{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Introduction\n\n**Main Topic**\n\nThis notebook will simply plug-in [SAM Optimizer](https://github.com/google-research/sam) from [pytorch baseline](https://www.kaggle.com/khyeh0719/pytorch-efficientnet-baseline-train-amp-aug) written by [@khyeh0719](https://www.kaggle.com/khyeh0719).\n\nIt increased Baseline LB score from 0.896 -> 0.9. but I used epoch [7, 8, 9, 19] instead of original configs [6, 7, 8, 9]. so It's a bit hard to compare on it but you guys easly can test plug-in SAM Optimizer on your models.\n\nmost of code below is same from original baseline, I just added SAM optimizer from on it. so if you want to check SAM Optimizer part, just click Define-SAM-Optimizer part of notebook contents.\n\nAnd [github source](https://github.com/davda54/sam) which i refer is not offical implement so maybe there is error to implement. Let me know about it.\n\n\n\n**References**\n\n[**Sharpness-Aware Minimization for Efficiently Improving Generalization**](https://arxiv.org/abs/2010.01412)\n\n[**Sharpness-Aware Minimization for Efficiently Improving Generalization in Pytorch**](https://github.com/davda54/sam)\n\n[**Pytorch Efficientnet Baseline [Train] AMP+Aug**](https://www.kaggle.com/khyeh0719/pytorch-efficientnet-baseline-train-amp-aug)"},{"metadata":{},"cell_type":"markdown","source":"## SAM Optimizer\n\nSharpness-Aware Minimization simultaneously minimizes loss value and loss sharpness. In particular, it seeks parameters that lie in neighborhoods having uniformly low loss. SAM improves model generalization and yields SoTA performance for several datasets. Additionally, it provides robustness to label noise on par with that provided by [SoTA procedures](https://paperswithcode.com/paper/sharpness-aware-minimization-for-efficiently-1) that specifically target learning with noisy labels.\n\n![image.png](attachment:image.png)\n\nResNet loss landscape at the end of training with and without SAM. Sharpness-aware updates lead to a significantly wider minimum, which then leads to better generalization properties.\n\n\n","attachments":{"image.png":{"image/png":"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"}}},{"metadata":{},"cell_type":"markdown","source":"EffNet with SAM Optimizer achieved SoTA on most of cImage Classification Tasks. So we can try to plug-in this optimizer with our on model."},{"metadata":{"trusted":true},"cell_type":"code","source":"package_paths = [\n    '../input/pytorch-image-models/pytorch-image-models-master', #'../input/efficientnet-pytorch-07/efficientnet_pytorch-0.7.0'\n    '../input/image-fmix/FMix-master'\n]\nimport sys; \n\nfor pth in package_paths:\n    sys.path.append(pth)\n    \nfrom fmix import sample_mask, make_low_freq_image, binarise_mask","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"from glob import glob\nfrom sklearn.model_selection import GroupKFold, StratifiedKFold\nimport cv2\nfrom skimage import io\nimport torch\nfrom torch import nn\nimport os\nfrom datetime import datetime\nimport time\nimport random\nimport cv2\nimport torchvision\nfrom torchvision import transforms\nimport pandas as pd\nimport numpy as np\nfrom tqdm import tqdm\n\nimport matplotlib.pyplot as plt\nfrom torch.utils.data import Dataset,DataLoader\nfrom torch.utils.data.sampler import SequentialSampler, RandomSampler\nfrom torch.cuda.amp import autocast, GradScaler\nfrom torch.nn.modules.loss import _WeightedLoss\nimport torch.nn.functional as F\n\nimport timm\n\nimport sklearn\nimport warnings\nimport joblib\nfrom sklearn.metrics import roc_auc_score, log_loss\nfrom sklearn import metrics\nimport warnings\nimport cv2\nimport pydicom\n#from efficientnet_pytorch import EfficientNet\nfrom scipy.ndimage.interpolation import zoom","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"CFG = {\n    'fold_num': 5,\n    'seed': 719,\n    'model_arch': 'tf_efficientnet_b4_ns',\n    'img_size': 512,\n    'epochs': 10,\n    'train_bs': 16,\n    'valid_bs': 32,\n    'T_0': 10,\n    'lr': 1e-4,\n    'min_lr': 1e-6,\n    'weight_decay':1e-6,\n    'num_workers': 4,\n    'accum_iter': 2, # suppoprt to do batch accumulation for backprop with effectively larger batch size\n    'verbose_step': 1,\n    'device': 'cuda:0'\n}","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv('../input/cassava-leaf-disease-classification/train.csv')\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.label.value_counts()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"> We could do stratified validation split in each fold to make each fold's train and validation set looks like the whole train set in target distributions."},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.read_csv('../input/cassava-leaf-disease-classification/sample_submission.csv')\nsubmission.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Helper Functions"},{"metadata":{"trusted":true},"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\n    torch.backends.cudnn.benchmark = True\n    \ndef get_img(path):\n    im_bgr = cv2.imread(path)\n    im_rgb = im_bgr[:, :, ::-1]\n    #print(im_rgb)\n    return im_rgb\n\nimg = get_img('../input/cassava-leaf-disease-classification/train_images/1000015157.jpg')\nplt.imshow(img)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Dataset"},{"metadata":{"trusted":true},"cell_type":"code","source":"def rand_bbox(size, lam):\n    W = size[0]\n    H = size[1]\n    cut_rat = np.sqrt(1. - lam)\n    cut_w = np.int(W * cut_rat)\n    cut_h = np.int(H * cut_rat)\n\n    # uniform\n    cx = np.random.randint(W)\n    cy = np.random.randint(H)\n\n    bbx1 = np.clip(cx - cut_w // 2, 0, W)\n    bby1 = np.clip(cy - cut_h // 2, 0, H)\n    bbx2 = np.clip(cx + cut_w // 2, 0, W)\n    bby2 = np.clip(cy + cut_h // 2, 0, H)\n    return bbx1, bby1, bbx2, bby2\n\n\nclass CassavaDataset(Dataset):\n    def __init__(self, df, data_root, \n                 transforms=None, \n                 output_label=True, \n                 one_hot_label=False,\n                 do_fmix=False, \n                 fmix_params={\n                     'alpha': 1., \n                     'decay_power': 3., \n                     'shape': (CFG['img_size'], CFG['img_size']),\n                     'max_soft': True, \n                     'reformulate': False\n                 },\n                 do_cutmix=False,\n                 cutmix_params={\n                     'alpha': 1,\n                 }\n                ):\n        \n        super().__init__()\n        self.df = df.reset_index(drop=True).copy()\n        self.transforms = transforms\n        self.data_root = data_root\n        self.do_fmix = do_fmix\n        self.fmix_params = fmix_params\n        self.do_cutmix = do_cutmix\n        self.cutmix_params = cutmix_params\n        \n        self.output_label = output_label\n        self.one_hot_label = one_hot_label\n        \n        if output_label == True:\n            self.labels = self.df['label'].values\n            #print(self.labels)\n            \n            if one_hot_label is True:\n                self.labels = np.eye(self.df['label'].max()+1)[self.labels]\n                #print(self.labels)\n            \n    def __len__(self):\n        return self.df.shape[0]\n    \n    def __getitem__(self, index: int):\n        \n        # get labels\n        if self.output_label:\n            target = self.labels[index]\n          \n        img  = get_img(\"{}/{}\".format(self.data_root, self.df.loc[index]['image_id']))\n\n        if self.transforms:\n            img = self.transforms(image=img)['image']\n        \n        if self.do_fmix and np.random.uniform(0., 1., size=1)[0] > 0.5:\n            with torch.no_grad():\n                #lam, mask = sample_mask(**self.fmix_params)\n                \n                lam = np.clip(np.random.beta(self.fmix_params['alpha'], self.fmix_params['alpha']),0.6,0.7)\n                \n                # Make mask, get mean / std\n                mask = make_low_freq_image(self.fmix_params['decay_power'], self.fmix_params['shape'])\n                mask = binarise_mask(mask, lam, self.fmix_params['shape'], self.fmix_params['max_soft'])\n    \n                fmix_ix = np.random.choice(self.df.index, size=1)[0]\n                fmix_img  = get_img(\"{}/{}\".format(self.data_root, self.df.iloc[fmix_ix]['image_id']))\n\n                if self.transforms:\n                    fmix_img = self.transforms(image=fmix_img)['image']\n\n                mask_torch = torch.from_numpy(mask)\n                \n                # mix image\n                img = mask_torch*img+(1.-mask_torch)*fmix_img\n\n                #print(mask.shape)\n\n                #assert self.output_label==True and self.one_hot_label==True\n\n                # mix target\n                rate = mask.sum()/CFG['img_size']/CFG['img_size']\n                target = rate*target + (1.-rate)*self.labels[fmix_ix]\n                #print(target, mask, img)\n                #assert False\n        \n        if self.do_cutmix and np.random.uniform(0., 1., size=1)[0] > 0.5:\n            #print(img.sum(), img.shape)\n            with torch.no_grad():\n                cmix_ix = np.random.choice(self.df.index, size=1)[0]\n                cmix_img  = get_img(\"{}/{}\".format(self.data_root, self.df.iloc[cmix_ix]['image_id']))\n                if self.transforms:\n                    cmix_img = self.transforms(image=cmix_img)['image']\n                    \n                lam = np.clip(np.random.beta(self.cutmix_params['alpha'], self.cutmix_params['alpha']),0.3,0.4)\n                bbx1, bby1, bbx2, bby2 = rand_bbox((CFG['img_size'], CFG['img_size']), lam)\n\n                img[:, bbx1:bbx2, bby1:bby2] = cmix_img[:, bbx1:bbx2, bby1:bby2]\n\n                rate = 1 - ((bbx2 - bbx1) * (bby2 - bby1) / (CFG['img_size'] * CFG['img_size']))\n                target = rate*target + (1.-rate)*self.labels[cmix_ix]\n                \n            #print('-', img.sum())\n            #print(target)\n            #assert False\n                            \n        # do label smoothing\n        #print(type(img), type(target))\n        if self.output_label == True:\n            return img, target\n        else:\n            return img","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Define Train\\Validation Image Augmentations"},{"metadata":{"trusted":true},"cell_type":"code","source":"from albumentations import (\n    HorizontalFlip, VerticalFlip, IAAPerspective, ShiftScaleRotate, CLAHE, RandomRotate90,\n    Transpose, ShiftScaleRotate, Blur, OpticalDistortion, GridDistortion, HueSaturationValue,\n    IAAAdditiveGaussianNoise, GaussNoise, MotionBlur, MedianBlur, IAAPiecewiseAffine, RandomResizedCrop,\n    IAASharpen, IAAEmboss, RandomBrightnessContrast, Flip, OneOf, Compose, Normalize, Cutout, CoarseDropout, ShiftScaleRotate, CenterCrop, Resize\n)\n\nfrom albumentations.pytorch import ToTensorV2\n\ndef get_train_transforms():\n    return Compose([\n            RandomResizedCrop(CFG['img_size'], CFG['img_size']),\n            Transpose(p=0.5),\n            HorizontalFlip(p=0.5),\n            VerticalFlip(p=0.5),\n            ShiftScaleRotate(p=0.5),\n            HueSaturationValue(hue_shift_limit=0.2, sat_shift_limit=0.2, val_shift_limit=0.2, p=0.5),\n            RandomBrightnessContrast(brightness_limit=(-0.1,0.1), contrast_limit=(-0.1, 0.1), p=0.5),\n            Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225], max_pixel_value=255.0, p=1.0),\n            CoarseDropout(p=0.5),\n            Cutout(p=0.5),\n            ToTensorV2(p=1.0),\n        ], p=1.)\n  \n        \ndef get_valid_transforms():\n    return Compose([\n            CenterCrop(CFG['img_size'], CFG['img_size'], p=1.),\n            Resize(CFG['img_size'], CFG['img_size']),\n            Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225], max_pixel_value=255.0, p=1.0),\n            ToTensorV2(p=1.0),\n        ], p=1.)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Model"},{"metadata":{"trusted":true},"cell_type":"code","source":"class CassvaImgClassifier(nn.Module):\n    def __init__(self, model_arch, n_class, pretrained=False):\n        super().__init__()\n        self.model = timm.create_model(model_arch, pretrained=pretrained)\n        n_features = self.model.classifier.in_features\n        self.model.classifier = nn.Linear(n_features, n_class)\n        '''\n        self.model.classifier = nn.Sequential(\n            nn.Dropout(0.3),\n            #nn.Linear(n_features, hidden_size,bias=True), nn.ELU(),\n            nn.Linear(n_features, n_class, bias=True)\n        )\n        '''\n    def forward(self, x):\n        x = self.model(x)\n        return x","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Define SAM Optimizer\n\n\noriginal source is [here](https://github.com/davda54/sam/blob/main/sam.py).\n\nAfter we define SAM Optimizer we just need to modify two part from below Training APIs, Main Loop\n\n- Main Loop : modify Optimizer adam to SAM, we need to call SGD first.\n- Training APIs : modify Optimizer with two step.\n\nI'll explan detail in title of Main Loop, Training APIs"},{"metadata":{"trusted":true},"cell_type":"code","source":"## original source is https://github.com/davda54/sam/blob/main/sam.py\n\nimport torch\n\n\nclass SAM(torch.optim.Optimizer):\n    def __init__(self, params, base_optimizer, rho=0.05, **kwargs):\n        assert rho >= 0.0, f\"Invalid rho, should be non-negative: {rho}\"\n\n        defaults = dict(rho=rho, **kwargs)\n        super(SAM, self).__init__(params, defaults)\n\n        self.base_optimizer = base_optimizer(self.param_groups, **kwargs)\n        self.param_groups = self.base_optimizer.param_groups\n\n    @torch.no_grad()\n    def first_step(self, zero_grad=False):\n        grad_norm = self._grad_norm()\n        for group in self.param_groups:\n            scale = group[\"rho\"] / (grad_norm + 1e-12)\n\n            for p in group[\"params\"]:\n                if p.grad is None: continue\n                e_w = p.grad * scale.to(p)\n                p.add_(e_w)  # climb to the local maximum \"w + e(w)\"\n                self.state[p][\"e_w\"] = e_w\n\n        if zero_grad: self.zero_grad()\n\n    @torch.no_grad()\n    def second_step(self, zero_grad=False):\n        for group in self.param_groups:\n            for p in group[\"params\"]:\n                if p.grad is None: continue\n                p.sub_(self.state[p][\"e_w\"])  # get back to \"w\" from \"w + e(w)\"\n\n        self.base_optimizer.step()  # do the actual \"sharpness-aware\" update\n\n        if zero_grad: self.zero_grad()\n\n    def step(self, closure=None):\n        raise NotImplementedError(\"SAM doesn't work like the other optimizers, you should first call `first_step` and the `second_step`; see the documentation for more info.\")\n\n    def _grad_norm(self):\n        shared_device = self.param_groups[0][\"params\"][0].device  # put everything on the same device, in case of model parallelism\n        norm = torch.norm(\n                    torch.stack([\n                        p.grad.norm(p=2).to(shared_device)\n                        for group in self.param_groups for p in group[\"params\"]\n                        if p.grad is not None\n                    ]),\n                    p=2\n               )\n        return norm","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Training APIs\n\nSAM Optimizer needs two forward-backward passes to estime the \"sharpness-aware\" gradient. so we need to change opmizer like this code.\n\n    loss = loss_fn(image_preds, image_labels) \n    loss.backward()\n    optimizer.first_step(zero_grad=True)\n\n    # second forward-backward pass\n    loss_fn(model(imgs), image_labels).backward()\n    optimizer.second_step(zero_grad=True)\n    \nnote that I skipped gradients clipping step caues it made a error with SAM Optimizer, you can modify this if you want."},{"metadata":{"trusted":true},"cell_type":"code","source":"def prepare_dataloader(df, trn_idx, val_idx, data_root='../input/cassava-leaf-disease-classification/train_images/'):\n    \n    from catalyst.data.sampler import BalanceClassSampler\n    \n    train_ = df.loc[trn_idx,:].reset_index(drop=True)\n    valid_ = df.loc[val_idx,:].reset_index(drop=True)\n        \n    train_ds = CassavaDataset(train_, data_root, transforms=get_train_transforms(), output_label=True, one_hot_label=False, do_fmix=False, do_cutmix=False)\n    valid_ds = CassavaDataset(valid_, data_root, transforms=get_valid_transforms(), output_label=True)\n    \n    train_loader = torch.utils.data.DataLoader(\n        train_ds,\n        batch_size=CFG['train_bs'],\n        pin_memory=False,\n        drop_last=False,\n        shuffle=True,        \n        num_workers=CFG['num_workers'],\n        #sampler=BalanceClassSampler(labels=train_['label'].values, mode=\"downsampling\")\n    )\n    val_loader = torch.utils.data.DataLoader(\n        valid_ds, \n        batch_size=CFG['valid_bs'],\n        num_workers=CFG['num_workers'],\n        shuffle=False,\n        pin_memory=False,\n    )\n    return train_loader, val_loader\n\ndef train_one_epoch(epoch, model, loss_fn, optimizer, train_loader, device, scheduler=None, schd_batch_update=False):\n    model.train()\n\n    t = time.time()\n    running_loss = None\n\n    pbar = tqdm(enumerate(train_loader), total=len(train_loader))\n    for step, (imgs, image_labels) in pbar:\n        imgs = imgs.to(device).float()\n        image_labels = image_labels.to(device).long()\n\n        #print(image_labels.shape, exam_label.shape)\n        with autocast():\n            image_preds = model(imgs)   #output = model(input)\n            #print(image_preds.shape, exam_pred.shape)\n\n            loss = loss_fn(image_preds, image_labels) \n            loss.backward()\n            optimizer.first_step(zero_grad=True)\n\n            # second forward-backward pass\n            loss_fn(model(imgs), image_labels).backward()\n            optimizer.second_step(zero_grad=True)\n            \n            \n            if running_loss is None:\n                running_loss = loss.item()\n            else:\n                running_loss = running_loss * .99 + loss.item() * .01\n\n#             if ((step + 1) %  CFG['accum_iter'] == 0) or ((step + 1) == len(train_loader)):\n#                 # may unscale_ here if desired (e.g., to allow clipping unscaled gradients)\n\n#                 scaler.step(optimizer)\n#                 scaler.update()\n#                 optimizer.zero_grad() \n                \n                if scheduler is not None and schd_batch_update:\n                    scheduler.step()\n\n            if ((step + 1) % CFG['verbose_step'] == 0) or ((step + 1) == len(train_loader)):\n                description = f'epoch {epoch} loss: {running_loss:.4f}'\n                \n                pbar.set_description(description)\n                \n    if scheduler is not None and not schd_batch_update:\n        scheduler.step()\n        \ndef valid_one_epoch(epoch, model, loss_fn, val_loader, device, scheduler=None, schd_loss_update=False):\n    model.eval()\n\n    t = time.time()\n    loss_sum = 0\n    sample_num = 0\n    image_preds_all = []\n    image_targets_all = []\n    \n    pbar = tqdm(enumerate(val_loader), total=len(val_loader))\n    for step, (imgs, image_labels) in pbar:\n        imgs = imgs.to(device).float()\n        image_labels = image_labels.to(device).long()\n        \n        image_preds = model(imgs)   #output = model(input)\n        #print(image_preds.shape, exam_pred.shape)\n        image_preds_all += [torch.argmax(image_preds, 1).detach().cpu().numpy()]\n        image_targets_all += [image_labels.detach().cpu().numpy()]\n        \n        loss = loss_fn(image_preds, image_labels)\n        \n        loss_sum += loss.item()*image_labels.shape[0]\n        sample_num += image_labels.shape[0]  \n\n        if ((step + 1) % CFG['verbose_step'] == 0) or ((step + 1) == len(val_loader)):\n            description = f'epoch {epoch} loss: {loss_sum/sample_num:.4f}'\n            pbar.set_description(description)\n    \n    image_preds_all = np.concatenate(image_preds_all)\n    image_targets_all = np.concatenate(image_targets_all)\n    print('validation multi-class accuracy = {:.4f}'.format((image_preds_all==image_targets_all).mean()))\n    \n    if scheduler is not None:\n        if schd_loss_update:\n            scheduler.step(loss_sum/sample_num)\n        else:\n            scheduler.step()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# reference: https://www.kaggle.com/c/siim-isic-melanoma-classification/discussion/173733\nclass MyCrossEntropyLoss(_WeightedLoss):\n    def __init__(self, weight=None, reduction='mean'):\n        super().__init__(weight=weight, reduction=reduction)\n        self.weight = weight\n        self.reduction = reduction\n\n    def forward(self, inputs, targets):\n        lsm = F.log_softmax(inputs, -1)\n\n        if self.weight is not None:\n            lsm = lsm * self.weight.unsqueeze(0)\n\n        loss = -(targets * lsm).sum(-1)\n\n        if  self.reduction == 'sum':\n            loss = loss.sum()\n        elif  self.reduction == 'mean':\n            loss = loss.mean()\n\n        return loss","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Main Loop\n\nsimply change optimizer to SAM Optimizer. we need to call SGD as a base_optimizer.\n\n        base_optimizer = torch.optim.SGD\n        optimizer = SAM(model.parameters(), base_optimizer, lr=0.1, momentum=0.9)  \n"},{"metadata":{"trusted":true},"cell_type":"code","source":"if __name__ == '__main__':\n     # for training only, need nightly build pytorch\n\n    seed_everything(CFG['seed'])\n    \n    folds = StratifiedKFold(n_splits=CFG['fold_num'], shuffle=True, random_state=CFG['seed']).split(np.arange(train.shape[0]), train.label.values)\n    \n    for fold, (trn_idx, val_idx) in enumerate(folds):\n        # we'll train fold 0 first\n        if fold > 0:\n            break \n\n        print('Training with {} started'.format(fold))\n\n        print(len(trn_idx), len(val_idx))\n        train_loader, val_loader = prepare_dataloader(train, trn_idx, val_idx, data_root='../input/cassava-leaf-disease-classification/train_images/')\n\n        device = torch.device(CFG['device'])\n        \n        model = CassvaImgClassifier(CFG['model_arch'], train.label.nunique(), pretrained=True).to(device)\n        scaler = GradScaler() \n        \n        base_optimizer = torch.optim.SGD\n        optimizer = SAM(model.parameters(), base_optimizer, lr=0.1, momentum=0.9)        \n        #optimizer = torch.optim.Adam(model.parameters(), lr=CFG['lr'], weight_decay=CFG['weight_decay'])\n        #scheduler = torch.optim.lr_scheduler.StepLR(optimizer, gamma=0.1, step_size=CFG['epochs']-1)\n        scheduler = torch.optim.lr_scheduler.CosineAnnealingWarmRestarts(optimizer, T_0=CFG['T_0'], T_mult=1, eta_min=CFG['min_lr'], last_epoch=-1)\n        #scheduler = torch.optim.lr_scheduler.OneCycleLR(optimizer=optimizer, pct_start=0.1, div_factor=25, \n        #                                                max_lr=CFG['lr'], epochs=CFG['epochs'], steps_per_epoch=len(train_loader))\n        \n        loss_tr = nn.CrossEntropyLoss().to(device) #MyCrossEntropyLoss().to(device)\n        loss_fn = nn.CrossEntropyLoss().to(device)\n        \n        for epoch in range(CFG['epochs']):\n            train_one_epoch(epoch, model, loss_tr, optimizer, train_loader, device, scheduler=scheduler, schd_batch_update=False)\n\n            with torch.no_grad():\n                valid_one_epoch(epoch, model, loss_fn, val_loader, device, scheduler=None, schd_loss_update=False)\n\n            torch.save(model.state_dict(),'{}_fold_{}_{}'.format(CFG['model_arch'], fold, epoch))\n            \n        #torch.save(model.cnn_model.state_dict(),'{}/cnn_model_fold_{}_{}'.format(CFG['model_path'], fold, CFG['tag']))\n        del model, optimizer, train_loader, val_loader, scaler, scheduler\n        torch.cuda.empty_cache()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Inferece part is here: https://www.kaggle.com/khyeh0719/pytorch-efficientnet-baseline-inference-tta"}],"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":4,"nbformat_minor":4}