{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.10","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\n# for dirname, _, filenames in os.walk('/kaggle/input'):\n#     for filename in filenames:\n#         print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-12-11T09:44:00.553278Z","iopub.execute_input":"2022-12-11T09:44:00.55425Z","iopub.status.idle":"2022-12-11T09:44:00.648556Z","shell.execute_reply.started":"2022-12-11T09:44:00.55413Z","shell.execute_reply":"2022-12-11T09:44:00.647515Z"},"trusted":true},"execution_count":1,"outputs":[]},{"cell_type":"code","source":"import cv2\nimport matplotlib.pyplot as plt\nfrom os.path import isfile\nimport torch.nn.init as init\nimport torch\nimport torch.nn as nn\nimport numpy as np\nimport pandas as pd \nimport os\nimport scipy as sp\nfrom PIL import Image, ImageFilter\nfrom sklearn.model_selection import train_test_split, StratifiedKFold\nfrom torch.utils.data import Dataset\nfrom torchvision import transforms\nfrom torch.optim import Adam, SGD, RMSprop\nimport time\nfrom torch.autograd import Variable\nimport torch.functional as F\nfrom tqdm import tqdm\nfrom sklearn import metrics\nimport urllib\nimport pickle\nimport torch.nn.functional as F\nfrom torchvision import models\nimport random\nimport sys\nfrom functools import partial\nfrom torch.utils.data import DataLoader\nfrom torch.autograd import Variable\n\nprint('Ready, set, go....')","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:00.650122Z","iopub.execute_input":"2022-12-11T09:44:00.650378Z","iopub.status.idle":"2022-12-11T09:44:06.083067Z","shell.execute_reply.started":"2022-12-11T09:44:00.650346Z","shell.execute_reply":"2022-12-11T09:44:06.082197Z"},"trusted":true},"execution_count":2,"outputs":[{"name":"stdout","text":"Ready, set, go....\n","output_type":"stream"}]},{"cell_type":"code","source":"!git clone https://github.com/quangphammessi/kaggle_aptos","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:06.087258Z","iopub.execute_input":"2022-12-11T09:44:06.087513Z","iopub.status.idle":"2022-12-11T09:44:08.707896Z","shell.execute_reply.started":"2022-12-11T09:44:06.087482Z","shell.execute_reply":"2022-12-11T09:44:08.707065Z"},"trusted":true},"execution_count":3,"outputs":[{"name":"stdout","text":"Cloning into 'kaggle_aptos'...\nremote: Enumerating objects: 309, done.\u001b[K\nremote: Counting objects: 100% (309/309), done.\u001b[K\nremote: Compressing objects: 100% (273/273), done.\u001b[K\nremote: Total 309 (delta 20), reused 309 (delta 20), pack-reused 0\u001b[K\nReceiving objects: 100% (309/309), 2.28 MiB | 4.24 MiB/s, done.\nResolving deltas: 100% (20/20), done.\n","output_type":"stream"}]},{"cell_type":"code","source":"NVIDIA_apex_path = '/kaggle/working/kaggle_aptos/repository/NVIDIA-apex-39e153a'\nWARMUP_LR = '/kaggle/input/gradual-lr/pytorch-gradual-warmup-lr'\nsys.path.append(NVIDIA_apex_path)\nsys.path.append(WARMUP_LR)\nsys.path.append('/kaggle/input/d/abhishek/efficientnet-pytorch')\nfrom efficientnet_pytorch import EfficientNet\n# from apex import amp","metadata":{"_kg_hide-output":true,"execution":{"iopub.status.busy":"2022-12-11T09:44:08.711697Z","iopub.execute_input":"2022-12-11T09:44:08.712363Z","iopub.status.idle":"2022-12-11T09:44:08.750693Z","shell.execute_reply.started":"2022-12-11T09:44:08.712331Z","shell.execute_reply":"2022-12-11T09:44:08.75003Z"},"trusted":true},"execution_count":4,"outputs":[]},{"cell_type":"code","source":"def seed_everything(seed):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.backends.cudnn.deterministic = True","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:08.751741Z","iopub.execute_input":"2022-12-11T09:44:08.751978Z","iopub.status.idle":"2022-12-11T09:44:08.756445Z","shell.execute_reply.started":"2022-12-11T09:44:08.751947Z","shell.execute_reply":"2022-12-11T09:44:08.755566Z"},"trusted":true},"execution_count":5,"outputs":[]},{"cell_type":"code","source":"n_epochs    = 30\nnum_classes = 1\nseed_everything(1234)\nlr          = 1e-3\nIMG_SIZE    = 380\ncoef = [0.5, 1.5, 2.5, 3.5]","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:08.757698Z","iopub.execute_input":"2022-12-11T09:44:08.758481Z","iopub.status.idle":"2022-12-11T09:44:08.769169Z","shell.execute_reply.started":"2022-12-11T09:44:08.758436Z","shell.execute_reply":"2022-12-11T09:44:08.76849Z"},"trusted":true},"execution_count":6,"outputs":[]},{"cell_type":"code","source":"train_csv = pd.read_csv('/kaggle/input/aptos2019-blindness-detection/train.csv')","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:08.770198Z","iopub.execute_input":"2022-12-11T09:44:08.770456Z","iopub.status.idle":"2022-12-11T09:44:08.792352Z","shell.execute_reply.started":"2022-12-11T09:44:08.770414Z","shell.execute_reply":"2022-12-11T09:44:08.791711Z"},"trusted":true},"execution_count":7,"outputs":[]},{"cell_type":"code","source":"train_csv.head()","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:08.793557Z","iopub.execute_input":"2022-12-11T09:44:08.793793Z","iopub.status.idle":"2022-12-11T09:44:08.812598Z","shell.execute_reply.started":"2022-12-11T09:44:08.793764Z","shell.execute_reply":"2022-12-11T09:44:08.811797Z"},"trusted":true},"execution_count":8,"outputs":[{"execution_count":8,"output_type":"execute_result","data":{"text/plain":"        id_code  diagnosis\n0  000c1434d8d7          2\n1  001639a390f0          4\n2  0024cdab0c1e          1\n3  002c21358ce6          0\n4  005b95c28852          0","text/html":"<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>id_code</th>\n      <th>diagnosis</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>000c1434d8d7</td>\n      <td>2</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>001639a390f0</td>\n      <td>4</td>\n    </tr>\n    <tr>\n      <th>2</th>\n      <td>0024cdab0c1e</td>\n      <td>1</td>\n    </tr>\n    <tr>\n      <th>3</th>\n      <td>002c21358ce6</td>\n      <td>0</td>\n    </tr>\n    <tr>\n      <th>4</th>\n      <td>005b95c28852</td>\n      <td>0</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}}]},{"cell_type":"code","source":"train_csv.shape","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:08.81389Z","iopub.execute_input":"2022-12-11T09:44:08.814176Z","iopub.status.idle":"2022-12-11T09:44:08.820503Z","shell.execute_reply.started":"2022-12-11T09:44:08.814144Z","shell.execute_reply":"2022-12-11T09:44:08.819812Z"},"trusted":true},"execution_count":9,"outputs":[{"execution_count":9,"output_type":"execute_result","data":{"text/plain":"(3662, 2)"},"metadata":{}}]},{"cell_type":"code","source":"train_df, val_df = train_test_split(train_csv, test_size = 0.1, random_state = 42, stratify=train_csv.diagnosis)\ntrain_df.reset_index(drop=True, inplace=True)\nval_df.reset_index(drop=True, inplace=True)","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:08.824077Z","iopub.execute_input":"2022-12-11T09:44:08.824288Z","iopub.status.idle":"2022-12-11T09:44:08.834563Z","shell.execute_reply.started":"2022-12-11T09:44:08.824258Z","shell.execute_reply":"2022-12-11T09:44:08.833845Z"},"trusted":true},"execution_count":10,"outputs":[]},{"cell_type":"code","source":"train = '/kaggle/input/aptos2019-blindness-detection/train_images/'","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:08.836488Z","iopub.execute_input":"2022-12-11T09:44:08.837005Z","iopub.status.idle":"2022-12-11T09:44:08.840539Z","shell.execute_reply.started":"2022-12-11T09:44:08.836972Z","shell.execute_reply":"2022-12-11T09:44:08.839696Z"},"trusted":true},"execution_count":11,"outputs":[]},{"cell_type":"code","source":"def expand_path(p):\n    p = str(p)\n    if isfile(train + p + \".png\"):\n        return train + (p + \".png\")\n    return p\n","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:08.841933Z","iopub.execute_input":"2022-12-11T09:44:08.842353Z","iopub.status.idle":"2022-12-11T09:44:08.850911Z","shell.execute_reply.started":"2022-12-11T09:44:08.842317Z","shell.execute_reply":"2022-12-11T09:44:08.850212Z"},"trusted":true},"execution_count":12,"outputs":[]},{"cell_type":"code","source":"def p_show(imgs, label_name=None, per_row=3):\n    n = len(imgs)\n    rows = (n + per_row - 1)//per_row\n    cols = min(per_row, n)\n    fig, axes = plt.subplots(rows,cols, figsize=(15,15))\n    for ax in axes.flatten(): ax.axis('off')\n    for i,(p, ax) in enumerate(zip(imgs, axes.flatten())): \n        img = Image.open(expand_path(p))\n        ax.imshow(img)\n        ax.set_title(train_df[train_df.id_code == p].diagnosis.values)\n","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:08.853751Z","iopub.execute_input":"2022-12-11T09:44:08.854063Z","iopub.status.idle":"2022-12-11T09:44:08.861853Z","shell.execute_reply.started":"2022-12-11T09:44:08.853925Z","shell.execute_reply":"2022-12-11T09:44:08.860934Z"},"trusted":true},"execution_count":13,"outputs":[]},{"cell_type":"code","source":"p_show(['/kaggle/input/aptos2019-blindness-detection/train_images/00cc2b75cddd.png',\n        '/kaggle/input/aptos2019-blindness-detection/train_images/00cb6555d108.png',\n        '/kaggle/input/aptos2019-blindness-detection/train_images/0151781fe50b.png'])","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:08.863735Z","iopub.execute_input":"2022-12-11T09:44:08.863951Z","iopub.status.idle":"2022-12-11T09:44:10.683353Z","shell.execute_reply.started":"2022-12-11T09:44:08.863928Z","shell.execute_reply":"2022-12-11T09:44:10.682678Z"},"trusted":true},"execution_count":14,"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.7/site-packages/matplotlib/text.py:1215: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison\n  if s != self._text:\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"<Figure size 1080x1080 with 3 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"cell_type":"code","source":"def crop_image1(img,tol=7):\n    # img is image data\n    # tol  is tolerance\n        \n    mask = img>tol\n    return img[np.ix_(mask.any(1),mask.any(0))]\n\ndef crop_image_from_gray(img,tol=7):\n    if img.ndim == 2:\n        mask = img>tol\n        return img[np.ix_(mask.any(1),mask.any(0))]\n    elif img.ndim==3:\n        gray_img = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)\n        mask = gray_img>tol\n        \n        check_shape = img[:,:,0][np.ix_(mask.any(1),mask.any(0))].shape[0]\n        if (check_shape == 0): # image is too dark so that we crop out everything,\n            return img # return original image\n        else:\n            img1=img[:,:,0][np.ix_(mask.any(1),mask.any(0))]\n            img2=img[:,:,1][np.ix_(mask.any(1),mask.any(0))]\n            img3=img[:,:,2][np.ix_(mask.any(1),mask.any(0))]\n    #         print(img1.shape,img2.shape,img3.shape)\n            img = np.stack([img1,img2,img3],axis=-1)\n#             print(img.shape)\n        return img","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:10.684337Z","iopub.execute_input":"2022-12-11T09:44:10.684631Z","iopub.status.idle":"2022-12-11T09:44:10.694893Z","shell.execute_reply.started":"2022-12-11T09:44:10.684589Z","shell.execute_reply":"2022-12-11T09:44:10.693915Z"},"trusted":true},"execution_count":15,"outputs":[]},{"cell_type":"code","source":"a = np.array([[1,2,10,10,10,10,7,8,1,2],[1,2,13,14,15,16,17,18,1,2]])\na","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:10.696079Z","iopub.execute_input":"2022-12-11T09:44:10.696867Z","iopub.status.idle":"2022-12-11T09:44:10.709563Z","shell.execute_reply.started":"2022-12-11T09:44:10.696831Z","shell.execute_reply":"2022-12-11T09:44:10.709045Z"},"trusted":true},"execution_count":16,"outputs":[{"execution_count":16,"output_type":"execute_result","data":{"text/plain":"array([[ 1,  2, 10, 10, 10, 10,  7,  8,  1,  2],\n       [ 1,  2, 13, 14, 15, 16, 17, 18,  1,  2]])"},"metadata":{}}]},{"cell_type":"code","source":"x = a>7","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:10.710592Z","iopub.execute_input":"2022-12-11T09:44:10.711296Z","iopub.status.idle":"2022-12-11T09:44:10.717362Z","shell.execute_reply.started":"2022-12-11T09:44:10.711202Z","shell.execute_reply":"2022-12-11T09:44:10.716609Z"},"trusted":true},"execution_count":17,"outputs":[]},{"cell_type":"code","source":"a[np.ix_(x.any(1),x.any(0))]","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:10.718478Z","iopub.execute_input":"2022-12-11T09:44:10.718829Z","iopub.status.idle":"2022-12-11T09:44:10.728234Z","shell.execute_reply.started":"2022-12-11T09:44:10.718796Z","shell.execute_reply":"2022-12-11T09:44:10.727432Z"},"trusted":true},"execution_count":18,"outputs":[{"execution_count":18,"output_type":"execute_result","data":{"text/plain":"array([[10, 10, 10, 10,  7,  8],\n       [13, 14, 15, 16, 17, 18]])"},"metadata":{}}]},{"cell_type":"code","source":"def get_network(args):\n\n    if args.net == 'vgg16':\n        from models.vgg import vgg16\n        net = vgg16()\n\n    elif args.net == 'vgg11':\n        from models.vgg import vgg11\n        net = vgg11()\n    \n    elif args.net == 'vgg13':\n        from models.vgg import vgg13\n        net = vgg13()\n    \n    elif args.net == 'vgg19':\n        from models.vgg import vgg19\n        net = vgg19()\n\n    return net","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:10.729485Z","iopub.execute_input":"2022-12-11T09:44:10.729943Z","iopub.status.idle":"2022-12-11T09:44:10.736981Z","shell.execute_reply.started":"2022-12-11T09:44:10.729902Z","shell.execute_reply":"2022-12-11T09:44:10.736099Z"},"trusted":true},"execution_count":19,"outputs":[]},{"cell_type":"code","source":"class MyDataset(Dataset):\n    \n    def __init__(self, dataframe, transform=None):\n        self.df = dataframe\n        self.transform = transform\n    \n    def __len__(self):\n        return len(self.df)\n    \n    def __getitem__(self, idx):\n        \n        label = self.df.diagnosis.values[idx]\n        label = np.expand_dims(label, -1)\n        \n        p = self.df.id_code.values[idx]\n        p_path = expand_path(p)\n        image = cv2.imread(p_path)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n        image = crop_image_from_gray(image)\n        image = cv2.resize(image, (IMG_SIZE, IMG_SIZE))\n        image = cv2.addWeighted ( image,4, cv2.GaussianBlur( image , (0,0) , 30) ,-4 ,128)\n        image = transforms.ToPILImage()(image)\n        \n        if self.transform:\n            image = self.transform(image)\n        \n        return image, label\n\n\n# Data Transformation\ntrain_transform = transforms.Compose([\n    transforms.RandomHorizontalFlip(),\n    transforms.RandomVerticalFlip(),\n    transforms.RandomAffine(degrees=360, scale=(1.05, 1.25)),\n    transforms.ColorJitter(brightness=0.5, contrast=0.5, saturation=0.5, hue=0.1),\n    transforms.RandomRotation((-120, 120)),\n    transforms.ToTensor(),\n    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])\n\ntest_transform = transforms.Compose([\n    transforms.RandomHorizontalFlip(),\n    transforms.RandomAffine(degrees=360, scale=(1.05, 1.25)),\n    transforms.ColorJitter(brightness=0.5, contrast=0.5, saturation=0.5, hue=0.1),\n    transforms.RandomRotation((-120, 120)),\n    transforms.ToTensor(),\n    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])\n\n\ntrainset     = MyDataset(train_df, transform =train_transform)\ntrain_loader = torch.utils.data.DataLoader(trainset, batch_size=8, shuffle=True, num_workers=4)\nvalset       = MyDataset(val_df, transform  =test_transform)\nval_loader   = torch.utils.data.DataLoader(valset, batch_size=8, shuffle=False, num_workers=4)\n\n\n# Model Architecture\nmodel = EfficientNet.from_name('efficientnet-b4')\nmodel.load_state_dict(torch.load('/kaggle/input/efficientnet-pytorch/efficientnet-b4-e116e8b3.pth'))\n\n# # Freeze model weights to warmup learning rate\n# for param in model.parameters():\n#     param.requires_grad = False\n\nin_features = model._fc.in_features\nmodel._fc = nn.Linear(in_features, num_classes)\nmodel.cuda()\n","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:10.738292Z","iopub.execute_input":"2022-12-11T09:44:10.738543Z","iopub.status.idle":"2022-12-11T09:44:18.586094Z","shell.execute_reply.started":"2022-12-11T09:44:10.738511Z","shell.execute_reply":"2022-12-11T09:44:18.585384Z"},"trusted":true},"execution_count":20,"outputs":[{"execution_count":20,"output_type":"execute_result","data":{"text/plain":"EfficientNet(\n  (_conv_stem): Conv2dStaticSamePadding(\n    3, 48, kernel_size=(3, 3), stride=(2, 2), bias=False\n    (static_padding): ZeroPad2d(padding=(0, 1, 0, 1), value=0.0)\n  )\n  (_bn0): BatchNorm2d(48, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n  (_blocks): ModuleList(\n    (0): MBConvBlock(\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        48, 48, kernel_size=(3, 3), stride=[1, 1], groups=48, bias=False\n        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)\n      )\n      (_bn1): BatchNorm2d(48, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        48, 12, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        12, 48, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        48, 24, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(24, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (1): MBConvBlock(\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        24, 24, kernel_size=(3, 3), stride=(1, 1), groups=24, bias=False\n        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)\n      )\n      (_bn1): BatchNorm2d(24, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        24, 6, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        6, 24, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        24, 24, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(24, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (2): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        24, 144, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(144, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        144, 144, kernel_size=(3, 3), stride=[2, 2], groups=144, bias=False\n        (static_padding): ZeroPad2d(padding=(0, 1, 0, 1), value=0.0)\n      )\n      (_bn1): BatchNorm2d(144, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        144, 6, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        6, 144, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        144, 32, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(32, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (3): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        192, 192, kernel_size=(3, 3), stride=(1, 1), groups=192, bias=False\n        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)\n      )\n      (_bn1): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        192, 8, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        8, 192, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(32, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (4): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        192, 192, kernel_size=(3, 3), stride=(1, 1), groups=192, bias=False\n        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)\n      )\n      (_bn1): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        192, 8, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        8, 192, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(32, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (5): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        192, 192, kernel_size=(3, 3), stride=(1, 1), groups=192, bias=False\n        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)\n      )\n      (_bn1): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        192, 8, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        8, 192, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        192, 32, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(32, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (6): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        32, 192, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        192, 192, kernel_size=(5, 5), stride=[2, 2], groups=192, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(192, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        192, 8, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        8, 192, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        192, 56, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(56, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (7): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        56, 336, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(336, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        336, 336, kernel_size=(5, 5), stride=(1, 1), groups=336, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(336, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        336, 14, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        14, 336, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        336, 56, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(56, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (8): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        56, 336, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(336, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        336, 336, kernel_size=(5, 5), stride=(1, 1), groups=336, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(336, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        336, 14, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        14, 336, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        336, 56, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(56, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (9): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        56, 336, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(336, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        336, 336, kernel_size=(5, 5), stride=(1, 1), groups=336, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(336, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        336, 14, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        14, 336, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        336, 56, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(56, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (10): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        56, 336, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(336, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        336, 336, kernel_size=(3, 3), stride=[2, 2], groups=336, bias=False\n        (static_padding): ZeroPad2d(padding=(0, 1, 0, 1), value=0.0)\n      )\n      (_bn1): BatchNorm2d(336, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        336, 14, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        14, 336, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        336, 112, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (11): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        672, 672, kernel_size=(3, 3), stride=(1, 1), groups=672, bias=False\n        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)\n      )\n      (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        672, 28, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        28, 672, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (12): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        672, 672, kernel_size=(3, 3), stride=(1, 1), groups=672, bias=False\n        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)\n      )\n      (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        672, 28, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        28, 672, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (13): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        672, 672, kernel_size=(3, 3), stride=(1, 1), groups=672, bias=False\n        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)\n      )\n      (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        672, 28, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        28, 672, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (14): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        672, 672, kernel_size=(3, 3), stride=(1, 1), groups=672, bias=False\n        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)\n      )\n      (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        672, 28, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        28, 672, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (15): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        672, 672, kernel_size=(3, 3), stride=(1, 1), groups=672, bias=False\n        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)\n      )\n      (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        672, 28, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        28, 672, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        672, 112, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(112, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (16): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        112, 672, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        672, 672, kernel_size=(5, 5), stride=[1, 1], groups=672, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(672, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        672, 28, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        28, 672, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        672, 160, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(160, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (17): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(960, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        960, 960, kernel_size=(5, 5), stride=(1, 1), groups=960, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(960, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        960, 40, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        40, 960, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(160, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (18): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(960, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        960, 960, kernel_size=(5, 5), stride=(1, 1), groups=960, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(960, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        960, 40, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        40, 960, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(160, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (19): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(960, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        960, 960, kernel_size=(5, 5), stride=(1, 1), groups=960, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(960, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        960, 40, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        40, 960, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(160, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (20): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(960, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        960, 960, kernel_size=(5, 5), stride=(1, 1), groups=960, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(960, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        960, 40, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        40, 960, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(160, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (21): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(960, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        960, 960, kernel_size=(5, 5), stride=(1, 1), groups=960, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(960, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        960, 40, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        40, 960, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        960, 160, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(160, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (22): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        160, 960, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(960, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        960, 960, kernel_size=(5, 5), stride=[2, 2], groups=960, bias=False\n        (static_padding): ZeroPad2d(padding=(1, 2, 1, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(960, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        960, 40, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        40, 960, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        960, 272, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(272, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (23): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        272, 1632, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        1632, 1632, kernel_size=(5, 5), stride=(1, 1), groups=1632, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        1632, 68, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        68, 1632, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        1632, 272, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(272, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (24): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        272, 1632, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        1632, 1632, kernel_size=(5, 5), stride=(1, 1), groups=1632, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        1632, 68, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        68, 1632, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        1632, 272, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(272, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (25): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        272, 1632, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        1632, 1632, kernel_size=(5, 5), stride=(1, 1), groups=1632, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        1632, 68, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        68, 1632, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        1632, 272, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(272, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (26): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        272, 1632, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        1632, 1632, kernel_size=(5, 5), stride=(1, 1), groups=1632, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        1632, 68, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        68, 1632, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        1632, 272, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(272, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (27): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        272, 1632, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        1632, 1632, kernel_size=(5, 5), stride=(1, 1), groups=1632, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        1632, 68, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        68, 1632, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        1632, 272, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(272, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (28): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        272, 1632, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        1632, 1632, kernel_size=(5, 5), stride=(1, 1), groups=1632, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        1632, 68, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        68, 1632, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        1632, 272, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(272, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (29): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        272, 1632, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        1632, 1632, kernel_size=(5, 5), stride=(1, 1), groups=1632, bias=False\n        (static_padding): ZeroPad2d(padding=(2, 2, 2, 2), value=0.0)\n      )\n      (_bn1): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        1632, 68, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        68, 1632, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        1632, 272, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(272, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (30): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        272, 1632, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        1632, 1632, kernel_size=(3, 3), stride=[1, 1], groups=1632, bias=False\n        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)\n      )\n      (_bn1): BatchNorm2d(1632, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        1632, 68, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        68, 1632, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        1632, 448, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(448, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n    (31): MBConvBlock(\n      (_expand_conv): Conv2dStaticSamePadding(\n        448, 2688, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn0): BatchNorm2d(2688, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_depthwise_conv): Conv2dStaticSamePadding(\n        2688, 2688, kernel_size=(3, 3), stride=(1, 1), groups=2688, bias=False\n        (static_padding): ZeroPad2d(padding=(1, 1, 1, 1), value=0.0)\n      )\n      (_bn1): BatchNorm2d(2688, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_se_reduce): Conv2dStaticSamePadding(\n        2688, 112, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_se_expand): Conv2dStaticSamePadding(\n        112, 2688, kernel_size=(1, 1), stride=(1, 1)\n        (static_padding): Identity()\n      )\n      (_project_conv): Conv2dStaticSamePadding(\n        2688, 448, kernel_size=(1, 1), stride=(1, 1), bias=False\n        (static_padding): Identity()\n      )\n      (_bn2): BatchNorm2d(448, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n      (_swish): MemoryEfficientSwish()\n    )\n  )\n  (_conv_head): Conv2dStaticSamePadding(\n    448, 1792, kernel_size=(1, 1), stride=(1, 1), bias=False\n    (static_padding): Identity()\n  )\n  (_bn1): BatchNorm2d(1792, eps=0.001, momentum=0.010000000000000009, affine=True, track_running_stats=True)\n  (_avg_pooling): AdaptiveAvgPool2d(output_size=1)\n  (_dropout): Dropout(p=0.4, inplace=False)\n  (_fc): Linear(in_features=1792, out_features=1, bias=True)\n  (_swish): MemoryEfficientSwish()\n)"},"metadata":{}}]},{"cell_type":"code","source":"# Class weight\nfrom sklearn.utils import class_weight\nclass_weight_ = class_weight.compute_class_weight(\n                                                 class_weight = 'balanced',\n                                                 classes = np.unique(train_df['diagnosis']),\n                                                 y = train_df['diagnosis']\n                                                 )\nclass_weight_ = torch.from_numpy(class_weight_)\n\n\nfrom sklearn.metrics import cohen_kappa_score\ndef quadratic_kappa(y_hat, y):\n    return torch.tensor(cohen_kappa_score(y_hat, y, weights='quadratic')).cuda()\n    # return torch.tensor(cohen_kappa_score(torch.round(y_hat), y, weights='quadratic'),device='cuda:0')","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:18.587349Z","iopub.execute_input":"2022-12-11T09:44:18.587753Z","iopub.status.idle":"2022-12-11T09:44:18.595724Z","shell.execute_reply.started":"2022-12-11T09:44:18.58771Z","shell.execute_reply":"2022-12-11T09:44:18.595024Z"},"trusted":true},"execution_count":21,"outputs":[]},{"cell_type":"code","source":"def get_label(output_test):\n    label = 0\n    if output_test < coef[0]:\n        label = 0\n    elif output_test >= coef[0] and output_test < coef[1]:\n        label = 1\n    elif output_test >= coef[1] and output_test < coef[2]:\n        label = 2\n    elif output_test >= coef[2] and output_test < coef[3]:\n        label = 3\n    else:\n        label = 4\n\n    return label\n","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:18.597194Z","iopub.execute_input":"2022-12-11T09:44:18.5975Z","iopub.status.idle":"2022-12-11T09:44:18.607281Z","shell.execute_reply.started":"2022-12-11T09:44:18.597466Z","shell.execute_reply":"2022-12-11T09:44:18.606555Z"},"trusted":true},"execution_count":22,"outputs":[]},{"cell_type":"code","source":"# Optimizer for Kappa score\nclass OptimizedRounder(object):\n    def __init__(self):\n        self.coef_ = 0\n\n    def _kappa_loss(self, coef, X, y):\n        X_p = np.copy(X)\n        for i, pred in enumerate(X_p):\n            X_p[i] = get_label(pred)\n\n        ll = cohen_kappa_score(y, X_p, weights='quadratic')\n        return -ll\n\n    def fit(self, X, y):\n        loss_partial = partial(self._kappa_loss, X=X, y=y)\n        initial_coef = [0.5, 1.5, 2.5, 3.5]\n        self.coef_ = sp.optimize.minimize(loss_partial, initial_coef, method='nelder-mead')\n\n    def predict(self, X, coef):\n        X_p = np.copy(X)\n        for i, pred in enumerate(X_p):\n            X_p[i] = get_label(pred)\n\n        return X_p\n\n    def coefficients(self):\n        return self.coef_['x']\n\n\nclass LogCoshLoss(torch.nn.Module):\n    def __init__(self):\n        super().__init__()\n\n    def forward(self, y_t, y_prime_t):\n        ey_t = y_t - y_prime_t\n        return torch.mean(torch.log(torch.cosh(ey_t + 1e-12)))\n","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:18.60852Z","iopub.execute_input":"2022-12-11T09:44:18.608832Z","iopub.status.idle":"2022-12-11T09:44:18.619126Z","shell.execute_reply.started":"2022-12-11T09:44:18.608793Z","shell.execute_reply":"2022-12-11T09:44:18.618343Z"},"trusted":true},"execution_count":23,"outputs":[]},{"cell_type":"code","source":"# Training Config\n\n# Apply no bias decay\n# params = split_weights(model)\noptimizer = torch.optim.Adam(model.parameters(), lr=lr, weight_decay=1e-5)\n\n# criterion = LogCoshLoss()\ncriterion = nn.MSELoss() \nscheduler_step = torch.optim.lr_scheduler.StepLR(optimizer, step_size=5, gamma=0.1)\n# scheduler_warmup = GradualWarmupScheduler(optimizer, multiplier=10, total_epoch=5, after_scheduler=scheduler_step)\n# model, optimizer = amp.initialize(model, optimizer, opt_level=\"O1\",verbosity=0)\n","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:18.620335Z","iopub.execute_input":"2022-12-11T09:44:18.620637Z","iopub.status.idle":"2022-12-11T09:44:18.637301Z","shell.execute_reply.started":"2022-12-11T09:44:18.620605Z","shell.execute_reply":"2022-12-11T09:44:18.636593Z"},"trusted":true},"execution_count":24,"outputs":[]},{"cell_type":"code","source":"# Training\ndef train_model(epoch):\n    model.train()\n        \n    avg_loss = 0.\n    optimizer.zero_grad()\n    for idx, (imgs, labels) in enumerate(train_loader):\n        imgs_train, labels_train = imgs.cuda(), labels.float().cuda()\n        output_train = model(imgs_train)\n        loss = criterion(output_train,labels_train)\n        with amp.scale_loss(loss, optimizer) as scaled_loss:\n            scaled_loss.backward()\n        optimizer.step()\n        optimizer.zero_grad()\n        avg_loss += loss.item() / len(train_loader)\n        \n    return avg_loss\n\ndef test_model():\n    correct = 0\n    total = 0\n    preds = []\n    truth_labels = []\n    \n    avg_val_loss = 0.\n    model.eval()\n    with torch.no_grad():\n        for idx, (imgs, labels) in enumerate(val_loader):\n            imgs_vaild, labels_vaild = imgs.cuda(), labels.float().cuda()\n            output_test = model(imgs_vaild)\n            avg_val_loss += criterion(output_test, labels_vaild).item() / len(val_loader)\n\n            for i in range(len(output_test)):\n                pred_label = get_label(output_test[i][0])\n                correct += (int(pred_label) == int(labels[i][0]))\n                total += 1\n\n                preds.append(int(pred_label))\n                truth_labels.append(int(labels[i][0]))\n            \n    preds = np.array(preds)\n    truth_labels = np.array(truth_labels)\n\n    kappa_score = quadratic_kappa(preds, truth_labels)\n    val_acc = correct * 100.0 / total\n        \n    return avg_val_loss, val_acc, kappa_score\n\n\nbest_avg_loss = 100.0\nbest_val_acc = 0.0\nbest_kappa_score = -100.0\n\nprint('transforms.RandomAffine(degrees=360, translate=(0.05, 0.05), scale=(1, 1.3)), \\\n    transforms.ColorJitter(brightness=0.5, contrast=0.5, saturation=0.5, hue=0.1), \\\n    transforms.RandomRotation((-120, 120))')\nprint('Model: 20190905_data3k_effib4_aug_adjust_clean_testzoom.pt')\n\nprint()\n\n\nprint('Start Training!')\nprint('-' * 10)\nfor epoch in range(n_epochs):\n    \n    print('Epoch {}/{}:' .format(epoch + 1, n_epochs))\n    print('lr:', scheduler_step.get_lr()[0]) \n    start_time   = time.time()\n    avg_loss     = train_model(epoch)\n    avg_val_loss, val_acc, kappa_score = test_model()\n    elapsed_time = time.time() - start_time \n    # print('Epoch {}/{} \\t loss={:.4f} \\t val_loss={:.4f} \\t val_acc={:.4f}% \\t time={:.2f}s'.format(\n    #     epoch + 1, n_epochs, avg_loss, avg_val_loss, val_acc, elapsed_time))\n    \n    print('Train: loss={:.4f}  \\t  Valid: val_loss={:.4f}  \\t  val_acc={:.4f}  \\t  val_kappa={:4f}  \\t  Time={:.2f}' .format(avg_loss, avg_val_loss, val_acc, kappa_score, elapsed_time))\n    print()\n\n    if avg_val_loss < best_avg_loss:\n        best_avg_loss = avg_val_loss\n        torch.save(model.state_dict(), '/kaggle/working/20190905_data3k_effib4_aug_adjust_clean_testzoom.pt')\n        print('Better val_loss. Model saved!')\n\n    # if val_acc > best_val_acc:\n    #     best_val_acc = val_acc\n    #     torch.save(model.state_dict(), './saved_model/20190816_2_data3k_effib4.pt')\n    #     print('Better val_accuracy. Model saved!')\n\n    # if kappa_score > best_kappa_score:\n    #     best_kappa_score = kappa_score\n    #     torch.save(model.state_dict(), './saved_model/20190829_data3k_effib4_aug_huber.pt')\n    #     print('Better kappa_score. Model saved!')\n    \n    scheduler_step.step()\n    print('-' * 10)\n\nprint('Finish Training!')","metadata":{"execution":{"iopub.status.busy":"2022-12-11T09:44:18.638463Z","iopub.execute_input":"2022-12-11T09:44:18.639086Z"},"trusted":true},"execution_count":null,"outputs":[{"name":"stdout","text":"transforms.RandomAffine(degrees=360, translate=(0.05, 0.05), scale=(1, 1.3)),     transforms.ColorJitter(brightness=0.5, contrast=0.5, saturation=0.5, hue=0.1),     transforms.RandomRotation((-120, 120))\nModel: 20190905_data3k_effib4_aug_adjust_clean_testzoom.pt\n\nStart Training!\n----------\nEpoch 1/30:\nlr: 0.001\n","output_type":"stream"},{"name":"stderr","text":"/opt/conda/lib/python3.7/site-packages/torch/optim/lr_scheduler.py:370: UserWarning: To get the last learning rate computed by the scheduler, please use `get_last_lr()`.\n  \"please use `get_last_lr()`.\", UserWarning)\n","output_type":"stream"}]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}