{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"

[Inference] Inception_v4 and PyTorchn Lightning

","metadata":{}},{"cell_type":"markdown","source":"
\nIt's an example of inference Inception_v4.
\n\nYou can train any model using [this notebook](https://www.kaggle.com/denispotapov/train-inception-v4-pytorch-lightning).
","metadata":{}},{"cell_type":"markdown","source":"Install and Import Libraries\n\nThere is nothing special. Install PyTorch Lightning and PyTorch Image Models.
","metadata":{}},{"cell_type":"code","source":"!pip install '/kaggle/input/pytorch-lightning142/pytorch_lightning-1.4.2-py3-none-any.whl' --no-deps\n!pip install '/kaggle/input/pytorchimagemodels/pytorch-image-models-master' --no-deps","metadata":{"execution":{"iopub.status.busy":"2021-08-27T11:49:40.881051Z","iopub.execute_input":"2021-08-27T11:49:40.881452Z","iopub.status.idle":"2021-08-27T11:50:30.793753Z","shell.execute_reply.started":"2021-08-27T11:49:40.88136Z","shell.execute_reply":"2021-08-27T11:50:30.79284Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nfrom os import walk\nimport cv2\nimport pickle\nimport shutil\nimport torchmetrics\nimport timm\nimport pandas as pd\n\nfrom pathlib import Path\nfrom tqdm import tqdm\n\nimport albumentations as A\nfrom albumentations.pytorch import ToTensorV2\n\nimport torch\nfrom torch import nn\nfrom torch.utils.data import Dataset, DataLoader\n\nimport pytorch_lightning as pl\nfrom pytorch_lightning.metrics.functional import accuracy","metadata":{"execution":{"iopub.status.busy":"2021-08-27T11:50:30.795517Z","iopub.execute_input":"2021-08-27T11:50:30.795847Z","iopub.status.idle":"2021-08-27T11:50:35.25747Z","shell.execute_reply.started":"2021-08-27T11:50:30.795808Z","shell.execute_reply":"2021-08-27T11:50:35.256555Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Model
\n\nThis is a module where we define our model, loss function, optimizer, scheduler, train/val/test steps.

\nBelow you will see a big \"if-elif-else\" construction with models names. It's because the models have different name for their last fully-connected layer where we should change default count of classes to our.
\nIn some models it is called \"fc\" or \"head\" or \"classifier\". When we create model for training we will only pass it's name and count of classes and this \"if-elif-else\" construction creates valid model for us.
","metadata":{}},{"cell_type":"code","source":"class ICPModel(pl.LightningModule):\n def __init__(self,\n model_type,\n num_classes,\n classes_weights,\n learning_rate=0.0001):\n super().__init__()\n\n # log hyperparameters\n self.save_hyperparameters()\n\n self.learning_rate = learning_rate\n self.num_classes = num_classes\n self.model_type = model_type\n\n # load network\n if self.model_type in ['densenet121', # classifier\n 'densenet161',\n 'densenet169',\n 'densenet201',\n 'densenetblur121d',\n 'efficientnet_b0',\n 'efficientnet_b1',\n 'efficientnet_b1_pruned',\n 'efficientnet_b2',\n 'efficientnet_b2a',\n 'efficientnet_b3',\n 'efficientnet_b3_pruned',\n 'efficientnet_b3a',\n 'efficientnet_em',\n 'efficientnet_es',\n 'efficientnet_lite0',\n 'fbnetc_100',\n 'hrnet_w18',\n 'hrnet_w18_small',\n 'hrnet_w18_small_v2',\n 'hrnet_w30',\n 'hrnet_w32',\n 'hrnet_w40',\n 'hrnet_w44',\n 'hrnet_w48',\n 'hrnet_w64',\n 'mixnet_l',\n 'mixnet_m',\n 'mixnet_s',\n 'mixnet_xl',\n 'mnasnet_100',\n 'mobilenetv2_100',\n 'mobilenetv2_110d',\n 'mobilenetv2_120d',\n 'mobilenetv2_140',\n 'mobilenetv3_large_100',\n 'mobilenetv3_rw',\n 'semnasnet_100',\n 'spnasnet_100',\n 'tf_efficientnet_b0',\n 'tf_efficientnet_b0_ap',\n 'tf_efficientnet_b0_ns',\n 'tf_efficientnet_b1',\n 'tf_efficientnet_b1_ap',\n 'tf_efficientnet_b1_ns',\n 'tf_efficientnet_b2',\n 'tf_efficientnet_b2_ap',\n 'tf_efficientnet_b2_ns',\n 'tf_efficientnet_b3',\n 'tf_efficientnet_b3_ap',\n 'tf_efficientnet_b3_ns',\n 'tf_efficientnet_b4',\n 'tf_efficientnet_b4_ap',\n 'tf_efficientnet_b4_ns',\n 'tf_efficientnet_b5',\n 'tf_efficientnet_b5_ap',\n 'tf_efficientnet_b5_ns',\n 'tf_efficientnet_b6',\n 'tf_efficientnet_b6_ap',\n 'tf_efficientnet_b6_ns',\n 'tf_efficientnet_b7',\n 'tf_efficientnet_b7_ap',\n 'tf_efficientnet_b7_ns',\n 'tf_efficientnet_b8',\n 'tf_efficientnet_b8_ap',\n 'tf_efficientnet_cc_b0_4e',\n 'tf_efficientnet_cc_b0_8e',\n 'tf_efficientnet_cc_b1_8e',\n 'tf_efficientnet_el',\n 'tf_efficientnet_em',\n 'tf_efficientnet_es',\n 'tf_efficientnet_l2_ns',\n 'tf_efficientnet_l2_ns_475',\n 'tf_efficientnet_lite0',\n 'tf_efficientnet_lite1',\n 'tf_efficientnet_lite2',\n 'tf_efficientnet_lite3',\n 'tf_efficientnet_lite4',\n 'tf_mixnet_l',\n 'tf_mixnet_m',\n 'tf_mixnet_s',\n 'tf_mobilenetv3_large_075',\n 'tf_mobilenetv3_large_100',\n 'tf_mobilenetv3_large_minimal_100',\n 'tf_mobilenetv3_small_075',\n 'tf_mobilenetv3_small_100',\n 'tf_mobilenetv3_small_minimal_100',\n 'tv_densenet121',\n 'tf_efficientnetv2_b0',\n 'tf_efficientnetv2_l',\n 'eca_efficientnet_b0',\n 'efficientnet_b2_pruned',\n 'efficientnet_b4',\n 'efficientnet_b5',\n 'efficientnet_b6',\n 'efficientnet_b7',\n 'efficientnet_b8',\n 'efficientnet_cc_b0_4e',\n 'efficientnet_cc_b0_8e',\n 'efficientnet_cc_b1_8e',\n 'efficientnet_el',\n 'efficientnet_el_pruned',\n 'efficientnet_es_pruned',\n 'efficientnet_l2',\n 'efficientnet_lite1',\n 'efficientnet_lite2',\n 'efficientnet_lite3',\n 'efficientnet_lite4',\n 'efficientnetv2_l',\n 'efficientnetv2_m',\n 'efficientnetv2_rw_m',\n 'efficientnetv2_rw_s',\n 'efficientnetv2_s',\n 'gc_efficientnet_b0',]:\n model = timm.create_model(model_type, pretrained=True)\n in_features = model.classifier.in_features\n model.classifier = nn.Linear(in_features, self.num_classes)\n self.model = model\n elif self.model_type in ['adv_inception_v3', # fc\n 'ecaresnet26t',\n 'ecaresnet50d',\n 'ecaresnet50d_pruned',\n 'ecaresnet50t',\n 'ecaresnet101d',\n 'ecaresnet101d_pruned',\n 'ecaresnet269d',\n 'ecaresnetlight',\n 'gluon_inception_v3',\n 'gluon_resnet18_v1b',\n 'gluon_resnet34_v1b',\n 'gluon_resnet50_v1b',\n 'gluon_resnet50_v1c',\n 'gluon_resnet50_v1d',\n 'gluon_resnet50_v1s',\n 'gluon_resnet101_v1b',\n 'gluon_resnet101_v1c',\n 'gluon_resnet101_v1d',\n 'gluon_resnet101_v1s',\n 'gluon_resnet152_v1b',\n 'gluon_resnet152_v1c',\n 'gluon_resnet152_v1d',\n 'gluon_resnet152_v1s',\n 'gluon_resnext50_32x4d',\n 'gluon_resnext101_32x4d',\n 'gluon_resnext101_64x4d',\n 'gluon_senet154',\n 'gluon_seresnext50_32x4d',\n 'gluon_seresnext101_32x4d',\n 'gluon_seresnext101_64x4d',\n 'gluon_xception65',\n 'ig_resnext101_32x8d',\n 'ig_resnext101_32x16d',\n 'ig_resnext101_32x32d',\n 'ig_resnext101_32x48d',\n 'inception_v3',\n 'res2net50_14w_8s',\n 'res2net50_26w_4s',\n 'res2net50_26w_6s',\n 'res2net50_26w_8s',\n 'res2net50_48w_2s',\n 'res2net101_26w_4s',\n 'res2next50',\n 'resnest14d',\n 'resnest26d',\n 'resnest50d',\n 'resnest50d_1s4x24d',\n 'resnest50d_4s2x40d',\n 'resnest101e',\n 'resnest200e',\n 'resnest269e',\n 'resnet18',\n 'resnet18d',\n 'resnet26',\n 'resnet26d',\n 'resnet34',\n 'resnet34d',\n 'resnet50',\n 'resnet50d',\n 'resnet101d',\n 'resnet152d',\n 'resnet200d',\n 'resnetblur50',\n 'resnext50_32x4d',\n 'resnext50d_32x4d',\n 'resnext101_32x8d',\n 'selecsls42b',\n 'selecsls60',\n 'selecsls60b',\n 'seresnet50',\n 'seresnet152d',\n 'seresnext26d_32x4d',\n 'seresnext26t_32x4d',\n 'seresnext50_32x4d',\n 'skresnet18',\n 'skresnet34',\n 'skresnext50_32x4d',\n 'ssl_resnet18',\n 'ssl_resnet50',\n 'ssl_resnext50_32x4d',\n 'ssl_resnext101_32x4d',\n 'ssl_resnext101_32x8d',\n 'ssl_resnext101_32x16d',\n 'swsl_resnet18',\n 'swsl_resnet50',\n 'swsl_resnext50_32x4d',\n 'swsl_resnext101_32x4d',\n 'swsl_resnext101_32x8d',\n 'swsl_resnext101_32x16d',\n 'tf_inception_v3',\n 'tv_resnet34',\n 'tv_resnet50',\n 'tv_resnet101',\n 'tv_resnet152',\n 'tv_resnext50_32x4d',\n 'wide_resnet50_2',\n 'wide_resnet101_2',\n 'xception', ]:\n model = timm.create_model(model_type, pretrained=True)\n in_features = model.fc.in_features\n model.classifier = nn.Linear(in_features, self.num_classes)\n self.model = model\n elif self.model_type in ['dla34',\n 'dla46_c',\n 'dla46x_c',\n 'dla60',\n 'dla60_res2net',\n 'dla60_res2next',\n 'dla60x',\n 'dla60x_c',\n 'dla102',\n 'dla102x',\n 'dla102x2',\n 'dla169',\n 'dpn68',\n 'dpn68b',\n 'dpn92',\n 'dpn98',\n 'dpn107',\n 'dpn131',\n ]:\n model = timm.create_model(model_type, pretrained=True)\n if self.model_type == 'dla34':\n model.fc = nn.Conv2d(512, self.num_classes, kernel_size=(1, 1), stride=(1, 1))\n elif self.model_type in ['dla46_c',\n 'dla46x_c',\n 'dla60x_c', ]:\n model.fc = nn.Conv2d(256, self.num_classes, kernel_size=(1, 1), stride=(1, 1))\n elif self.model_type in ['dla60',\n 'dla60_res2net',\n 'dla60_res2next',\n 'dla60x',\n 'dla102',\n 'dla102x',\n 'dla102x2',\n 'dla169']:\n model.fc = nn.Conv2d(1024, self.num_classes, kernel_size=(1, 1), stride=(1, 1))\n elif self.model_type in ['dpn68', 'dpn68b', ]:\n model.fc = nn.Conv2d(832, self.num_classes, kernel_size=(1, 1), stride=(1, 1))\n elif self.model_type in ['dpn92', 'dpn98', 'dpn107', 'dpn131', ]:\n model.fc = nn.Conv2d(2688, self.num_classes, kernel_size=(1, 1), stride=(1, 1))\n self.model = model\n elif self.model_type in ['cspdarknet53', # head.fc\n 'cspresnet50',\n 'cspresnext50',\n 'dm_nfnet_f0',\n 'dm_nfnet_f1',\n 'dm_nfnet_f2',\n 'dm_nfnet_f3',\n 'dm_nfnet_f4',\n 'dm_nfnet_f5',\n 'dm_nfnet_f6',\n 'ese_vovnet19b_dw',\n 'ese_vovnet39b',\n 'gernet_l',\n 'gernet_m',\n 'gernet_s',\n 'nf_regnet_b1',\n 'nf_resnet50',\n 'nfnet_l0c',\n 'regnetx_002',\n 'regnetx_004',\n 'regnetx_006',\n 'regnetx_008',\n 'regnetx_016',\n 'regnetx_032',\n 'regnetx_040',\n 'regnetx_064',\n 'regnetx_080',\n 'regnetx_120',\n 'regnetx_160',\n 'regnetx_320',\n 'regnety_002',\n 'regnety_004',\n 'regnety_006',\n 'regnety_008',\n 'regnety_016',\n 'regnety_032',\n 'regnety_040',\n 'regnety_064',\n 'regnety_080',\n 'regnety_120',\n 'regnety_160',\n 'regnety_320',\n 'repvgg_a2',\n 'repvgg_b0',\n 'repvgg_b1',\n 'repvgg_b1g4',\n 'repvgg_b2',\n 'repvgg_b2g4',\n 'repvgg_b3',\n 'repvgg_b3g4',\n 'resnetv2_50x1_bitm',\n 'resnetv2_50x1_bitm_in21k',\n 'resnetv2_50x3_bitm',\n 'resnetv2_50x3_bitm_in21k',\n 'resnetv2_101x1_bitm',\n 'resnetv2_101x1_bitm_in21k',\n 'resnetv2_101x3_bitm',\n 'resnetv2_101x3_bitm_in21k',\n 'resnetv2_152x2_bitm',\n 'resnetv2_152x2_bitm_in21k',\n 'resnetv2_152x4_bitm',\n 'resnetv2_152x4_bitm_in21k',\n 'rexnet_100',\n 'rexnet_130',\n 'rexnet_150',\n 'rexnet_200',\n 'tresnet_l',\n 'tresnet_l_448',\n 'tresnet_m',\n 'tresnet_m_448',\n 'tresnet_xl',\n 'tresnet_xl_448',\n 'vgg11',\n 'vgg11_bn',\n 'vgg13',\n 'vgg13_bn',\n 'vgg16',\n 'vgg16_bn',\n 'vgg19',\n 'vgg19_bn',\n 'xception41',\n 'xception65',\n 'xception71', ]:\n model = timm.create_model(model_type, pretrained=True)\n in_features = model.head.fc.in_features\n model.classifier = nn.Linear(in_features, self.num_classes)\n self.model = model\n elif self.model_type in ['deit_base_distilled_patch16_224']:\n model = timm.create_model(model_type, pretrained=True)\n in_features_head = model.head.in_features\n in_features_head_dist = model.head_dist.in_features\n model.head = nn.Linear(in_features_head, self.num_classes)\n model.head_dist = nn.Linear(in_features_head_dist, self.num_classes)\n print(model)\n self.model = model\n elif self.model_type in ['ens_adv_inception_resnet_v2', # classif\n 'inception_resnet_v2', ]:\n model = timm.create_model(model_type, pretrained=True)\n in_features = model.classif.in_features\n model.classifier = nn.Linear(in_features, self.num_classes)\n self.model = model\n elif self.model_type in ['inception_v4', # last_linear\n 'legacy_senet154',\n 'legacy_seresnet18',\n 'legacy_seresnet34',\n 'legacy_seresnet50',\n 'legacy_seresnet101',\n 'legacy_seresnet152',\n 'legacy_seresnext26_32x4d',\n 'legacy_seresnext50_32x4d',\n 'legacy_seresnext101_32x4d',\n 'nasnetalarge',\n 'pnasnet5large', ]:\n model = timm.create_model(model_type, pretrained=True)\n in_features = model.last_linear.in_features\n model.last_linear = nn.Linear(in_features, self.num_classes)\n self.model = model\n elif self.model_type in ['vit_base_patch16_224', # head\n 'vit_base_patch16_224_in21k',\n 'vit_base_patch16_384',\n 'vit_base_patch32_224_in21k',\n 'vit_base_patch32_384',\n 'vit_base_resnet50_224_in21k',\n 'vit_base_resnet50_384',\n 'vit_deit_base_distilled_patch16_224',\n 'vit_deit_base_distilled_patch16_384',\n 'vit_deit_base_patch16_224',\n 'vit_deit_base_patch16_384',\n 'vit_deit_small_distilled_patch16_224',\n 'vit_deit_small_patch16_224',\n 'vit_deit_tiny_distilled_patch16_224',\n 'vit_deit_tiny_patch16_224',\n 'vit_large_patch16_224',\n 'vit_large_patch16_224_in21k',\n 'vit_large_patch16_384',\n 'vit_large_patch32_224_in21k',\n 'vit_large_patch32_384',\n 'vit_small_patch16_224',\n 'cait_m36_384',\n 'cait_m48_448',\n 'cait_s24_224',\n 'cait_s24_384',\n 'cait_s36_384',\n 'cait_xs24_384',\n 'cait_xxs24_224',\n 'cait_xxs24_384',\n 'cait_xxs36_224',\n 'cait_xxs36_384',\n 'coat_lite_mini',\n 'coat_lite_small',\n 'coat_lite_tiny',\n 'coat_mini',\n 'coat_tiny',\n 'convit_base',\n 'convit_small',\n 'convit_tiny', ]:\n model = timm.create_model(model_type, pretrained=True)\n in_features = model.head.in_features\n model.classifier = nn.Linear(in_features, self.num_classes)\n self.model = model\n else:\n assert (\n False\n ), f\"model_type '{self.model_type}' not implemented. Please, choose from {MODELS}\"\n\n if classes_weights:\n self.classes_weights = torch.FloatTensor(classes_weights).cuda()\n self.loss_func = nn.CrossEntropyLoss(weight=self.classes_weights)\n else:\n self.loss_func = nn.CrossEntropyLoss()\n\n# self.f1 = torchmetrics.F1(num_classes=self.num_classes)\n\n def loss(self, logits, labels):\n return self.loss_func(input=logits, target=labels)\n\n # will be used during inference\n def forward(self, x):\n return self.model(x)\n\n # Using custom or multiple metrics (default_hp_metric=False)\n def on_train_start(self):\n self.logger.log_hyperparams(self.hparams)\n\n # logic for a single training step\n def training_step(self, batch, batch_idx):\n x, y = batch\n output = self.forward(x)\n train_loss = self.loss(output, y)\n\n # training metrics\n output = torch.argmax(output, dim=1)\n acc = accuracy(output, y)\n\n self.log('train_loss', train_loss, prog_bar=True)\n self.log('train_acc', acc, prog_bar=True)\n\n return train_loss\n\n # logic for a single validation step\n def validation_step(self, batch, batch_idx):\n x, y = batch\n output = self.forward(x)\n val_loss = self.loss(output, y)\n\n # validation metrics\n output = torch.argmax(output, dim=1)\n acc = accuracy(output, y)\n\n self.log('val_loss', val_loss, prog_bar=True)\n self.log('val_acc', acc, prog_bar=True)\n\n return val_loss\n\n # logic for a single testing step\n def test_step(self, batch, batch_idx):\n x, y = batch\n output = self(x)\n test_loss = self.loss(output, y)\n\n # validation metrics\n output = torch.argmax(output, dim=1)\n acc = accuracy(output, y)\n\n self.log('test_loss', test_loss, prog_bar=True)\n self.log('test_acc', acc, prog_bar=True)\n\n return test_loss\n\n # def training_epoch_end(self, outputs):\n # self.log('train_f1_epoch', self.f1.compute())\n # self.f1.reset()\n #\n # def validation_epoch_end(self, outputs):\n # self.log('val_f1_epoch', self.f1.compute(), prog_bar=True)\n # self.f1.reset()\n #\n # def test_epoch_end(self, outputs):\n # self.log('test_f1_epoch', self.f1.compute())\n # self.f1.reset()\n\n def configure_optimizers(self):\n gen_opt = torch.optim.Adam(self.parameters(), lr=self.learning_rate)\n\n gen_sched = {'scheduler': torch.optim.lr_scheduler.ExponentialLR(gen_opt, gamma=0.999, verbose=False),\n 'interval': 'epoch'}\n\n return [gen_opt], [gen_sched]","metadata":{"execution":{"iopub.status.busy":"2021-08-27T11:57:49.208199Z","iopub.execute_input":"2021-08-27T11:57:49.208605Z","iopub.status.idle":"2021-08-27T11:57:49.287456Z","shell.execute_reply.started":"2021-08-27T11:57:49.208566Z","shell.execute_reply":"2021-08-27T11:57:49.286487Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Dataset
\nThis is how you process a pair \"image - label\" of your dataset. ","metadata":{}},{"cell_type":"code","source":"class InferenceDataset(Dataset):\n def __init__(self,\n image_ids,\n img_size,\n mean=[0.485, 0.456, 0.406],\n std=[0.229, 0.224, 0.225]):\n super().__init__()\n self.image_ids = image_ids\n self.mean = mean\n self.std = std\n self.img_size = img_size\n self.transform = A.Compose([\n A.Normalize(mean=self.mean, std=self.std), ToTensorV2(transpose_mask=True)])\n\n def __len__(self):\n return len(self.image_ids)\n\n def __getitem__(self, item):\n image_id = str(self.image_ids[item]).split('/')[-1].split('.')[0]\n image = cv2.imread(self.image_ids[item], cv2.IMREAD_COLOR)\n image = cv2.resize(image, (self.img_size, self.img_size), interpolation=cv2.INTER_NEAREST)\n image = self.transform(image=image)\n \n return image, image_id","metadata":{"execution":{"iopub.status.busy":"2021-08-27T11:55:17.066777Z","iopub.execute_input":"2021-08-27T11:55:17.067184Z","iopub.status.idle":"2021-08-27T11:55:17.077424Z","shell.execute_reply.started":"2021-08-27T11:55:17.067148Z","shell.execute_reply":"2021-08-27T11:55:17.07512Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# import timm\n# from pprint import pprint\n\n# model = 'inception_v4'\n# m = timm.create_model(model, pretrained=True)\n# print(model)\n# pprint(m.default_cfg)","metadata":{"execution":{"iopub.status.busy":"2021-08-27T04:55:13.629573Z","iopub.execute_input":"2021-08-27T04:55:13.632479Z","iopub.status.idle":"2021-08-27T04:55:13.640357Z","shell.execute_reply.started":"2021-08-27T04:55:13.63243Z","shell.execute_reply":"2021-08-27T04:55:13.639135Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Upload initial weights
","metadata":{}},{"cell_type":"code","source":"!mkdir -p /root/.cache/torch/hub/checkpoints/","metadata":{"execution":{"iopub.status.busy":"2021-08-27T11:55:20.757469Z","iopub.execute_input":"2021-08-27T11:55:20.757789Z","iopub.status.idle":"2021-08-27T11:55:21.399754Z","shell.execute_reply.started":"2021-08-27T11:55:20.757758Z","shell.execute_reply":"2021-08-27T11:55:21.39869Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%cd /root/.cache/torch/hub/checkpoints/","metadata":{"execution":{"iopub.status.busy":"2021-08-27T11:55:21.401605Z","iopub.execute_input":"2021-08-27T11:55:21.401987Z","iopub.status.idle":"2021-08-27T11:55:21.409716Z","shell.execute_reply.started":"2021-08-27T11:55:21.401943Z","shell.execute_reply":"2021-08-27T11:55:21.408786Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!cp /kaggle/input/timm-pretrained-models-weights/inceptionv4-8e4777a0.pth .","metadata":{"execution":{"iopub.status.busy":"2021-08-27T11:55:21.65063Z","iopub.execute_input":"2021-08-27T11:55:21.650959Z","iopub.status.idle":"2021-08-27T11:55:25.050176Z","shell.execute_reply.started":"2021-08-27T11:55:21.650929Z","shell.execute_reply":"2021-08-27T11:55:25.049049Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%cd /kaggle/working","metadata":{"execution":{"iopub.status.busy":"2021-08-27T11:55:25.053132Z","iopub.execute_input":"2021-08-27T11:55:25.053508Z","iopub.status.idle":"2021-08-27T11:55:25.062138Z","shell.execute_reply.started":"2021-08-27T11:55:25.053469Z","shell.execute_reply":"2021-08-27T11:55:25.06132Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Set parameters of our model","metadata":{}},{"cell_type":"code","source":"checkpoint = '/kaggle/input/inception-v4-weights/inception_v4__epoch4_val_loss2.132_val_acc0.587.ckpt'\n# mean = [0.485, 0.456, 0.406]\n# std = [0.229, 0.224, 0.225]\nmean = [0.5, 0.5, 0.5]\nstd = [0.5, 0.5, 0.5]\nimg_size = 299\n\nmodel = ICPModel.load_from_checkpoint(checkpoint_path=checkpoint)\nmodel = model.to(\"cuda\")\nmodel.eval()\nmodel.freeze()\n\nsm = torch.nn.Softmax()","metadata":{"execution":{"iopub.status.busy":"2021-08-27T11:57:52.919596Z","iopub.execute_input":"2021-08-27T11:57:52.919936Z","iopub.status.idle":"2021-08-27T11:58:05.039483Z","shell.execute_reply.started":"2021-08-27T11:57:52.919904Z","shell.execute_reply":"2021-08-27T11:58:05.038637Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# get mapping from labels to landmarks\n# we created label_encoder_0_5000.pkl during training\nlabel_encoder = pickle.load(open(\"/kaggle/input/inception-v4-weights/label_encoder_0_5000.pkl\", 'rb'))","metadata":{"execution":{"iopub.status.busy":"2021-08-27T04:55:29.8903Z","iopub.execute_input":"2021-08-27T04:55:29.890738Z","iopub.status.idle":"2021-08-27T04:55:30.030638Z","shell.execute_reply.started":"2021-08-27T04:55:29.890661Z","shell.execute_reply":"2021-08-27T04:55:30.02946Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# get all images paths\nimages = []\nfor dirpath, dirnames, filenames in os.walk(\"/kaggle/input/landmark-recognition-2021/test\"):\n for filename in [f for f in filenames if f.endswith(\".jpg\")]:\n images.append(os.path.join(dirpath, filename))","metadata":{"execution":{"iopub.status.busy":"2021-08-27T04:55:30.032278Z","iopub.execute_input":"2021-08-27T04:55:30.032792Z","iopub.status.idle":"2021-08-27T04:55:36.604921Z","shell.execute_reply.started":"2021-08-27T04:55:30.03275Z","shell.execute_reply":"2021-08-27T04:55:36.603428Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# create dataset and dataloader\ntest_dataset = InferenceDataset(image_ids=images, img_size=img_size, mean=mean, std=std)\ntest_loader = DataLoader(test_dataset, batch_size=1)","metadata":{"execution":{"iopub.status.busy":"2021-08-27T04:55:36.62156Z","iopub.execute_input":"2021-08-27T04:55:36.62237Z","iopub.status.idle":"2021-08-27T04:55:36.630489Z","shell.execute_reply.started":"2021-08-27T04:55:36.622325Z","shell.execute_reply":"2021-08-27T04:55:36.628971Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Predict and save results","metadata":{}},{"cell_type":"code","source":"images = [] \nresults = []\n \nfor i, data in enumerate(tqdm(test_loader)):\n file = data[1][0]\n images.append(file)\n \n y_hat = model(data[0].get('image').to(\"cuda\"))\n probabilities = sm(y_hat)\n \n \n predicted_class = torch.argmax(probabilities, dim=1)\n\n y_hat = predicted_class.cpu().detach().numpy()[0]\n probabilities = probabilities.cpu().detach().numpy()[0]\n\n\n class1 = label_encoder.classes_[y_hat]\n\n results.append(str(class1) + ' ' + str(probabilities[y_hat]))","metadata":{"execution":{"iopub.status.busy":"2021-08-27T04:55:36.632658Z","iopub.execute_input":"2021-08-27T04:55:36.633177Z","iopub.status.idle":"2021-08-27T04:58:35.258451Z","shell.execute_reply.started":"2021-08-27T04:55:36.633134Z","shell.execute_reply":"2021-08-27T04:58:35.254704Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.DataFrame(list(zip(images, results)), columns=['id', 'landmarks'])\ndf.to_csv('/kaggle/working/submission.csv', index=None)","metadata":{"execution":{"iopub.status.busy":"2021-08-27T04:58:35.259331Z","iopub.status.idle":"2021-08-27T04:58:35.259822Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.head()","metadata":{"execution":{"iopub.status.busy":"2021-08-27T04:58:35.261297Z","iopub.status.idle":"2021-08-27T04:58:35.261959Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Thank you for attention!\n
\nā€‹\nIf you have some questions or suggestions you can write comments šŸ’¬
\nā€‹\nDon't give up, keep trying! šŸ’Ŗ","metadata":{}}]}