{"cells":[{"metadata":{},"cell_type":"markdown","source":"# Alaska2 Baseline PyTorch\n\nHi everyone!\n\nMy name is Alex Shonenkov, I am DL/NLP/CV/TS research engineer. Especially I am in Love with NLP & DL.\n\nI would like to share with you my starter pipeline for solving this competition :)","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"# Main Ideas\n\n- 4 Classes\n- GroupKFold splitting\n- Class Balance\n- Flips\n- Label Smoothing\n- EfficientNetB2\n- ReduceLROnPlateau","execution_count":null},{"metadata":{},"cell_type":"markdown","source":"# Dependencies","execution_count":null},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"!pip install -q efficientnet_pytorch > /dev/null","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from glob import glob\nfrom sklearn.model_selection import GroupKFold\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 pandas as pd\nimport numpy as np\nimport albumentations as A\nimport matplotlib.pyplot as plt\nfrom albumentations.pytorch.transforms import ToTensorV2\nfrom torch.utils.data import Dataset,DataLoader\nfrom torch.utils.data.sampler import SequentialSampler, RandomSampler\nimport sklearn\n\nSEED = 42\n\ndef 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\nseed_everything(SEED)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# GroupKFold splitting\n\nI think group splitting by image_name is really important for correct validation in this competition ;) ","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\ndataset = []\n\nfor label, kind in enumerate(['Cover', 'JMiPOD', 'JUNIWARD', 'UERD']):\n    for path in glob('../input/alaska2-image-steganalysis/Cover/*.jpg'):\n        dataset.append({\n            'kind': kind,\n            'image_name': path.split('/')[-1],\n            'label': label\n        })\n\nrandom.shuffle(dataset)\ndataset = pd.DataFrame(dataset)\n\ngkf = GroupKFold(n_splits=5)\n\ndataset.loc[:, 'fold'] = 0\nfor fold_number, (train_index, val_index) in enumerate(gkf.split(X=dataset.index, y=dataset['label'], groups=dataset['image_name'])):\n    dataset.loc[dataset.iloc[val_index].index, 'fold'] = fold_number","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Simple Augs: Flips","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_train_transforms():\n    return A.Compose([\n            A.HorizontalFlip(p=0.5),\n            A.VerticalFlip(p=0.5),\n            A.Resize(height=512, width=512, p=1.0),\n            ToTensorV2(p=1.0),\n        ], p=1.0)\n\ndef get_valid_transforms():\n    return A.Compose([\n            A.Resize(height=512, width=512, p=1.0),\n            ToTensorV2(p=1.0),\n        ], p=1.0)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Dataset","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"DATA_ROOT_PATH = '../input/alaska2-image-steganalysis'\n\ndef onehot(size, target):\n    vec = torch.zeros(size, dtype=torch.float32)\n    vec[target] = 1.\n    return vec\n\nclass DatasetRetriever(Dataset):\n\n    def __init__(self, kinds, image_names, labels, transforms=None):\n        super().__init__()\n        self.kinds = kinds\n        self.image_names = image_names\n        self.labels = labels\n        self.transforms = transforms\n\n    def __getitem__(self, index: int):\n        kind, image_name, label = self.kinds[index], self.image_names[index], self.labels[index]\n        image = cv2.imread(f'{DATA_ROOT_PATH}/{kind}/{image_name}', cv2.IMREAD_COLOR)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB).astype(np.float32)\n        image /= 255.0\n        if self.transforms:\n            sample = {'image': image}\n            sample = self.transforms(**sample)\n            image = sample['image']\n            \n        target = onehot(4, label)\n        return image, target\n\n    def __len__(self) -> int:\n        return self.image_names.shape[0]\n\n    def get_labels(self):\n        return list(self.labels)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fold_number = 0\n\ntrain_dataset = DatasetRetriever(\n    kinds=dataset[dataset['fold'] != fold_number].kind.values,\n    image_names=dataset[dataset['fold'] != fold_number].image_name.values,\n    labels=dataset[dataset['fold'] != fold_number].label.values,\n    transforms=get_train_transforms(),\n)\n\nvalidation_dataset = DatasetRetriever(\n    kinds=dataset[dataset['fold'] == fold_number].kind.values,\n    image_names=dataset[dataset['fold'] == fold_number].image_name.values,\n    labels=dataset[dataset['fold'] == fold_number].label.values,\n    transforms=get_valid_transforms(),\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"image, target = train_dataset[0]\nnumpy_image = image.permute(1,2,0).cpu().numpy()\n\nfig, ax = plt.subplots(1, 1, figsize=(16, 8))\n    \nax.set_axis_off()\nax.imshow(numpy_image);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Metrics","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn import metrics\n\nclass AverageMeter(object):\n    \"\"\"Computes and stores the average and current value\"\"\"\n    def __init__(self):\n        self.reset()\n\n    def reset(self):\n        self.val = 0\n        self.avg = 0\n        self.sum = 0\n        self.count = 0\n\n    def update(self, val, n=1):\n        self.val = val\n        self.sum += val * n\n        self.count += n\n        self.avg = self.sum / self.count\n        \n        \ndef alaska_weighted_auc(y_true, y_valid):\n    \"\"\"\n    https://www.kaggle.com/anokas/weighted-auc-metric-updated\n    \"\"\"\n    tpr_thresholds = [0.0, 0.4, 1.0]\n    weights = [2, 1]\n\n    fpr, tpr, thresholds = metrics.roc_curve(y_true, y_valid, pos_label=1)\n\n    # size of subsets\n    areas = np.array(tpr_thresholds[1:]) - np.array(tpr_thresholds[:-1])\n\n    # The total area is normalized by the sum of weights such that the final weighted AUC is between 0 and 1.\n    normalization = np.dot(areas, weights)\n\n    competition_metric = 0\n    for idx, weight in enumerate(weights):\n        y_min = tpr_thresholds[idx]\n        y_max = tpr_thresholds[idx + 1]\n        mask = (y_min < tpr) & (tpr < y_max)\n        # pdb.set_trace()\n\n        x_padding = np.linspace(fpr[mask][-1], 1, 100)\n\n        x = np.concatenate([fpr[mask], x_padding])\n        y = np.concatenate([tpr[mask], [y_max] * len(x_padding)])\n        y = y - y_min  # normalize such that curve starts at y=0\n        score = metrics.auc(x, y)\n        submetric = score * weight\n        best_subscore = (y_max - y_min) * weight\n        competition_metric += submetric\n\n    return competition_metric / normalization\n        \nclass RocAucMeter(object):\n    def __init__(self):\n        self.reset()\n\n    def reset(self):\n        self.y_true = np.array([0,1])\n        self.y_pred = np.array([0.5,0.5])\n        self.score = 0\n\n    def update(self, y_true, y_pred):\n        y_true = y_true.cpu().numpy().argmax(axis=1).clip(min=0, max=1).astype(int)\n        y_pred = 1 - nn.functional.softmax(y_pred, dim=1).data.cpu().numpy()[:,0]\n        self.y_true = np.hstack((self.y_true, y_true))\n        self.y_pred = np.hstack((self.y_pred, y_pred))\n        self.score = alaska_weighted_auc(self.y_true, self.y_pred)\n    \n    @property\n    def avg(self):\n        return self.score","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Label Smoothing","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"class LabelSmoothing(nn.Module):\n    def __init__(self, smoothing = 0.05):\n        super(LabelSmoothing, self).__init__()\n        self.confidence = 1.0 - smoothing\n        self.smoothing = smoothing\n\n    def forward(self, x, target):\n        if self.training:\n            x = x.float()\n            target = target.float()\n            logprobs = torch.nn.functional.log_softmax(x, dim = -1)\n\n            nll_loss = -logprobs * target\n            nll_loss = nll_loss.sum(-1)\n    \n            smooth_loss = -logprobs.mean(dim=-1)\n\n            loss = self.confidence * nll_loss + self.smoothing * smooth_loss\n\n            return loss.mean()\n        else:\n            return torch.nn.functional.cross_entropy(x, target)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Fitter","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"import warnings\n\nwarnings.filterwarnings(\"ignore\")\n\nclass Fitter:\n    \n    def __init__(self, model, device, config):\n        self.config = config\n        self.epoch = 0\n        \n        self.base_dir = './'\n        self.log_path = f'{self.base_dir}/log.txt'\n        self.best_summary_loss = 10**5\n\n        self.model = model\n        self.device = device\n\n        param_optimizer = list(self.model.named_parameters())\n        no_decay = ['bias', 'LayerNorm.bias', 'LayerNorm.weight']\n        optimizer_grouped_parameters = [\n            {'params': [p for n, p in param_optimizer if not any(nd in n for nd in no_decay)], 'weight_decay': 0.001},\n            {'params': [p for n, p in param_optimizer if any(nd in n for nd in no_decay)], 'weight_decay': 0.0}\n        ] \n\n        self.optimizer = torch.optim.AdamW(self.model.parameters(), lr=config.lr)\n        self.scheduler = config.SchedulerClass(self.optimizer, **config.scheduler_params)\n        self.criterion = LabelSmoothing().to(self.device)\n        self.log(f'Fitter prepared. Device is {self.device}')\n\n    def fit(self, train_loader, validation_loader):\n        for e in range(self.config.n_epochs):\n            if self.config.verbose:\n                lr = self.optimizer.param_groups[0]['lr']\n                timestamp = datetime.utcnow().isoformat()\n                self.log(f'\\n{timestamp}\\nLR: {lr}')\n\n            t = time.time()\n            summary_loss, final_scores = self.train_one_epoch(train_loader)\n\n            self.log(f'[RESULT]: Train. Epoch: {self.epoch}, summary_loss: {summary_loss.avg:.5f}, final_score: {final_scores.avg:.5f}, time: {(time.time() - t):.5f}')\n            self.save(f'{self.base_dir}/last-checkpoint.bin')\n\n            t = time.time()\n            summary_loss, final_scores = self.validation(validation_loader)\n\n            self.log(f'[RESULT]: Val. Epoch: {self.epoch}, summary_loss: {summary_loss.avg:.5f}, final_score: {final_scores.avg:.5f}, time: {(time.time() - t):.5f}')\n            if summary_loss.avg < self.best_summary_loss:\n                self.best_summary_loss = summary_loss.avg\n                self.model.eval()\n                self.save(f'{self.base_dir}/best-checkpoint-{str(self.epoch).zfill(3)}epoch.bin')\n                for path in sorted(glob(f'{self.base_dir}/best-checkpoint-*epoch.bin'))[:-3]:\n                    os.remove(path)\n\n            if self.config.validation_scheduler:\n                self.scheduler.step(metrics=summary_loss.avg)\n\n            self.epoch += 1\n\n    def validation(self, val_loader):\n        self.model.eval()\n        summary_loss = AverageMeter()\n        final_scores = RocAucMeter()\n        t = time.time()\n        for step, (images, targets) in enumerate(val_loader):\n            if self.config.verbose:\n                if step % self.config.verbose_step == 0:\n                    print(\n                        f'Val Step {step}/{len(val_loader)}, ' + \\\n                        f'summary_loss: {summary_loss.avg:.5f}, final_score: {final_scores.avg:.5f}, ' + \\\n                        f'time: {(time.time() - t):.5f}', end='\\r'\n                    )\n            with torch.no_grad():\n                targets = targets.to(self.device).float()\n                batch_size = images.shape[0]\n                images = images.to(self.device).float()\n                outputs = self.model(images)\n                loss = self.criterion(outputs, targets)\n                final_scores.update(targets, outputs)\n                summary_loss.update(loss.detach().item(), batch_size)\n\n        return summary_loss, final_scores\n\n    def train_one_epoch(self, train_loader):\n        self.model.train()\n        summary_loss = AverageMeter()\n        final_scores = RocAucMeter()\n        t = time.time()\n        for step, (images, targets) in enumerate(train_loader):\n            if self.config.verbose:\n                if step % self.config.verbose_step == 0:\n                    print(\n                        f'Train Step {step}/{len(train_loader)}, ' + \\\n                        f'summary_loss: {summary_loss.avg:.5f}, final_score: {final_scores.avg:.5f}, ' + \\\n                        f'time: {(time.time() - t):.5f}', end='\\r'\n                    )\n            \n            targets = targets.to(self.device).float()\n            images = images.to(self.device).float()\n            batch_size = images.shape[0]\n\n            self.optimizer.zero_grad()\n            outputs = self.model(images)\n            loss = self.criterion(outputs, targets)\n            loss.backward()\n            \n            final_scores.update(targets, outputs)\n            summary_loss.update(loss.detach().item(), batch_size)\n\n            self.optimizer.step()\n\n            if self.config.step_scheduler:\n                self.scheduler.step()\n\n        return summary_loss, final_scores\n    \n    def save(self, path):\n        self.model.eval()\n        torch.save({\n            'model_state_dict': self.model.state_dict(),\n            'optimizer_state_dict': self.optimizer.state_dict(),\n            'scheduler_state_dict': self.scheduler.state_dict(),\n            'best_summary_loss': self.best_summary_loss,\n            'epoch': self.epoch,\n        }, path)\n\n    def load(self, path):\n        checkpoint = torch.load(path)\n        self.model.load_state_dict(checkpoint['model_state_dict'])\n        self.optimizer.load_state_dict(checkpoint['optimizer_state_dict'])\n        self.scheduler.load_state_dict(checkpoint['scheduler_state_dict'])\n        self.best_summary_loss = checkpoint['best_summary_loss']\n        self.epoch = checkpoint['epoch'] + 1\n        \n    def log(self, message):\n        if self.config.verbose:\n            print(message)\n        with open(self.log_path, 'a+') as logger:\n            logger.write(f'{message}\\n')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# EfficientNet","execution_count":null},{"metadata":{"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"from efficientnet_pytorch import EfficientNet\n\ndef get_net():\n    net = EfficientNet.from_pretrained('efficientnet-b2')\n    net._fc = nn.Linear(in_features=1408, out_features=4, bias=True)\n    return net\n\nnet = get_net().cuda()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Config","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"class TrainGlobalConfig:\n    num_workers = 4\n    batch_size = 16 \n    n_epochs = 25\n    lr = 0.001\n\n    # -------------------\n    verbose = True\n    verbose_step = 1\n    # -------------------\n\n    # --------------------\n    step_scheduler = False  # do scheduler.step after optimizer.step\n    validation_scheduler = True  # do scheduler.step after validation stage loss\n\n#     SchedulerClass = torch.optim.lr_scheduler.OneCycleLR\n#     scheduler_params = dict(\n#         max_lr=0.001,\n#         epochs=n_epochs,\n#         steps_per_epoch=int(len(train_dataset) / batch_size),\n#         pct_start=0.1,\n#         anneal_strategy='cos', \n#         final_div_factor=10**5\n#     )\n    \n    SchedulerClass = torch.optim.lr_scheduler.ReduceLROnPlateau\n    scheduler_params = dict(\n        mode='min',\n        factor=0.5,\n        patience=1,\n        verbose=False, \n        threshold=0.0001,\n        threshold_mode='abs',\n        cooldown=0, \n        min_lr=1e-8,\n        eps=1e-08\n    )\n    # --------------------","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Class Balance \"on fly\" from [@CatalystTeam](https://github.com/catalyst-team/catalyst)","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"from catalyst.data.sampler import BalanceClassSampler\n\ndef run_training():\n    device = torch.device('cuda:0')\n\n    train_loader = torch.utils.data.DataLoader(\n        train_dataset,\n        sampler=BalanceClassSampler(labels=train_dataset.get_labels(), mode=\"downsampling\"),\n        batch_size=TrainGlobalConfig.batch_size,\n        pin_memory=False,\n        drop_last=True,\n        num_workers=TrainGlobalConfig.num_workers,\n    )\n    val_loader = torch.utils.data.DataLoader(\n        validation_dataset, \n        batch_size=TrainGlobalConfig.batch_size,\n        num_workers=TrainGlobalConfig.num_workers,\n        shuffle=False,\n        sampler=SequentialSampler(validation_dataset),\n        pin_memory=False,\n    )\n\n    fitter = Fitter(model=net, device=device, config=TrainGlobalConfig)\n#     fitter.load(f'{fitter.base_dir}/last-checkpoint.bin')\n    fitter.fit(train_loader, val_loader)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Training\n\nI have used 1xV100 for training model, in kaggle kernel it works also. You can make fork and check it, but I would like to share with you my logs","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"# run_training()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"trusted":true},"cell_type":"code","source":"# file = open('../input/alaska2-public-baseline/log.txt', 'r')\n# for line in file.readlines():\n#     print(line[:-1])\n# file.close()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Inference","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"checkpoint = torch.load('../input/alaska2-public-baseline/best-checkpoint-023epoch.bin')\nnet.load_state_dict(checkpoint['model_state_dict']);\nnet.eval();","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"In checkpoint you can find states for optimizer and scheduler if you need","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"checkpoint.keys()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class DatasetSubmissionRetriever(Dataset):\n\n    def __init__(self, image_names, transforms=None):\n        super().__init__()\n        self.image_names = image_names\n        self.transforms = transforms\n\n    def __getitem__(self, index: int):\n        image_name = self.image_names[index]\n        image = cv2.imread(f'{DATA_ROOT_PATH}/Test/{image_name}', cv2.IMREAD_COLOR)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB).astype(np.float32)\n        image /= 255.0\n        if self.transforms:\n            sample = {'image': image}\n            sample = self.transforms(**sample)\n            image = sample['image']\n\n        return image_name, image\n\n    def __len__(self) -> int:\n        return self.image_names.shape[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dataset = DatasetSubmissionRetriever(\n    image_names=np.array([path.split('/')[-1] for path in glob('../input/alaska2-image-steganalysis/Test/*.jpg')]),\n    transforms=get_valid_transforms(),\n)\n\n\ndata_loader = DataLoader(\n    dataset,\n    batch_size=8,\n    shuffle=False,\n    num_workers=2,\n    drop_last=False,\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\nresult = {'Id': [], 'Label': []}\nfor step, (image_names, images) in enumerate(data_loader):\n    print(step, end='\\r')\n    \n    y_pred = net(images.cuda())\n    y_pred = 1 - nn.functional.softmax(y_pred, dim=1).data.cpu().numpy()[:,0]\n    \n    result['Id'].extend(image_names)\n    result['Label'].extend(y_pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.DataFrame(result)\nsubmission.sort_values(by='Id', inplace=True)\nsubmission.reset_index(drop=True, inplace=True)\nsubmission.to_csv('submission_b2.csv', index=False)\nsubmission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub_stack = pd.read_csv('/kaggle/input/alaska-stacking-files/stack_minmax_mean.csv')\nsub_stack.sort_values(by='Id', inplace=True)\nsub_stack.reset_index(drop=True, inplace=True)\nsub_stack.to_csv('submission_stack.csv', index=False)\nsub_stack.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = sub_stack.copy()\nsub['Label'] = sub['Label']*0.5+submission['Label']*0.5\nsub.to_csv('submission_ensemble.csv', index=False)\nsub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission['Label'].hist(bins=100);","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Thank you for reading my kernel!","execution_count":null}],"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}