4 , 10 , 255 , 3 , 3 , 'non-drivable' , 3 , 1 , False , False , (230,150,140) ),\n Label( 'non-drivable fallback', 5 , 255 , 9 , 4 , 3 , 'non-drivable' , 3 , 1 , False , False , (152,251,152) ),\n Label( 'person' , 6 , 24 , 11 , 5 , 4 , 'living-thing' , 4 , 2 , True , False , (220, 20, 60) ),\n Label( 'animal' , 7 , 255 , 255 , 6 , 4 , 'living-thing' , 4 , 2 , True , True , (246, 198, 145)),\n Label( 'rider' , 8 , 25 , 12 , 7 , 5 , 'living-thing' , 5 , 2 , True , False , (255, 0, 0) ),\n Label( 'motorcycle' , 9 , 32 , 17 , 8 , 6 , '2-wheeler' , 6 , 3 , True , False , ( 0, 0,230) ),\n Label( 'bicycle' , 10 , 33 , 18 , 9 , 7 , '2-wheeler' , 6 , 3 , True , False , (119, 11, 32) ),\n Label( 'autorickshaw' , 11 , 255 , 255 , 10 , 8 , 'autorickshaw' , 7 , 3 , True , False , (255, 204, 54) ),\n Label( 'car' , 12 , 26 , 13 , 11 , 9 , 'car' , 7 , 3 , True , False , ( 0, 0,142) ),\n Label( 'truck' , 13 , 27 , 14 , 12 , 10 , 'large-vehicle' , 8 , 3 , True , False , ( 0, 0, 70) ),\n Label( 'bus' , 14 , 28 , 15 , 13 , 11 , 'large-vehicle' , 8 , 3 , True , False , ( 0, 60,100) ),\n Label( 'caravan' , 15 , 29 , 255 , 14 , 12 , 'large-vehicle' , 8 , 3 , True , True , ( 0, 0, 90) ),\n Label( 'trailer' , 16 , 30 , 255 , 15 , 12 , 'large-vehicle' , 8 , 3 , True , True , ( 0, 0,110) ),\n Label( 'train' , 17 , 31 , 16 , 15 , 12 , 'large-vehicle' , 8 , 3 , True , True , ( 0, 80,100) ),\n Label( 'vehicle fallback' , 18 , 355 , 255 , 15 , 12 , 'large-vehicle' , 8 , 3 , True , False , (136, 143, 153)),\n Label( 'curb' , 19 ,255 , 255 , 16 , 13 , 'barrier' , 9 , 4 , False , False , (220, 190, 40)),\n Label( 'wall' , 20 , 12 , 3 , 17 , 14 , 'barrier' , 9 , 4 , False , False , (102,102,156) ),\n Label( 'fence' , 21 , 13 , 4 , 18 , 15 , 'barrier' , 10 , 4 , False , False , (190,153,153) ),\n Label( 'guard rail' , 22 , 14 , 255 , 19 , 16 , 'barrier' , 10 , 4 , False , False , (180,165,180) ),\n Label( 'billboard' , 23 , 255 , 255 , 20 , 17 , 'structures' , 11 , 4 , False , False , (174, 64, 67) ),\n Label( 'traffic sign' , 24 , 20 , 7 , 21 , 18 , 'structures' , 11 , 4 , False , False , (220,220, 0) ),\n Label( 'traffic light' , 25 , 19 , 6 , 22 , 19 , 'structures' , 11 , 4 , False , False , (250,170, 30) ),\n Label( 'pole' , 26 , 17 , 5 , 23 , 20 , 'structures' , 12 , 4 , False , False , (153,153,153) ),\n Label( 'polegroup' , 27 , 18 , 255 , 23 , 20 , 'structures' , 12 , 4 , False , False , (153,153,153) ),\n Label( 'obs-str-bar-fallback' , 28 , 255 , 255 , 24 , 21 , 'structures' , 12 , 4 , False , False , (169, 187, 214) ),\n Label( 'building' , 29 , 11 , 2 , 25 , 22 , 'construction' , 13 , 5 , False , False , ( 70, 70, 70) ),\n Label( 'bridge' , 30 , 15 , 255 , 26 , 23 , 'construction' , 13 , 5 , False , False , (150,100,100) ),\n Label( 'tunnel' , 31 , 16 , 255 , 26 , 23 , 'construction' , 13 , 5 , False , False , (150,120, 90) ),\n Label( 'vegetation' , 32 , 21 , 8 , 27 , 24 , 'vegetation' , 14 , 5 , False , False , (107,142, 35) ),\n Label( 'sky' , 33 , 23 , 10 , 28 , 25 , 'sky' , 15 , 6 , False , False , ( 70,130,180) ),\n Label( 'fallback background' , 34 , 255 , 255 , 29 , 25 , 'object fallback' , 15 , 6 , False , False , (169, 187, 214)),\n Label( 'unlabeled' , 35 , 0 , 255 , 255 , 255 , 'void' , 255 , 255 , False , True , ( 0, 0, 0) ),\n Label( 'ego vehicle' , 36 , 1 , 255 , 255 , 255 , 'void' , 255 , 255 , False , True , ( 0, 0, 0) ),\n Label( 'rectification border' , 37 , 2 , 255 , 255 , 255 , 'void' , 255 , 255 , False , True , ( 0, 0, 0) ),\n Label( 'out of roi' , 38 , 3 , 255 , 255 , 255 , 'void' , 255 , 255 , False , True , ( 0, 0, 0) ),\n Label( 'license plate' , 39 , 255 , 255 , 255 , 255 , 'vehicle' , 255 , 255 , False , True , ( 0, 0,142) ),\n\n]","metadata":{"id":"y-y6VKPT_Gf7","execution":{"iopub.status.busy":"2024-10-10T17:44:12.181606Z","iopub.execute_input":"2024-10-10T17:44:12.182005Z","iopub.status.idle":"2024-10-10T17:44:12.215161Z","shell.execute_reply.started":"2024-10-10T17:44:12.181961Z","shell.execute_reply":"2024-10-10T17:44:12.214083Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2024-10-10T17:54:22.508586Z","iopub.execute_input":"2024-10-10T17:54:22.508978Z","iopub.status.idle":"2024-10-10T17:54:22.519125Z","shell.execute_reply.started":"2024-10-10T17:54:22.508940Z","shell.execute_reply":"2024-10-10T17:54:22.518155Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport random\nfrom typing import Any, Tuple\nfrom torchvision import transforms\nfrom PIL import Image\nfrom torch.utils.data import Dataset\nfrom dataclasses import dataclass\nimport albumentations as A\nfrom transformers import Mask2FormerImageProcessor\n\n# Assuming df is your DataFrame containing the image and mask paths\n# Example: df = pd.read_csv('path_to_your_csv_file.csv')\n\n# Step 1: Prepare your dataset by extracting paths from the DataFrame\nimage_paths = df['image'].values # Extract image paths\nmask_paths = df['mask'].values # Extract mask paths\n\n# Function to split data\ndef split_data_randomly(image_list, mask_list, train_ratio=0.8, val_ratio=0.1, test_ratio=0.1):\n # Ensure the lengths of image_list and mask_list are the same\n assert len(image_list) == len(mask_list), \"Image list and Mask list must have the same length\"\n\n # Combine image and mask paths into pairs to ensure they are shuffled together\n paired_data = list(zip(image_list, mask_list))\n\n # Shuffle the data\n random.shuffle(paired_data)\n\n # Split the data\n total_size = len(paired_data)\n train_size = int(total_size * train_ratio)\n val_size = int(total_size * val_ratio)\n test_size = total_size - train_size - val_size # Remaining for test set\n\n train_data = paired_data[:train_size]\n val_data = paired_data[train_size:train_size + val_size]\n test_data = paired_data[train_size + val_size:]\n\n # Unzip the paired data back into image and mask lists\n train_images, train_masks = zip(*train_data)\n val_images, val_masks = zip(*val_data)\n test_images, test_masks = zip(*test_data)\n\n return (train_images, val_images, test_images), (train_masks, val_masks, test_masks)\n\n# Split the data\n(image_splits, mask_splits) = split_data_randomly(image_paths, mask_paths)\n\n(train_images, val_images, test_images) = image_splits\n(train_masks, val_masks, test_masks) = mask_splits\n\n# Print the lengths of the splits\nprint(\"Train Images:\", len(train_images))\nprint(\"Validation Images:\", len(val_images))\nprint(\"Test Images:\", len(test_images))\n\n\n# Step 2: Define the preprocessing pipeline\npreprocessor = Mask2FormerImageProcessor(\n ignore_index=0,\n do_reduce_labels=False,\n do_resize=False,\n do_rescale=False,\n do_normalize=False,\n)\n\nade_mean = [123.675 / 255, 116.280 / 255, 103.530 / 255]\nade_std = [58.395 / 255, 57.120 / 255, 57.375 / 255]\n\ntrain_transform = A.Compose(\n [\n A.RandomCrop(width=512, height=512),\n A.HorizontalFlip(p=0.5),\n A.Normalize(mean=ade_mean, std=ade_std),\n ]\n)\n\ntest_transform = A.Compose(\n [\n A.Resize(width=512, height=512),\n A.Normalize(mean=ade_mean, std=ade_std),\n ]\n)\n\n@dataclass\nclass SegmentationDataInput:\n original_image: np.ndarray\n transformed_image: np.ndarray\n original_segmentation_map: np.ndarray\n transformed_segmentation_map: np.ndarray\n\nclass SemanticSegmentationDataset(Dataset):\n def __init__(self, image_paths, mask_paths, transform: Any) -> None:\n self.image_paths = image_paths\n self.mask_paths = mask_paths # Store mask paths\n self.transform = transform\n\n def __len__(self) -> int:\n return len(self.image_paths)\n\n def __getitem__(self, idx: int) -> SegmentationDataInput:\n # Load the image and mask from the file paths\n image_path = self.image_paths[idx]\n mask_path = self.mask_paths[idx] # Get the corresponding mask path\n\n original_image = np.array(Image.open(image_path).convert(\"RGB\"))\n original_segmentation_map = np.array(Image.open(mask_path).convert(\"L\")) # Assuming masks are grayscale\n\n # Rescale the mask from 0-255 to 0-39\n original_segmentation_map = np.floor(original_segmentation_map / (255 / 39)).astype(np.uint8)\n\n # Apply the transformation to both image and mask\n transformed = self.transform(\n image=original_image, mask=original_segmentation_map\n )\n transformed_image = transformed[\"image\"].transpose(2, 0, 1) # Transpose to channel-first format\n transformed_segmentation_map = transformed[\"mask\"]\n\n return SegmentationDataInput(\n original_image=original_image,\n transformed_image=transformed_image,\n original_segmentation_map=original_segmentation_map,\n transformed_segmentation_map=transformed_segmentation_map,\n )\n\ndef collate_fn(batch: SegmentationDataInput) -> dict:\n original_images = [sample.original_image for sample in batch]\n transformed_images = [sample.transformed_image for sample in batch]\n original_segmentation_maps = [sample.original_segmentation_map for sample in batch]\n transformed_segmentation_maps = [sample.transformed_segmentation_map for sample in batch]\n\n preprocessed_batch = preprocessor(\n transformed_images,\n segmentation_maps=transformed_segmentation_maps,\n return_tensors=\"pt\",\n )\n\n preprocessed_batch[\"original_images\"] = original_images\n preprocessed_batch[\"original_segmentation_maps\"] = original_segmentation_maps\n\n return preprocessed_batch\n","metadata":{"execution":{"iopub.status.busy":"2024-10-10T17:54:36.284288Z","iopub.execute_input":"2024-10-10T17:54:36.284667Z","iopub.status.idle":"2024-10-10T17:54:36.319981Z","shell.execute_reply.started":"2024-10-10T17:54:36.284631Z","shell.execute_reply":"2024-10-10T17:54:36.318990Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def id_to_label_map():\n new_dict = {}\n for label in labels_details:\n new_dict[int(label.level3Id)] = label.name\n return new_dict","metadata":{"id":"-8_qGGuz_VIQ","execution":{"iopub.status.busy":"2024-10-10T17:54:41.990053Z","iopub.execute_input":"2024-10-10T17:54:41.990973Z","iopub.status.idle":"2024-10-10T17:54:41.995791Z","shell.execute_reply.started":"2024-10-10T17:54:41.990928Z","shell.execute_reply":"2024-10-10T17:54:41.994827Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"id2label = id_to_label_map()\nprint(id2label)","metadata":{"id":"QsR0EGK7_kD9","outputId":"8762a7a6-df39-4f65-95ea-6abc77494fff","execution":{"iopub.status.busy":"2024-10-10T17:54:52.511305Z","iopub.execute_input":"2024-10-10T17:54:52.512253Z","iopub.status.idle":"2024-10-10T17:54:52.517052Z","shell.execute_reply.started":"2024-10-10T17:54:52.512211Z","shell.execute_reply":"2024-10-10T17:54:52.516095Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nfrom torch.utils.data import Dataset, DataLoader\n\ntrain_dataset = SemanticSegmentationDataset(train_images,train_masks, transform=train_transform)\nval_dataset = SemanticSegmentationDataset(val_images,val_masks, transform=train_transform)\ntest_dataset = SemanticSegmentationDataset(test_images,test_masks, transform=test_transform)\n\n# Prepare Dataloaders\ntrain_dataloader = DataLoader(\n train_dataset, batch_size=2, shuffle=True, collate_fn=collate_fn\n)\nval_dataloader = DataLoader(\n val_dataset, batch_size=2, shuffle=True, collate_fn=collate_fn\n)\ntest_dataloader = DataLoader(\n test_dataset, batch_size=2, shuffle=False, collate_fn=collate_fn\n)","metadata":{"id":"9WJEc4jx8FrW","execution":{"iopub.status.busy":"2024-10-10T17:56:05.815027Z","iopub.execute_input":"2024-10-10T17:56:05.815460Z","iopub.status.idle":"2024-10-10T17:56:05.822710Z","shell.execute_reply.started":"2024-10-10T17:56:05.815422Z","shell.execute_reply":"2024-10-10T17:56:05.821736Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample = next(iter(train_dataloader))\nprint(\n {\n key: value[0].shape if isinstance(value, list) else value.shape\n for key, value in sample.items()\n }\n)","metadata":{"id":"5_X5D6sb8v_6","outputId":"b30c563c-ba37-486d-cb05-497ced7a53f4","execution":{"iopub.status.busy":"2024-10-10T17:56:17.102599Z","iopub.execute_input":"2024-10-10T17:56:17.103293Z","iopub.status.idle":"2024-10-10T17:56:17.372062Z","shell.execute_reply.started":"2024-10-10T17:56:17.103254Z","shell.execute_reply":"2024-10-10T17:56:17.371049Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nfrom transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation\n\nprocessor = AutoImageProcessor.from_pretrained(\"facebook/mask2former-swin-large-ade-semantic\")\nmodel = Mask2FormerForUniversalSegmentation.from_pretrained(\n \"facebook/mask2former-swin-large-ade-semantic\"\n)","metadata":{"id":"3skwcut484do","outputId":"77895417-9b2b-49ae-cf5e-268e994e1247","execution":{"iopub.status.busy":"2024-10-10T17:57:46.390430Z","iopub.execute_input":"2024-10-10T17:57:46.390918Z","iopub.status.idle":"2024-10-10T17:57:51.796848Z","shell.execute_reply.started":"2024-10-10T17:57:46.390873Z","shell.execute_reply":"2024-10-10T17:57:51.796071Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# pixel level module contains both the backbone and the pixel decoder\nfor param in model.model.pixel_level_module.parameters():\n param.requires_grad = False\n\n# Confirm that the parameters are correctly frozen\nfor name, param in model.model.pixel_level_module.named_parameters():\n assert not param.requires_grad","metadata":{"id":"xDOqITHz-NFP","execution":{"iopub.status.busy":"2024-10-10T17:58:03.004475Z","iopub.execute_input":"2024-10-10T17:58:03.005600Z","iopub.status.idle":"2024-10-10T17:58:03.015876Z","shell.execute_reply.started":"2024-10-10T17:58:03.005553Z","shell.execute_reply":"2024-10-10T17:58:03.015050Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import torch\nfrom torch.utils.data import DataLoader\nfrom tqdm import tqdm\nimport evaluate\nfrom transformers import AutoImageProcessor\nfrom transformers import Mask2FormerForUniversalSegmentation\n\ndevice = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\nmetric = evaluate.load(\"mean_iou\")\n\ndef evaluate_model(\n model: Mask2FormerForUniversalSegmentation,\n dataloader: DataLoader,\n preprocessor: AutoImageProcessor,\n metric: Any,\n id2label: dict,\n max_batches=None,\n):\n \"\"\"\n Evaluates the given model using the specified dataloader and computes the mean Intersection over Union (IoU).\n ----\n Args:\n - model (MaskFormerForUniversalSegmentation): The trained model to be evaluated.\n - dataloader (DataLoader): DataLoader containing the dataset for evaluation.\n - preprocessor (AutoImageProcessor): The preprocessor used for post-processing the model outputs.\n - metric (Any): Metric instance used for calculating IoU.\n - id2label (dict): Dictionary mapping class ids to their corresponding labels.\n - max_batches (int, optional): Maximum number of batches to evaluate. If None, evaluates on the entire validation dataset.\n\n Returns:\n float: The mean IoU calculated over the specified number of batches.\n \"\"\"\n model.eval()\n running_iou = 0\n num_batches = 0\n with torch.no_grad():\n for idx, batch in enumerate(tqdm(dataloader)):\n if max_batches and idx >= max_batches:\n break\n\n pixel_values = batch[\"pixel_values\"].to(device)\n outputs = model(pixel_values=pixel_values)\n\n original_images = batch[\"original_images\"]\n target_sizes = [(image.shape[0], image.shape[1]) for image in original_images]\n\n predicted_segmentation_maps = preprocessor.post_process_semantic_segmentation(\n outputs, target_sizes=target_sizes\n )\n\n ground_truth_segmentation_maps = batch[\"original_segmentation_maps\"]\n metric.add_batch(\n references=ground_truth_segmentation_maps,\n predictions=predicted_segmentation_maps,\n )\n\n running_iou += metric.compute(num_labels=len(id2label), ignore_index=0)[\"mean_iou\"]\n num_batches += 1\n\n mean_iou = running_iou / num_batches if num_batches > 0 else 0.0\n return mean_iou\n\ndef train_model(\n model: Mask2FormerForUniversalSegmentation,\n train_dataloader: DataLoader,\n val_dataloader: DataLoader,\n preprocessor: AutoImageProcessor,\n metric: Any,\n id2label: dict,\n num_epochs=100,\n learning_rate=5e-5,\n log_interval=100,\n):\n \"\"\"\n Trains the MaskFormer model for semantic segmentation over a specified number of epochs and evaluates it on a validation set.\n ----\n Args: \n - model (MaskFormerForUniversalSegmentation): The model to be trained.\n - train_dataloader (DataLoader): DataLoader for the training data.\n - val_dataloader (DataLoader): DataLoader for the validation data.\n - preprocessor (AutoImageProcessor): The preprocessor used for preparing the data.\n - metric (Any): Metric instance used for calculating performance metrics.\n - id2label (dict): Dictionary mapping class IDs to their corresponding labels.\n - num_epochs (int): Number of epochs to train the model.\n - learning_rate (float): Learning rate for the optimizer.\n - log_interval (int): Interval (in number of batches) at which to log training progress.\n\n \"\"\"\n model.to(device)\n optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)\n\n for epoch in range(num_epochs):\n print(f\"Current epoch: {epoch + 1}/{num_epochs}\")\n model.train()\n\n running_loss = 0.0\n num_samples = 0\n\n for idx, batch in enumerate(tqdm(train_dataloader)):\n optimizer.zero_grad()\n\n outputs = model(\n pixel_values=batch[\"pixel_values\"].to(device),\n mask_labels=[labels.to(device) for labels in batch[\"mask_labels\"]],\n class_labels=[labels.to(device) for labels in batch[\"class_labels\"]],\n )\n\n loss = outputs.loss\n loss.backward()\n\n batch_size = batch[\"pixel_values\"].size(0)\n running_loss += loss.item()\n num_samples += batch_size\n\n if idx % log_interval == 0 and idx > 0:\n print(f\"Iteration {idx} - loss: {running_loss / num_samples:.4f}\")\n\n optimizer.step()\n\n val_mean_iou = evaluate_model(\n model, val_dataloader, preprocessor, metric, id2label, max_batches=6\n )\n print(f\"Validation Mean IoU: {val_mean_iou:.4f}\")\n","metadata":{"id":"k7Ozmgxo-kaT","execution":{"iopub.status.busy":"2024-10-10T17:59:22.354491Z","iopub.execute_input":"2024-10-10T17:59:22.354857Z","iopub.status.idle":"2024-10-10T17:59:23.847996Z","shell.execute_reply.started":"2024-10-10T17:59:22.354823Z","shell.execute_reply":"2024-10-10T17:59:23.847091Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_model(\n model,\n train_dataloader,\n val_dataloader,\n preprocessor,\n metric,\n id2label,\n num_epochs=2,\n log_interval=100,\n)","metadata":{"id":"819iSGtf-wtu","outputId":"94a7a589-0495-4ea0-ab96-e1f0923d4654","execution":{"iopub.status.busy":"2024-10-10T17:59:51.072199Z","iopub.execute_input":"2024-10-10T17:59:51.073460Z","iopub.status.idle":"2024-10-10T19:03:57.814191Z","shell.execute_reply.started":"2024-10-10T17:59:51.073413Z","shell.execute_reply":"2024-10-10T19:03:57.813204Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import torch\n\n# Assuming your model is defined as 'model'\ntorch.save(model.state_dict(), 'model.pth') # Save the model's parameters\n","metadata":{"id":"Ur5FWCadBcfg","execution":{"iopub.status.busy":"2024-10-10T19:27:39.804182Z","iopub.execute_input":"2024-10-10T19:27:39.805202Z","iopub.status.idle":"2024-10-10T19:27:41.033720Z","shell.execute_reply.started":"2024-10-10T19:27:39.805147Z","shell.execute_reply":"2024-10-10T19:27:41.032708Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"torch.save(model, 'full_model.pth') # Save the entire model\n","metadata":{"execution":{"iopub.status.busy":"2024-10-10T19:28:59.564720Z","iopub.execute_input":"2024-10-10T19:28:59.565554Z","iopub.status.idle":"2024-10-10T19:29:00.860873Z","shell.execute_reply.started":"2024-10-10T19:28:59.565480Z","shell.execute_reply":"2024-10-10T19:29:00.860051Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}