add imbalanced classes video code and kaggle cat vs dog

.github/FUNDING.yml

@@ -1,12 +0,0 @@
-# These are supported funding model platforms
-
-github: aladdinpersson # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
-patreon: #aladdinpersson # Replace with a single Patreon username
-open_collective: # Replace with a single Open Collective username
-ko_fi: # Replace with a single Ko-fi username
-tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
-community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
-liberapay: # Replace with a single Liberapay username
-issuehunt: # Replace with a single IssueHunt username
-otechie: # Replace with a single Otechie username
-custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2']

ML/Kaggles/Dog vs Cat Competition/Logistic Regression on EfficientNet Features.ipynb

@@ -0,0 +1,119 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "51c78b68",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sklearn\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.metrics import log_loss"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "4421a043",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Training data shape: (25000, 2560), labels shape: (25000,)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "LogisticRegression(max_iter=2000)"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X = np.load(f'data_features/X_train_b7.npy')\n",
+    "y = np.load(f'data_features/y_train_b7.npy')\n",
+    "\n",
+    "# Split data and train classifier\n",
+    "print(f\"Training data shape: {X.shape}, labels shape: {y.shape}\")\n",
+    "X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.001, random_state=1337)\n",
+    "clf = LogisticRegression(max_iter=2000)\n",
+    "clf.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "d5cfc5b0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "On validation set:\n",
+      "Accuracy: 1.0\n",
+      "LOG LOSS: 7.980845755748817e-05 \n",
+      "%--------------------------------------------------%\n",
+      "Getting predictions for test set\n",
+      "Done getting predictions!\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Check on validation\n",
+    "val_preds= clf.predict_proba(X_val)[:,1]\n",
+    "print(f\"On validation set:\")\n",
+    "print(f\"Accuracy: {clf.score(X_val, y_val)}\")\n",
+    "print(f\"LOG LOSS: {log_loss(y_val, val_preds)} \")\n",
+    "print(\"%--------------------------------------------------%\")\n",
+    "\n",
+    "# Get predictions on test set\n",
+    "print(\"Getting predictions for test set\")\n",
+    "X_test = np.load(f'data_features/X_test_b7.npy')\n",
+    "X_test_preds = clf.predict_proba(X_test)[:,1]\n",
+    "df = pd.DataFrame({'id': np.arange(1, 12501), 'label': np.clip(X_test_preds, 0.005, 0.995)})\n",
+    "df.to_csv(f\"submissions/mysubmission.csv\", index=False)\n",
+    "print(\"Done getting predictions!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a9cce7af",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

ML/Kaggles/Dog vs Cat Competition/competition.txt

@@ -0,0 +1 @@
+https://www.kaggle.com/c/dogs-vs-cats-redux-kernels-edition

ML/Kaggles/Dog vs Cat Competition/config.py

@@ -0,0 +1,26 @@
+import torch
+import albumentations as A
+from albumentations.pytorch import ToTensorV2
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+NUM_WORKERS = 4
+BATCH_SIZE = 20
+PIN_MEMORY = True
+LOAD_MODEL = True
+SAVE_MODEL = True
+CHECKPOINT_FILE = "b7.pth.tar"
+WEIGHT_DECAY = 1e-4
+LEARNING_RATE = 1e-4
+NUM_EPOCHS = 1
+
+basic_transform = A.Compose(
+    [
+        A.Resize(height=448, width=448),
+        A.Normalize(
+            mean=[0.485, 0.456, 0.406],
+            std=[0.229, 0.224, 0.225],
+            max_pixel_value=255.0,
+        ),
+        ToTensorV2(),
+    ]
+)

ML/Kaggles/Dog vs Cat Competition/dataset.py

@@ -0,0 +1,32 @@
+import os
+import re
+import numpy as np
+from torch.utils.data import Dataset
+from PIL import Image
+
+
+class CatDog(Dataset):
+    def __init__(self, root, transform=None):
+        self.images = os.listdir(root)
+        self.images.sort(key=lambda x: int(re.findall(r"\d+", x)[0]))
+        self.root = root
+        self.transform = transform
+
+    def __len__(self):
+        return len(self.images)
+
+    def __getitem__(self, index):
+        file = self.images[index]
+        img = np.array(Image.open(os.path.join(self.root, file)))
+
+        if self.transform is not None:
+            img = self.transform(image=img)["image"]
+
+        if "dog" in file:
+            label = 1
+        elif "cat" in file:
+            label = 0
+        else:
+            label = -1
+
+        return img, label

ML/Kaggles/Dog vs Cat Competition/train.py

@@ -0,0 +1,93 @@
+# Imports
+import os
+import torch
+import torch.nn.functional as F
+import numpy as np
+import config
+from torch import nn, optim
+from torch.utils.data import DataLoader
+from tqdm import tqdm
+from dataset import CatDog
+from efficientnet_pytorch import EfficientNet
+from utils import check_accuracy, load_checkpoint, save_checkpoint
+
+
+def save_feature_vectors(model, loader, output_size=(1, 1), file="trainb7"):
+    model.eval()
+    images, labels = [], []
+
+    for idx, (x, y) in enumerate(tqdm(loader)):
+        x = x.to(config.DEVICE)
+
+        with torch.no_grad():
+            features = model.extract_features(x)
+            features = F.adaptive_avg_pool2d(features, output_size=output_size)
+        images.append(features.reshape(x.shape[0], -1).detach().cpu().numpy())
+        labels.append(y.numpy())
+
+    np.save(f"data_features/X_{file}.npy", np.concatenate(images, axis=0))
+    np.save(f"data_features/y_{file}.npy", np.concatenate(labels, axis=0))
+    model.train()
+
+
+def train_one_epoch(loader, model, loss_fn, optimizer, scaler):
+    loop = tqdm(loader)
+
+    for batch_idx, (data, targets) in enumerate(loop):
+        data = data.to(config.DEVICE)
+        targets = targets.to(config.DEVICE).unsqueeze(1).float()
+
+        with torch.cuda.amp.autocast():
+            scores = model(data)
+            loss = loss_fn(scores, targets)
+
+        optimizer.zero_grad()
+        scaler.scale(loss).backward()
+        scaler.step(optimizer)
+        scaler.update()
+        loop.set_postfix(loss=loss.item())
+
+
+def main():
+    model = EfficientNet.from_pretrained("efficientnet-b7")
+    model._fc = nn.Linear(2560, 1)
+    train_dataset = CatDog(root="data/train/", transform=config.basic_transform)
+    test_dataset = CatDog(root="data/test/", transform=config.basic_transform)
+    train_loader = DataLoader(
+        train_dataset,
+        shuffle=True,
+        batch_size=config.BATCH_SIZE,
+        num_workers=config.NUM_WORKERS,
+        pin_memory=True,
+    )
+    test_loader = DataLoader(
+        test_dataset,
+        shuffle=False,
+        batch_size=config.BATCH_SIZE,
+        num_workers=config.NUM_WORKERS,
+    )
+    model = model.to(config.DEVICE)
+
+    scaler = torch.cuda.amp.GradScaler()
+    loss_fn = nn.BCEWithLogitsLoss()
+    optimizer = optim.Adam(
+        model.parameters(), lr=config.LEARNING_RATE, weight_decay=config.WEIGHT_DECAY
+    )
+
+    if config.LOAD_MODEL and config.CHECKPOINT_FILE in os.listdir():
+        load_checkpoint(torch.load(config.CHECKPOINT_FILE), model)
+
+    for epoch in range(config.NUM_EPOCHS):
+        train_one_epoch(train_loader, model, loss_fn, optimizer, scaler)
+        check_accuracy(train_loader, model, loss_fn)
+
+    if config.SAVE_MODEL:
+        checkpoint = {"state_dict": model.state_dict(), "optimizer": optimizer.state_dict()}
+        save_checkpoint(checkpoint, filename=config.CHECKPOINT_FILE)
+
+    save_feature_vectors(model, train_loader, output_size=(1, 1), file="train_b7")
+    save_feature_vectors(model, test_loader, output_size=(1, 1), file="test_b7")
+
+
+if __name__ == "__main__":
+    main()

ML/Kaggles/Dog vs Cat Competition/utils.py

@@ -0,0 +1,192 @@
+import torch
+import os
+import pandas as pd
+import numpy as np
+import albumentations as A
+from albumentations.pytorch import ToTensorV2
+import config
+from tqdm import tqdm
+from dataset import CatDog
+from torch.utils.data import DataLoader
+from sklearn.metrics import log_loss
+
+
+def check_accuracy(
+    loader, model, loss_fn, input_shape=None, toggle_eval=True, print_accuracy=True
+):
+    """
+    Check accuracy of model on data from loader
+    """
+    if toggle_eval:
+        model.eval()
+    device = next(model.parameters()).device
+    num_correct = 0
+    num_samples = 0
+
+    y_preds = []
+    y_true = []
+
+    with torch.no_grad():
+        for x, y in loader:
+            x = x.to(device=device)
+            y = y.to(device=device)
+            if input_shape:
+                x = x.reshape(x.shape[0], *input_shape)
+            scores = model(x)
+            predictions = torch.sigmoid(scores) > 0.5
+            y_preds.append(torch.clip(torch.sigmoid(scores), 0.005, 0.995).cpu().numpy())
+            y_true.append(y.cpu().numpy())
+            num_correct += (predictions.squeeze(1) == y).sum()
+            num_samples += predictions.size(0)
+
+    accuracy = num_correct / num_samples
+
+    if toggle_eval:
+        model.train()
+
+    if print_accuracy:
+        print(f"Accuracy: {accuracy * 100:.2f}%")
+        print(log_loss(np.concatenate(y_true, axis=0), np.concatenate(y_preds, axis=0)))
+
+    return accuracy
+
+
+def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
+    print("=> Saving checkpoint")
+    torch.save(state, filename)
+
+
+def load_checkpoint(checkpoint, model):
+    print("=> Loading checkpoint")
+    model.load_state_dict(checkpoint["state_dict"])
+
+
+def create_submission(model, model_name, files_dir):
+    my_transforms = {
+        "base": A.Compose(
+            [
+                A.Resize(height=240, width=240),
+                A.Normalize(
+                    mean=[0.485, 0.456, 0.406],
+                    std=[0.229, 0.224, 0.225],
+                    max_pixel_value=255.0,
+                ),
+                ToTensorV2(),
+            ]
+        ),
+        "horizontal_flip": A.Compose(
+            [
+                A.Resize(height=240, width=240),
+                A.HorizontalFlip(p=1.0),
+                A.Normalize(
+                    mean=[0.485, 0.456, 0.406],
+                    std=[0.229, 0.224, 0.225],
+                    max_pixel_value=255.0,
+                ),
+                ToTensorV2(),
+            ]
+        ),
+        "vertical_flip": A.Compose(
+            [
+                A.Resize(height=240, width=240),
+                A.VerticalFlip(p=1.0),
+                A.Normalize(
+                    mean=[0.485, 0.456, 0.406],
+                    std=[0.229, 0.224, 0.225],
+                    max_pixel_value=255.0,
+                ),
+                ToTensorV2(),
+            ]
+        ),
+        "coloring": A.Compose(
+            [
+                A.Resize(height=240, width=240),
+                A.ColorJitter(p=1.0),
+                A.Normalize(
+                    mean=[0.485, 0.456, 0.406],
+                    std=[0.229, 0.224, 0.225],
+                    max_pixel_value=255.0,
+                ),
+                ToTensorV2(),
+            ]
+        ),
+        "rotate": A.Compose(
+            [
+                A.Resize(height=240, width=240),
+                A.Rotate(p=1.0, limit=45),
+                A.Normalize(
+                    mean=[0.485, 0.456, 0.406],
+                    std=[0.229, 0.224, 0.225],
+                    max_pixel_value=255.0,
+                ),
+                ToTensorV2(),
+            ]
+        ),
+        "shear": A.Compose(
+            [
+                A.Resize(height=240, width=240),
+                A.IAAAffine(p=1.0),
+                A.Normalize(
+                    mean=[0.485, 0.456, 0.406],
+                    std=[0.229, 0.224, 0.225],
+                    max_pixel_value=255.0,
+                ),
+                ToTensorV2(),
+            ]
+        ),
+    }
+
+    for t in ["base", "horizontal_flip", "vertical_flip", "coloring", "rotate", "shear"]:
+        predictions = []
+        labels = []
+        all_files = []
+        test_dataset = MyDataset(root=files_dir, transform=my_transforms[t])
+        test_loader = DataLoader(
+            test_dataset, batch_size=32, num_workers=4, shuffle=False, pin_memory=True
+        )
+        model.eval()
+
+        for idx, (x, y, filenames) in enumerate(tqdm(test_loader)):
+            x = x.to(config.DEVICE)
+            with torch.no_grad():
+                outputs = (
+                    torch.clip(torch.sigmoid(model(x)), 0.005, 0.995).squeeze(1).cpu().numpy()
+                )
+                predictions.append(outputs)
+                labels += y.numpy().tolist()
+                all_files += filenames
+
+        df = pd.DataFrame(
+            {
+                "id": np.arange(
+                    1,
+                    (len(predictions) - 1) * predictions[0].shape[0]
+                    + predictions[-1].shape[0]
+                    + 1,
+                ),
+                "label": np.concatenate(predictions, axis=0),
+            }
+        )
+        df.to_csv(f"predictions_test/submission_{model_name}_{t}.csv", index=False)
+
+        model.train()
+        print(f"Created submission file for model {model_name} and transform {t}")
+
+
+def blending_ensemble_data():
+    pred_csvs = []
+    root_dir = "predictions_validation/"
+
+    for file in os.listdir(root_dir):
+        if "label" not in file:
+            df = pd.read_csv(root_dir + "/" + file)
+            pred_csvs.append(df)
+        else:
+            label_csv = pd.read_csv(root_dir + "/" + file)
+
+    all_preds = pd.concat(pred_csvs, axis=1)
+    print(all_preds)
+
+
+if __name__ == "__main__":
+    blending_ensemble_data()

ML/Pytorch/Basics/Imbalanced_classes/main.py

@@ -0,0 +1,54 @@
+import torch
+import torchvision.datasets as datasets
+import os
+from torch.utils.data import WeightedRandomSampler, DataLoader
+import torchvision.transforms as transforms
+import torch.nn as nn
+
+# Methods for dealing with imbalanced datasets:
+# 1. Oversampling
+# 2. Class weighting
+
+def get_loader(root_dir, batch_size):
+    my_transforms = transforms.Compose(
+        [
+            transforms.Resize((224, 224)),
+            transforms.ToTensor(),
+        ]
+    )
+
+    dataset = datasets.ImageFolder(root=root_dir, transform=my_transforms)
+    class_weights = []
+    for root, subdir, files in os.walk(root_dir):
+        if len(files) > 0:
+            class_weights.append(1/len(files))
+
+    sample_weights = [0] * len(dataset)
+
+    for idx, (data, label) in enumerate(dataset):
+        class_weight = class_weights[label]
+        sample_weights[idx] = class_weight
+
+    sampler = WeightedRandomSampler(sample_weights, num_samples=
+                                    len(sample_weights), replacement=True)
+
+    loader = DataLoader(dataset, batch_size=batch_size, sampler=sampler)
+    return loader
+
+
+def main():
+    loader = get_loader(root_dir="dataset", batch_size=8)
+
+    num_retrievers = 0
+    num_elkhounds = 0
+    for epoch in range(10):
+        for data, labels in loader:
+            num_retrievers += torch.sum(labels==0)
+            num_elkhounds += torch.sum(labels==1)
+
+    print(num_retrievers)
+    print(num_elkhounds)
+
+if __name__ == "__main__":
+    main()
+