{"cells":[{"metadata":{},"cell_type":"markdown","source":"# ADAM -> ADAMP\n\nThis notebook is based on [Pytorch Efficientnet Baseline [Train] AMP+Aug](https://www.kaggle.com/khyeh0719/pytorch-efficientnet-baseline-train-amp-aug)\n\n## Instead of the adam optimizer, I used the ADAMP introduced in ICLR 2021.\n\n### Before: fold0 best accuracy = 0.8932\n\n### After: fold0 best accuracy = 0.8944\n\n\n> AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (ICLR 2021)\n> ![image.png](attachment:image.png)\n> Official PyTorch implementation of AdamP and SGDP optimizers | [Paper](https://arxiv.org/abs/2006.08217) | [Project page](https://github.com/clovaai/AdamP)\n> Byeongho Heo*, Sanghyuk Chun*, Seong Joon Oh, Dongyoon Han, Sangdoo Yun, Gyuwan Kim, Youngjung Uh, Jung-Woo Ha.\n\nInferece part is here: https://www.kaggle.com/khyeh0719/pytorch-efficientnet-baseline-inference-tta","attachments":{"image.png":{"image/png":"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"}}},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install adamp","execution_count":null,"outputs":[]},{"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\nfrom adamp import AdamP\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":"# Training APIs"},{"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            \n            scaler.scale(loss).backward()\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"},{"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        optimizer = AdamP(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":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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}