added requirements and new for linkeidn posts

Update pytorch_inceptionet.py

.dockerignore

@@ -0,0 +1,9 @@
+__pycache__
+.git
+.gitignore
+.vscode
+.idea
+*.pyc
+*~
+data/
+secrets.env

.github/FUNDING.yml

@@ -1,12 +0,0 @@
-# These are supported funding model platforms
-
-github: # 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']

.gitignore

@@ -1,3 +1,12 @@
 .idea/
 ML/Pytorch/more_advanced/image_captioning/flickr8k/
 ML/algorithms/svm/__pycache__/utils.cpython-38.pyc
+__pycache__/
+*.pth.tar
+*.DS_STORE
+ML/Pytorch/huggingface/train.csv
+ML/Pytorch/huggingface/validation.csv
+ML/Pytorch/huggingface/test.csv
+ML/Pytorch/huggingface/tb_logs/
+ML/Pytorch/huggingface/checkpoints/
+ML/Pytorch/huggingface/notebooks/

Dockerfile

@@ -0,0 +1,5 @@
+FROM pytorch/pytorch:2.1.1-cuda12.1-cudnn8-runtime
+RUN pip install --upgrade pip
+WORKDIR /code
+COPY requirements.txt /code/
+RUN pip install --no-cache-dir -r requirements.txt

ML/Kaggles/DiabeticRetinopathy/config.py

@@ -0,0 +1,48 @@
+import torch
+import albumentations as A
+from albumentations.pytorch import ToTensorV2
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+LEARNING_RATE = 3e-5
+WEIGHT_DECAY = 5e-4
+BATCH_SIZE = 20
+NUM_EPOCHS = 100
+NUM_WORKERS = 6
+CHECKPOINT_FILE = "b3.pth.tar"
+PIN_MEMORY = True
+SAVE_MODEL = True
+LOAD_MODEL = True
+
+# Data augmentation for images
+train_transforms = A.Compose(
+    [
+        A.Resize(width=760, height=760),
+        A.RandomCrop(height=728, width=728),
+        A.HorizontalFlip(p=0.5),
+        A.VerticalFlip(p=0.5),
+        A.RandomRotate90(p=0.5),
+        A.Blur(p=0.3),
+        A.CLAHE(p=0.3),
+        A.ColorJitter(p=0.3),
+        A.CoarseDropout(max_holes=12, max_height=20, max_width=20, p=0.3),
+        A.IAAAffine(shear=30, rotate=0, p=0.2, mode="constant"),
+        A.Normalize(
+            mean=[0.3199, 0.2240, 0.1609],
+            std=[0.3020, 0.2183, 0.1741],
+            max_pixel_value=255.0,
+        ),
+        ToTensorV2(),
+    ]
+)
+
+val_transforms = A.Compose(
+    [
+        A.Resize(height=728, width=728),
+        A.Normalize(
+            mean=[0.3199, 0.2240, 0.1609],
+            std=[0.3020, 0.2183, 0.1741],
+            max_pixel_value=255.0,
+        ),
+        ToTensorV2(),
+    ]
+)

ML/Kaggles/DiabeticRetinopathy/dataset.py

@@ -0,0 +1,56 @@
+import config
+import os
+import pandas as pd
+import numpy as np
+from torch.utils.data import Dataset, DataLoader
+from PIL import Image
+from tqdm import tqdm
+
+
+class DRDataset(Dataset):
+    def __init__(self, images_folder, path_to_csv, train=True, transform=None):
+        super().__init__()
+        self.data = pd.read_csv(path_to_csv)
+        self.images_folder = images_folder
+        self.image_files = os.listdir(images_folder)
+        self.transform = transform
+        self.train = train
+
+    def __len__(self):
+        return self.data.shape[0] if self.train else len(self.image_files)
+
+    def __getitem__(self, index):
+        if self.train:
+            image_file, label = self.data.iloc[index]
+        else:
+            # if test simply return -1 for label, I do this in order to
+            # re-use same dataset class for test set submission later on
+            image_file, label = self.image_files[index], -1
+            image_file = image_file.replace(".jpeg", "")
+
+        image = np.array(Image.open(os.path.join(self.images_folder, image_file+".jpeg")))
+
+        if self.transform:
+            image = self.transform(image=image)["image"]
+
+        return image, label, image_file
+
+
+if __name__ == "__main__":
+    """
+    Test if everything works ok
+    """
+    dataset = DRDataset(
+        images_folder="../train/images_resized_650/",
+        path_to_csv="../train/trainLabels.csv",
+        transform=config.val_transforms,
+    )
+    loader = DataLoader(
+        dataset=dataset, batch_size=32, num_workers=2, shuffle=True, pin_memory=True
+    )
+
+    for x, label, file in tqdm(loader):
+        print(x.shape)
+        print(label.shape)
+        import sys
+        sys.exit()

ML/Kaggles/DiabeticRetinopathy/preprocess_images.py

@@ -0,0 +1,82 @@
+"""
+Tries to remove unnecessary black borders around the images, and
+"trim" the images to they take up the entirety of the image.
+It's hacky & not very nice but it works :))
+"""
+
+import os
+import numpy as np
+from PIL import Image
+import warnings
+from multiprocessing import Pool
+from tqdm import tqdm
+import cv2
+
+
+def trim(im):
+    """
+    Converts image to grayscale using cv2, then computes binary matrix
+    of the pixels that are above a certain threshold, then takes out
+    the first row where a certain percetage of the pixels are above the
+    threshold will be the first clip point. Same idea for col, max row, max col.
+    """
+    percentage = 0.02
+
+    img = np.array(im)
+    img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+    im = img_gray > 0.1 * np.mean(img_gray[img_gray != 0])
+    row_sums = np.sum(im, axis=1)
+    col_sums = np.sum(im, axis=0)
+    rows = np.where(row_sums > img.shape[1] * percentage)[0]
+    cols = np.where(col_sums > img.shape[0] * percentage)[0]
+    min_row, min_col = np.min(rows), np.min(cols)
+    max_row, max_col = np.max(rows), np.max(cols)
+    im_crop = img[min_row : max_row + 1, min_col : max_col + 1]
+    return Image.fromarray(im_crop)
+
+
+def resize_maintain_aspect(image, desired_size):
+    """
+    Stole this from some stackoverflow post but can't remember which,
+    this will add padding to maintain the aspect ratio.
+    """
+    old_size = image.size  # old_size[0] is in (width, height) format
+    ratio = float(desired_size) / max(old_size)
+    new_size = tuple([int(x * ratio) for x in old_size])
+    im = image.resize(new_size, Image.ANTIALIAS)
+    new_im = Image.new("RGB", (desired_size, desired_size))
+    new_im.paste(im, ((desired_size - new_size[0]) // 2, (desired_size - new_size[1]) // 2))
+    return new_im
+
+
+def save_single(args):
+    img_file, input_path_folder, output_path_folder, output_size = args
+    image_original = Image.open(os.path.join(input_path_folder, img_file))
+    image = trim(image_original)
+    image = resize_maintain_aspect(image, desired_size=output_size[0])
+    image.save(os.path.join(output_path_folder + img_file))
+
+
+def fast_image_resize(input_path_folder, output_path_folder, output_size=None):
+    """
+    Uses multiprocessing to make it fast
+    """
+    if not output_size:
+        warnings.warn("Need to specify output_size! For example: output_size=100")
+        exit()
+
+    if not os.path.exists(output_path_folder):
+        os.makedirs(output_path_folder)
+
+    jobs = [
+        (file, input_path_folder, output_path_folder, output_size)
+        for file in os.listdir(input_path_folder)
+    ]
+
+    with Pool() as p:
+        list(tqdm(p.imap_unordered(save_single, jobs), total=len(jobs)))
+
+
+if __name__ == "__main__":
+    fast_image_resize("../train/images/", "../train/images_resized_150/", output_size=(150, 150))
+    fast_image_resize("../test/images/", "../test/images_resized_150/", output_size=(150, 150))

ML/Kaggles/DiabeticRetinopathy/train.py

@@ -0,0 +1,125 @@
+import torch
+from torch import nn, optim
+import os
+import config
+from torch.utils.data import DataLoader
+from tqdm import tqdm
+from sklearn.metrics import cohen_kappa_score
+from efficientnet_pytorch import EfficientNet
+from dataset import DRDataset
+from torchvision.utils import save_image
+from utils import (
+    load_checkpoint,
+    save_checkpoint,
+    check_accuracy,
+    make_prediction,
+    get_csv_for_blend,
+)
+
+
+def train_one_epoch(loader, model, optimizer, loss_fn, scaler, device):
+    losses = []
+    loop = tqdm(loader)
+    for batch_idx, (data, targets, _) in enumerate(loop):
+        # save examples and make sure they look ok with the data augmentation,
+        # tip is to first set mean=[0,0,0], std=[1,1,1] so they look "normal"
+        #save_image(data, f"hi_{batch_idx}.png")
+
+        data = data.to(device=device)
+        targets = targets.to(device=device)
+
+        # forward
+        with torch.cuda.amp.autocast():
+            scores = model(data)
+            loss = loss_fn(scores, targets.unsqueeze(1).float())
+
+        losses.append(loss.item())
+
+        # backward
+        optimizer.zero_grad()
+        scaler.scale(loss).backward()
+        scaler.step(optimizer)
+        scaler.update()
+        loop.set_postfix(loss=loss.item())
+
+    print(f"Loss average over epoch: {sum(losses)/len(losses)}")
+
+
+def main():
+    train_ds = DRDataset(
+        images_folder="train/images_preprocessed_1000/",
+        path_to_csv="train/trainLabels.csv",
+        transform=config.val_transforms,
+    )
+    val_ds = DRDataset(
+        images_folder="train/images_preprocessed_1000/",
+        path_to_csv="train/valLabels.csv",
+        transform=config.val_transforms,
+    )
+    test_ds = DRDataset(
+        images_folder="test/images_preprocessed_1000",
+        path_to_csv="train/trainLabels.csv",
+        transform=config.val_transforms,
+        train=False,
+    )
+    test_loader = DataLoader(
+        test_ds, batch_size=config.BATCH_SIZE, num_workers=6, shuffle=False
+    )
+    train_loader = DataLoader(
+        train_ds,
+        batch_size=config.BATCH_SIZE,
+        num_workers=config.NUM_WORKERS,
+        pin_memory=config.PIN_MEMORY,
+        shuffle=False,
+    )
+    val_loader = DataLoader(
+        val_ds,
+        batch_size=config.BATCH_SIZE,
+        num_workers=2,
+        pin_memory=config.PIN_MEMORY,
+        shuffle=False,
+    )
+    loss_fn = nn.MSELoss()
+
+    model = EfficientNet.from_pretrained("efficientnet-b3")
+    model._fc = nn.Linear(1536, 1)
+    model = model.to(config.DEVICE)
+    optimizer = optim.Adam(model.parameters(), lr=config.LEARNING_RATE, weight_decay=config.WEIGHT_DECAY)
+    scaler = torch.cuda.amp.GradScaler()
+
+    if config.LOAD_MODEL and config.CHECKPOINT_FILE in os.listdir():
+        load_checkpoint(torch.load(config.CHECKPOINT_FILE), model, optimizer, config.LEARNING_RATE)
+
+    # Run after training is done and you've achieved good result
+    # on validation set, then run train_blend.py file to use information
+    # about both eyes concatenated
+    get_csv_for_blend(val_loader, model, "../train/val_blend.csv")
+    get_csv_for_blend(train_loader, model, "../train/train_blend.csv")
+    get_csv_for_blend(test_loader, model, "../train/test_blend.csv")
+    make_prediction(model, test_loader, "submission_.csv")
+    import sys
+    sys.exit()
+    #make_prediction(model, test_loader)
+
+    for epoch in range(config.NUM_EPOCHS):
+        train_one_epoch(train_loader, model, optimizer, loss_fn, scaler, config.DEVICE)
+
+        # get on validation
+        preds, labels = check_accuracy(val_loader, model, config.DEVICE)
+        print(f"QuadraticWeightedKappa (Validation): {cohen_kappa_score(labels, preds, weights='quadratic')}")
+
+        # get on train
+        #preds, labels = check_accuracy(train_loader, model, config.DEVICE)
+        #print(f"QuadraticWeightedKappa (Training): {cohen_kappa_score(labels, preds, weights='quadratic')}")
+
+        if config.SAVE_MODEL:
+            checkpoint = {
+                "state_dict": model.state_dict(),
+                "optimizer": optimizer.state_dict(),
+            }
+            save_checkpoint(checkpoint, filename=f"b3_{epoch}.pth.tar")
+
+
+
+if __name__ == "__main__":
+    main()

ML/Kaggles/DiabeticRetinopathy/train_blend.py

@@ -0,0 +1,126 @@
+import torch
+from tqdm import tqdm
+import numpy as np
+from torch import nn
+from torch import optim
+from torch.utils.data import DataLoader, Dataset
+from utils import save_checkpoint, load_checkpoint, check_accuracy
+from sklearn.metrics import cohen_kappa_score
+import config
+import os
+import pandas as pd
+
+
+def make_prediction(model, loader, file):
+    preds = []
+    filenames = []
+    model.eval()
+
+    for x, y, files in tqdm(loader):
+        x = x.to(config.DEVICE)
+        with torch.no_grad():
+            predictions = model(x)
+            # Convert MSE floats to integer predictions
+            predictions[predictions < 0.5] = 0
+            predictions[(predictions >= 0.5) & (predictions < 1.5)] = 1
+            predictions[(predictions >= 1.5) & (predictions < 2.5)] = 2
+            predictions[(predictions >= 2.5) & (predictions < 3.5)] = 3
+            predictions[(predictions >= 3.5) & (predictions < 1000000000000)] = 4
+            predictions = predictions.long().view(-1)
+            y = y.view(-1)
+
+            preds.append(predictions.cpu().numpy())
+            filenames += map(list, zip(files[0], files[1]))
+
+    filenames = [item for sublist in filenames for item in sublist]
+    df = pd.DataFrame({"image": filenames, "level": np.concatenate(preds, axis=0)})
+    df.to_csv(file, index=False)
+    model.train()
+    print("Done with predictions")
+
+
+class MyDataset(Dataset):
+    def __init__(self, csv_file):
+        self.csv = pd.read_csv(csv_file)
+
+    def __len__(self):
+        return self.csv.shape[0]
+
+    def __getitem__(self, index):
+        example = self.csv.iloc[index, :]
+        features = example.iloc[: example.shape[0] - 4].to_numpy().astype(np.float32)
+        labels = example.iloc[-4:-2].to_numpy().astype(np.int64)
+        filenames = example.iloc[-2:].values.tolist()
+        return features, labels, filenames
+
+
+class MyModel(nn.Module):
+    def __init__(self):
+        super().__init__()
+        self.model = nn.Sequential(
+            nn.BatchNorm1d((1536 + 1) * 2),
+            nn.Linear((1536+1) * 2, 500),
+            nn.BatchNorm1d(500),
+            nn.ReLU(),
+            nn.Dropout(0.2),
+            nn.Linear(500, 100),
+            nn.BatchNorm1d(100),
+            nn.ReLU(),
+            nn.Dropout(0.2),
+            nn.Linear(100, 2),
+        )
+
+    def forward(self, x):
+        return self.model(x)
+
+
+if __name__ == "__main__":
+    model = MyModel().to(config.DEVICE)
+    ds = MyDataset(csv_file="train/train_blend.csv")
+    loader = DataLoader(ds, batch_size=256, num_workers=3, pin_memory=True, shuffle=True)
+    ds_val = MyDataset(csv_file="train/val_blend.csv")
+    loader_val = DataLoader(
+        ds_val, batch_size=256, num_workers=3, pin_memory=True, shuffle=True
+    )
+    ds_test = MyDataset(csv_file="train/test_blend.csv")
+    loader_test = DataLoader(
+        ds_test, batch_size=256, num_workers=2, pin_memory=True, shuffle=False
+    )
+    optimizer = optim.Adam(model.parameters(), lr=1e-4, weight_decay=1e-5)
+    loss_fn = nn.MSELoss()
+
+    if config.LOAD_MODEL and "linear.pth.tar" in os.listdir():
+        load_checkpoint(torch.load("linear.pth.tar"), model, optimizer, lr=1e-4)
+        model.train()
+
+    for _ in range(5):
+        losses = []
+        for x, y, files in tqdm(loader_val):
+            x = x.to(config.DEVICE).float()
+            y = y.to(config.DEVICE).view(-1).float()
+
+            # forward
+            scores = model(x).view(-1)
+            loss = loss_fn(scores, y)
+            losses.append(loss.item())
+
+            # backward
+            optimizer.zero_grad()
+            loss.backward()
+
+            # gradient descent or adam step
+            optimizer.step()
+
+        print(f"Loss: {sum(losses)/len(losses)}")
+
+    if config.SAVE_MODEL:
+        checkpoint = {"state_dict": model.state_dict(), "optimizer": optimizer.state_dict()}
+        save_checkpoint(checkpoint, filename="linear.pth.tar")
+
+    preds, labels = check_accuracy(loader_val, model)
+    print(cohen_kappa_score(labels, preds, weights="quadratic"))
+
+    preds, labels = check_accuracy(loader, model)
+    print(cohen_kappa_score(labels, preds, weights="quadratic"))
+
+    make_prediction(model, loader_test, "test_preds.csv")

ML/Kaggles/DiabeticRetinopathy/utils.py

@@ -0,0 +1,128 @@
+import torch
+import pandas as pd
+import numpy as np
+import config
+from tqdm import tqdm
+import warnings
+import torch.nn.functional as F
+
+
+def make_prediction(model, loader, output_csv="submission.csv"):
+    preds = []
+    filenames = []
+    model.eval()
+
+    for x, y, files in tqdm(loader):
+        x = x.to(config.DEVICE)
+        with torch.no_grad():
+            predictions = model(x)
+            # Convert MSE floats to integer predictions
+            predictions[predictions < 0.5] = 0
+            predictions[(predictions >= 0.5) & (predictions < 1.5)] = 1
+            predictions[(predictions >= 1.5) & (predictions < 2.5)] = 2
+            predictions[(predictions >= 2.5) & (predictions < 3.5)] = 3
+            predictions[(predictions >= 3.5) & (predictions < 10000000)] = 4
+            predictions = predictions.long().squeeze(1)
+            preds.append(predictions.cpu().numpy())
+            filenames += files
+
+    df = pd.DataFrame({"image": filenames, "level": np.concatenate(preds, axis=0)})
+    df.to_csv(output_csv, index=False)
+    model.train()
+    print("Done with predictions")
+
+
+def check_accuracy(loader, model, device="cuda"):
+    model.eval()
+    all_preds, all_labels = [], []
+    num_correct = 0
+    num_samples = 0
+
+    for x, y, filename in tqdm(loader):
+        x = x.to(device=device)
+        y = y.to(device=device)
+
+        with torch.no_grad():
+            predictions = model(x)
+
+        # Convert MSE floats to integer predictions
+        predictions[predictions < 0.5] = 0
+        predictions[(predictions >= 0.5) & (predictions < 1.5)] = 1
+        predictions[(predictions >= 1.5) & (predictions < 2.5)] = 2
+        predictions[(predictions >= 2.5) & (predictions < 3.5)] = 3
+        predictions[(predictions >= 3.5) & (predictions < 100)] = 4
+        predictions = predictions.long().view(-1)
+        y = y.view(-1)
+
+        num_correct += (predictions == y).sum()
+        num_samples += predictions.shape[0]
+
+        # add to lists
+        all_preds.append(predictions.detach().cpu().numpy())
+        all_labels.append(y.detach().cpu().numpy())
+
+    print(
+        f"Got {num_correct} / {num_samples} with accuracy {float(num_correct) / float(num_samples) * 100:.2f}"
+    )
+    model.train()
+    return np.concatenate(all_preds, axis=0, dtype=np.int64), np.concatenate(
+        all_labels, axis=0, dtype=np.int64
+    )
+
+
+def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
+    print("=> Saving checkpoint")
+    torch.save(state, filename)
+
+
+def load_checkpoint(checkpoint, model, optimizer, lr):
+    print("=> Loading checkpoint")
+    model.load_state_dict(checkpoint["state_dict"])
+    #optimizer.load_state_dict(checkpoint["optimizer"])
+
+    # If we don't do this then it will just have learning rate of old checkpoint
+    # and it will lead to many hours of debugging \:
+    for param_group in optimizer.param_groups:
+        param_group["lr"] = lr
+
+
+def get_csv_for_blend(loader, model, output_csv_file):
+    warnings.warn("Important to have shuffle=False (and to ensure batch size is even size) when running get_csv_for_blend also set val_transforms to train_loader!")
+    model.eval()
+    filename_first = []
+    filename_second = []
+    labels_first = []
+    labels_second = []
+    all_features = []
+
+    for idx, (images, y, image_files) in enumerate(tqdm(loader)):
+        images = images.to(config.DEVICE)
+
+        with torch.no_grad():
+            features = F.adaptive_avg_pool2d(
+                model.extract_features(images), output_size=1
+            )
+            features_logits = features.reshape(features.shape[0] // 2, 2, features.shape[1])
+            preds = model(images).reshape(images.shape[0] // 2, 2, 1)
+            new_features = (
+                torch.cat([features_logits, preds], dim=2)
+                .view(preds.shape[0], -1)
+                .cpu()
+                .numpy()
+            )
+            all_features.append(new_features)
+            filename_first += image_files[::2]
+            filename_second += image_files[1::2]
+            labels_first.append(y[::2].cpu().numpy())
+            labels_second.append(y[1::2].cpu().numpy())
+
+    all_features = np.concatenate(all_features, axis=0)
+    df = pd.DataFrame(
+        data=all_features, columns=[f"f_{idx}" for idx in range(all_features.shape[1])]
+    )
+    df["label_first"] = np.concatenate(labels_first, axis=0)
+    df["label_second"] = np.concatenate(labels_second, axis=0)
+    df["file_first"] = filename_first
+    df["file_second"] = filename_second
+    df.to_csv(output_csv_file, index=False)
+    model.train()

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/Kaggles/Facial Keypoint Detection Competition/config.py

@@ -0,0 +1,61 @@
+import torch
+import albumentations as A
+from albumentations.pytorch import ToTensorV2
+import cv2
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+LEARNING_RATE = 1e-4
+WEIGHT_DECAY = 5e-4
+BATCH_SIZE = 64
+NUM_EPOCHS = 100
+NUM_WORKERS = 4
+CHECKPOINT_FILE = "b0_4.pth.tar"
+PIN_MEMORY = True
+SAVE_MODEL = True
+LOAD_MODEL = True
+
+# Data augmentation for images
+train_transforms = A.Compose(
+    [
+        A.Resize(width=96, height=96),
+        A.Rotate(limit=15, border_mode=cv2.BORDER_CONSTANT, p=0.8),
+        A.IAAAffine(shear=15, scale=1.0, mode="constant", p=0.2),
+        A.RandomBrightnessContrast(contrast_limit=0.5, brightness_limit=0.5, p=0.2),
+        A.OneOf([
+            A.GaussNoise(p=0.8),
+            A.CLAHE(p=0.8),
+            A.ImageCompression(p=0.8),
+            A.RandomGamma(p=0.8),
+            A.Posterize(p=0.8),
+            A.Blur(p=0.8),
+        ], p=1.0),
+        A.OneOf([
+            A.GaussNoise(p=0.8),
+            A.CLAHE(p=0.8),
+            A.ImageCompression(p=0.8),
+            A.RandomGamma(p=0.8),
+            A.Posterize(p=0.8),
+            A.Blur(p=0.8),
+        ], p=1.0),
+        A.ShiftScaleRotate(shift_limit=0.1, scale_limit=0.1, rotate_limit=0, p=0.2, border_mode=cv2.BORDER_CONSTANT),
+        A.Normalize(
+            mean=[0.4897, 0.4897, 0.4897],
+            std=[0.2330, 0.2330, 0.2330],
+            max_pixel_value=255.0,
+        ),
+        ToTensorV2(),
+    ], keypoint_params=A.KeypointParams(format="xy", remove_invisible=False),
+)
+
+
+val_transforms = A.Compose(
+    [
+        A.Resize(height=96, width=96),
+        A.Normalize(
+            mean=[0.4897, 0.4897, 0.4897],
+            std=[0.2330, 0.2330, 0.2330],
+            max_pixel_value=255.0,
+        ),
+        ToTensorV2(),
+    ], keypoint_params=A.KeypointParams(format="xy", remove_invisible=False),
+)

ML/Kaggles/Facial Keypoint Detection Competition/dataset.py

@@ -0,0 +1,50 @@
+import pandas as pd
+import numpy as np
+import config
+import matplotlib.pyplot as plt
+from torch.utils.data import DataLoader, Dataset
+
+
+class FacialKeypointDataset(Dataset):
+    def __init__(self, csv_file, train=True, transform=None):
+        super().__init__()
+        self.data = pd.read_csv(csv_file)
+        self.category_names = ['left_eye_center_x', 'left_eye_center_y', 'right_eye_center_x', 'right_eye_center_y', 'left_eye_inner_corner_x', 'left_eye_inner_corner_y', 'left_eye_outer_corner_x', 'left_eye_outer_corner_y', 'right_eye_inner_corner_x', 'right_eye_inner_corner_y', 'right_eye_outer_corner_x', 'right_eye_outer_corner_y', 'left_eyebrow_inner_end_x', 'left_eyebrow_inner_end_y', 'left_eyebrow_outer_end_x', 'left_eyebrow_outer_end_y', 'right_eyebrow_inner_end_x', 'right_eyebrow_inner_end_y', 'right_eyebrow_outer_end_x', 'right_eyebrow_outer_end_y', 'nose_tip_x', 'nose_tip_y', 'mouth_left_corner_x', 'mouth_left_corner_y', 'mouth_right_corner_x', 'mouth_right_corner_y', 'mouth_center_top_lip_x', 'mouth_center_top_lip_y', 'mouth_center_bottom_lip_x', 'mouth_center_bottom_lip_y']
+        self.transform = transform
+        self.train = train
+
+    def __len__(self):
+        return self.data.shape[0]
+
+    def __getitem__(self, index):
+        if self.train:
+            image = np.array(self.data.iloc[index, 30].split()).astype(np.float32)
+            labels = np.array(self.data.iloc[index, :30].tolist())
+            labels[np.isnan(labels)] = -1
+        else:
+            image = np.array(self.data.iloc[index, 1].split()).astype(np.float32)
+            labels = np.zeros(30)
+
+        ignore_indices = labels == -1
+        labels = labels.reshape(15, 2)
+
+        if self.transform:
+            image = np.repeat(image.reshape(96, 96, 1), 3, 2).astype(np.uint8)
+            augmentations = self.transform(image=image, keypoints=labels)
+            image = augmentations["image"]
+            labels = augmentations["keypoints"]
+
+        labels = np.array(labels).reshape(-1)
+        labels[ignore_indices] = -1
+
+        return image, labels.astype(np.float32)
+
+
+if __name__ == "__main__":
+    ds = FacialKeypointDataset(csv_file="data/train_4.csv", train=True, transform=config.train_transforms)
+    loader = DataLoader(ds, batch_size=1, shuffle=True, num_workers=0)
+
+    for idx, (x, y) in enumerate(loader):
+        plt.imshow(x[0][0].detach().cpu().numpy(), cmap='gray')
+        plt.plot(y[0][0::2].detach().cpu().numpy(), y[0][1::2].detach().cpu().numpy(), "go")
+        plt.show()

ML/Kaggles/Facial Keypoint Detection Competition/extract_images_from_csv.py

@@ -0,0 +1,19 @@
+import numpy as np
+import pandas as pd
+import os
+from PIL import Image
+
+
+def extract_images_from_csv(csv, column, save_folder, resize=(96, 96)):
+    if not os.path.exists(save_folder):
+        os.makedirs(save_folder)
+
+    for idx, image in enumerate(csv[column]):
+        image = np.array(image.split()).astype(np.uint8)
+        image = image.reshape(resize[0], resize[1])
+        img = Image.fromarray(image, 'L')
+        img.save(save_folder+f"img_{idx}.png")
+
+
+csv = pd.read_csv("test.csv")
+extract_images_from_csv(csv, "Image", "data/test/")

ML/Kaggles/Facial Keypoint Detection Competition/train.py

@@ -0,0 +1,111 @@
+import torch
+from dataset import FacialKeypointDataset
+from torch import nn, optim
+import os
+import config
+from torch.utils.data import DataLoader
+from tqdm import tqdm
+from efficientnet_pytorch import EfficientNet
+from utils import (
+    load_checkpoint,
+    save_checkpoint,
+    get_rmse,
+    get_submission
+)
+
+
+def train_one_epoch(loader, model, optimizer, loss_fn, scaler, device):
+    losses = []
+    loop = tqdm(loader)
+    num_examples = 0
+    for batch_idx, (data, targets) in enumerate(loop):
+        data = data.to(device=device)
+        targets = targets.to(device=device)
+
+        # forward
+        scores = model(data)
+        scores[targets == -1] = -1
+        loss = loss_fn(scores, targets)
+        num_examples += torch.numel(scores[targets != -1])
+        losses.append(loss.item())
+
+        # backward
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+    print(f"Loss average over epoch: {(sum(losses)/num_examples)**0.5}")
+
+
+def main():
+    train_ds = FacialKeypointDataset(
+        csv_file="data/train_4.csv",
+        transform=config.train_transforms,
+    )
+    train_loader = DataLoader(
+        train_ds,
+        batch_size=config.BATCH_SIZE,
+        num_workers=config.NUM_WORKERS,
+        pin_memory=config.PIN_MEMORY,
+        shuffle=True,
+    )
+    val_ds = FacialKeypointDataset(
+        transform=config.val_transforms,
+        csv_file="data/val_4.csv",
+    )
+    val_loader = DataLoader(
+        val_ds,
+        batch_size=config.BATCH_SIZE,
+        num_workers=config.NUM_WORKERS,
+        pin_memory=config.PIN_MEMORY,
+        shuffle=False,
+    )
+
+    test_ds = FacialKeypointDataset(
+        csv_file="data/test.csv",
+        transform=config.val_transforms,
+        train=False,
+    )
+
+    test_loader = DataLoader(
+        test_ds,
+        batch_size=1,
+        num_workers=config.NUM_WORKERS,
+        pin_memory=config.PIN_MEMORY,
+        shuffle=False,
+    )
+    loss_fn = nn.MSELoss(reduction="sum")
+    model = EfficientNet.from_pretrained("efficientnet-b0")
+    model._fc = nn.Linear(1280, 30)
+    model = model.to(config.DEVICE)
+    optimizer = optim.Adam(model.parameters(), lr=config.LEARNING_RATE, weight_decay=config.WEIGHT_DECAY)
+    scaler = torch.cuda.amp.GradScaler()
+
+    model_4 = EfficientNet.from_pretrained("efficientnet-b0")
+    model_4._fc = nn.Linear(1280, 30)
+    model_15 = EfficientNet.from_pretrained("efficientnet-b0")
+    model_15._fc = nn.Linear(1280, 30)
+    model_4 = model_4.to(config.DEVICE)
+    model_15 = model_15.to(config.DEVICE)
+
+    if config.LOAD_MODEL and config.CHECKPOINT_FILE in os.listdir():
+        load_checkpoint(torch.load(config.CHECKPOINT_FILE), model, optimizer, config.LEARNING_RATE)
+        load_checkpoint(torch.load("b0_4.pth.tar"), model_4, optimizer, config.LEARNING_RATE)
+        load_checkpoint(torch.load("b0_15.pth.tar"), model_15, optimizer, config.LEARNING_RATE)
+
+    get_submission(test_loader, test_ds, model_15, model_4)
+
+    for epoch in range(config.NUM_EPOCHS):
+        get_rmse(val_loader, model, loss_fn, config.DEVICE)
+        train_one_epoch(train_loader, model, optimizer, loss_fn, scaler, config.DEVICE)
+
+        # get on validation
+        if config.SAVE_MODEL:
+            checkpoint = {
+                "state_dict": model.state_dict(),
+                "optimizer": optimizer.state_dict(),
+            }
+            save_checkpoint(checkpoint, filename=config.CHECKPOINT_FILE)
+
+if __name__ == "__main__":
+    main()

ML/Kaggles/Facial Keypoint Detection Competition/utils.py

@@ -0,0 +1,71 @@
+import torch
+import numpy as np
+import config
+import pandas as pd
+from tqdm import tqdm
+
+
+def get_submission(loader, dataset, model_15, model_4):
+    """
+    This can be done a lot faster.. but it didn't take
+    too much time to do it in this inefficient way
+    """
+    model_15.eval()
+    model_4.eval()
+    id_lookup = pd.read_csv("data/IdLookupTable.csv")
+    predictions = []
+    image_id = 1
+
+    for image, label in tqdm(loader):
+        image = image.to(config.DEVICE)
+        preds_15 = torch.clip(model_15(image).squeeze(0), 0.0, 96.0)
+        preds_4 = torch.clip(model_4(image).squeeze(0), 0.0, 96.0)
+        feature_names = id_lookup.loc[id_lookup["ImageId"] == image_id]["FeatureName"]
+
+        for feature_name in feature_names:
+            feature_index = dataset.category_names.index(feature_name)
+            if feature_names.shape[0] < 10:
+                predictions.append(preds_4[feature_index].item())
+            else:
+                predictions.append(preds_15[feature_index].item())
+
+        image_id += 1
+
+    df = pd.DataFrame({"RowId": np.arange(1, len(predictions)+1), "Location": predictions})
+    df.to_csv("submission.csv", index=False)
+    model_15.train()
+    model_4.train()
+
+
+def get_rmse(loader, model, loss_fn, device):
+    model.eval()
+    num_examples = 0
+    losses = []
+    for batch_idx, (data, targets) in enumerate(loader):
+        data = data.to(device=device)
+        targets = targets.to(device=device)
+
+        # forward
+        scores = model(data)
+        loss = loss_fn(scores[targets != -1], targets[targets != -1])
+        num_examples += scores[targets != -1].shape[0]
+        losses.append(loss.item())
+
+    model.train()
+    print(f"Loss on val: {(sum(losses)/num_examples)**0.5}")
+
+
+def save_checkpoint(state, filename="my_checkpoint.pth.tar"):
+    print("=> Saving checkpoint")
+    torch.save(state, filename)
+
+
+def load_checkpoint(checkpoint, model, optimizer, lr):
+    print("=> Loading checkpoint")
+    model.load_state_dict(checkpoint["state_dict"])
+    optimizer.load_state_dict(checkpoint["optimizer"])
+
+    # If we don't do this then it will just have learning rate of old checkpoint
+    # and it will lead to many hours of debugging \:
+    for param_group in optimizer.param_groups:
+        param_group["lr"] = lr

ML/Pytorch/Basics/Imbalanced_classes/main.py

@@ -0,0 +1,93 @@
+"""
+This code is for dealing with imbalanced datasets in PyTorch. Imbalanced datasets 
+are those where the number of samples in one or more classes is significantly lower 
+than the number of samples in the other classes. This can be a problem because it 
+can lead to a model that is biased towards the more common classes, which can result 
+in poor performance on the less common classes.
+
+To deal with imbalanced datasets, this code implements two methods: oversampling and 
+class weighting.
+
+Oversampling involves generating additional samples for the underrepresented classes, 
+while class weighting involves assigning higher weights to the loss of samples in the 
+underrepresented classes, so that the model pays more attention to them.
+
+In this code, the get_loader function takes a root directory for a dataset and a batch 
+size, and returns a PyTorch data loader. The data loader is used to iterate over the 
+dataset in batches. The get_loader function first applies some transformations to the 
+images in the dataset using the transforms module from torchvision. Then it calculates 
+the class weights based on the number of samples in each class. It then creates a 
+WeightedRandomSampler object, which is used to randomly select a batch of samples with a 
+probability proportional to their weights. Finally, it creates the data loader using the 
+dataset and the weighted random sampler.
+
+The main function then uses the data loader to iterate over the dataset for 10 epochs, 
+and counts the number of samples in each class. Finally, it prints the counts for each class.
+
+Programmed by Aladdin Persson <aladdin.persson at hotmail dot com>
+* 2020-04-08: Initial coding
+* 2021-03-24: Added more detailed comments also removed part of
+              check_accuracy which would only work specifically on MNIST.
+* 2022-12-19: Updated detailed comments, small code revision, checked code still works with latest PyTorch. 
+"""
+
+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 (probably preferable)
+# 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)
+    subdirectories = dataset.classes
+    class_weights = []
+
+    # loop through each subdirectory and calculate the class weight
+    # that is 1 / len(files) in that subdirectory
+    for subdir in subdirectories:
+        files = os.listdir(os.path.join(root_dir, subdir))
+        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.item())
+    print(num_elkhounds.item())
+
+
+if __name__ == "__main__":
+    main()

ML/Pytorch/Basics/albumentations_tutorial/classification.py

@@ -3,6 +3,7 @@ import albumentations as A
 import numpy as np
 from utils import plot_examples
 from PIL import Image
+from tqdm import tqdm
 
 image = Image.open("images/elon.jpeg")
 
@@ -14,18 +15,20 @@ transform = A.Compose(
         A.HorizontalFlip(p=0.5),
         A.VerticalFlip(p=0.1),
         A.RGBShift(r_shift_limit=25, g_shift_limit=25, b_shift_limit=25, p=0.9),
-        A.OneOf([
-            A.Blur(blur_limit=3, p=0.5),
-            A.ColorJitter(p=0.5),
-        ], p=1.0),
+        A.OneOf(
+            [
+                A.Blur(blur_limit=3, p=0.5),
+                A.ColorJitter(p=0.5),
+            ],
+            p=1.0,
+        ),
     ]
 )
 
 images_list = [image]
 image = np.array(image)
-for i in range(15):
+for i in tqdm(range(15)):
     augmentations = transform(image=image)
     augmented_img = augmentations["image"]
     images_list.append(augmented_img)
 plot_examples(images_list)
-

ML/Pytorch/Basics/albumentations_tutorial/full_pytorch_example.py

@@ -8,6 +8,7 @@ from albumentations.pytorch import ToTensorV2
 from torch.utils.data import Dataset
 import os
 
+
 class ImageFolder(Dataset):
     def __init__(self, root_dir, transform=None):
         super(ImageFolder, self).__init__()
@@ -18,7 +19,7 @@ class ImageFolder(Dataset):
 
         for index, name in enumerate(self.class_names):
             files = os.listdir(os.path.join(root_dir, name))
-            self.data += list(zip(files, [index]*len(files)))
+            self.data += list(zip(files, [index] * len(files)))
 
     def __len__(self):
         return len(self.data)
@@ -43,10 +44,13 @@ transform = A.Compose(
         A.HorizontalFlip(p=0.5),
         A.VerticalFlip(p=0.1),
         A.RGBShift(r_shift_limit=25, g_shift_limit=25, b_shift_limit=25, p=0.9),
-        A.OneOf([
-            A.Blur(blur_limit=3, p=0.5),
-            A.ColorJitter(p=0.5),
-        ], p=1.0),
+        A.OneOf(
+            [
+                A.Blur(blur_limit=3, p=0.5),
+                A.ColorJitter(p=0.5),
+            ],
+            p=1.0,
+        ),
         A.Normalize(
             mean=[0, 0, 0],
             std=[1, 1, 1],
@@ -58,5 +62,5 @@ transform = A.Compose(
 
 dataset = ImageFolder(root_dir="cat_dogs", transform=transform)
 
-for x,y in dataset:
+for x, y in dataset:
     print(x.shape)

ML/Pytorch/Basics/albumentations_tutorial/utils.py

@@ -8,7 +8,7 @@ import albumentations as A
 
 def visualize(image):
     plt.figure(figsize=(10, 10))
-    plt.axis('off')
+    plt.axis("off")
     plt.imshow(image)
     plt.show()
 
@@ -22,7 +22,7 @@ def plot_examples(images, bboxes=None):
         if bboxes is not None:
             img = visualize_bbox(images[i - 1], bboxes[i - 1], class_name="Elon")
         else:
-            img = images[i-1]
+            img = images[i - 1]
         fig.add_subplot(rows, columns, i)
         plt.imshow(img)
     plt.show()

ML/Pytorch/Basics/custom_dataset/custom_FCNN.py

@@ -1,131 +0,0 @@
-# Imports
-import os
-from typing import Union
-
-import torch.nn.functional as F  # All functions that don't have any parameters
-import pandas as pd
-import torch
-import torch.nn as nn  # All neural network modules, nn.Linear, nn.Conv2d, BatchNorm, Loss functions
-import torch.optim as optim  # For all Optimization algorithms, SGD, Adam, etc.
-import torchvision
-import torchvision.transforms as transforms  # Transformations we can perform on our dataset
-from pandas import io
-
-# from skimage import io
-from torch.utils.data import (
-    Dataset,
-    DataLoader,
-)  # Gives easier dataset managment and creates mini batches
-import torch.nn as nn  # All neural network modules, nn.Linear, nn.Conv2d, BatchNorm, Loss functions
-
-
-# Create Fully Connected Network
-class NN(nn.Module):
-    def __init__(self, input_size, num_classes):
-        super(NN, self).__init__()
-        self.fc1 = nn.Linear(input_size, 50)
-        self.fc2 = nn.Linear(50, num_classes)
-
-    def forward(self, x):
-        x = F.relu(self.fc1(x))
-        x = self.fc2(x)
-        return x
-
-
-class SoloDataset(Dataset):
-    def __init__(self, csv_file, root_dir, transform=None):
-        self.annotations = pd.read_csv(csv_file)
-        self.root_dir = root_dir
-        self.transform = transform
-
-    def __len__(self):
-        return len(self.annotations)
-
-    def __getitem__(self, index):
-        x_data = self.annotations.iloc[index, 0:11]
-        x_data = torch.tensor(x_data)
-        y_label = torch.tensor(int(self.annotations.iloc[index, 11]))
-
-        return (x_data.float(), y_label)
-
-
-# Set device
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-# Hyperparameters
-num_classes = 26
-learning_rate = 1e-3
-batch_size = 5
-num_epochs = 30
-input_size = 11
-
-# Load Data
-dataset = SoloDataset(
-    csv_file="power.csv", root_dir="test123", transform=transforms.ToTensor()
-)
-train_set, test_set = torch.utils.data.random_split(dataset, [2900, 57])
-train_loader = DataLoader(dataset=train_set, batch_size=batch_size, shuffle=True)
-test_loader = DataLoader(dataset=test_set, batch_size=batch_size, shuffle=True)
-
-# Model
-model = NN(input_size=input_size, num_classes=num_classes).to(device)
-
-# Loss and optimizer
-criterion = nn.CrossEntropyLoss()
-optimizer = optim.Adam(model.parameters(), lr=learning_rate)
-
-print(len(train_set))
-print(len(test_set))
-# Train Network
-for epoch in range(num_epochs):
-    losses = []
-
-    for batch_idx, (data, targets) in enumerate(train_loader):
-        # Get data to cuda if possible
-        data = data.to(device=device)
-        targets = targets.to(device=device)
-
-        # forward
-        scores = model(data)
-        loss = criterion(scores, targets)
-
-        losses.append(loss.item())
-
-        # backward
-        optimizer.zero_grad()
-        loss.backward()
-
-        # gradient descent or adam step
-        optimizer.step()
-
-    print(f"Cost at epoch {epoch} is {sum(losses) / len(losses)}")
-
-
-# Check accuracy on training to see how good our model is
-def check_accuracy(loader, model):
-    num_correct = 0
-    num_samples = 0
-    model.eval()
-
-    with torch.no_grad():
-        for x, y in loader:
-            x = x.to(device=device)
-            y = y.to(device=device)
-
-            scores = model(x)
-            _, predictions = scores.max(1)
-            num_correct += (predictions == y).sum()
-            num_samples += predictions.size(0)
-
-        print(
-            f"Got {num_correct} / {num_samples} with accuracy {float(num_correct) / float(num_samples) * 100:.2f}"
-        )
-
-    model.train()
-
-
-print("Checking accuracy on Training Set")
-check_accuracy(train_loader, model)
-
-print("Checking accuracy on Test Set")
-check_accuracy(test_loader, model)

ML/Pytorch/Basics/custom_dataset/custom_dataset.py

@@ -6,7 +6,7 @@ label (0 for cat, 1 for dog).
 
 Programmed by Aladdin Persson <aladdin.persson at hotmail dot com>
 *    2020-04-03 Initial coding
-
+*    2022-12-19 Updated with better comments, improved code using PIL, and checked code still functions as intended.
 """
 
 # Imports
@@ -17,7 +17,7 @@ import torchvision.transforms as transforms  # Transformations we can perform on
 import torchvision
 import os
 import pandas as pd
-from skimage import io
+from PIL import Image
 from torch.utils.data import (
     Dataset,
     DataLoader,
@@ -35,7 +35,7 @@ class CatsAndDogsDataset(Dataset):
 
     def __getitem__(self, index):
         img_path = os.path.join(self.root_dir, self.annotations.iloc[index, 0])
-        image = io.imread(img_path)
+        image = Image.open(img_path)
         y_label = torch.tensor(int(self.annotations.iloc[index, 1]))
 
         if self.transform:
@@ -50,7 +50,7 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 # Hyperparameters
 in_channel = 3
 num_classes = 2
-learning_rate = 1e-3
+learning_rate = 3e-4
 batch_size = 32
 num_epochs = 10
 
@@ -69,12 +69,19 @@ train_loader = DataLoader(dataset=train_set, batch_size=batch_size, shuffle=True
 test_loader = DataLoader(dataset=test_set, batch_size=batch_size, shuffle=True)
 
 # Model
-model = torchvision.models.googlenet(pretrained=True)
+model = torchvision.models.googlenet(weights="DEFAULT")
+
+# freeze all layers, change final linear layer with num_classes
+for param in model.parameters():
+    param.requires_grad = False
+
+# final layer is not frozen
+model.fc = nn.Linear(in_features=1024, out_features=num_classes)
 model.to(device)
 
 # Loss and optimizer
 criterion = nn.CrossEntropyLoss()
-optimizer = optim.Adam(model.parameters(), lr=learning_rate)
+optimizer = optim.Adam(model.parameters(), lr=learning_rate, weight_decay=1e-5)
 
 # Train Network
 for epoch in range(num_epochs):

ML/Pytorch/Basics/custom_dataset_txt/get_data.sh

@@ -0,0 +1,3 @@
+#!/bin/sh
+
+wget https://www.kaggle.com/datasets/e1cd22253a9b23b073794872bf565648ddbe4f17e7fa9e74766ad3707141adeb/download?datasetVersionNumber=1

ML/Pytorch/Basics/custom_dataset_txt/loader_customtext.py

@@ -1,3 +1,15 @@
+"""
+Introductory tutorial on how to deal with custom text datasets in PyTorch.
+Note that there are better ways to do this when dealing with huge text datasets.
+But this is a good way of understanding how it works and can be used as a starting 
+point, particularly for smaller/medium datasets.
+
+Programmed by Aladdin Persson <aladdin.persson at hotmail dot com>
+*    2020-04-09 Initial coding
+*    2022-12-19 Updated comments, minor code revision, and checked code still works with latest PyTorch.
+"""
+
+
 import os  # when loading file paths
 import pandas as pd  # for lookup in annotation file
 import spacy  # for tokenizer
@@ -15,8 +27,8 @@ import torchvision.transforms as transforms
 #    of same seq_len and setup dataloader)
 # Note that loading the image is very easy compared to the text!
 
-# Download with: python -m spacy download en
-spacy_eng = spacy.load("en")
+# Download with: python -m spacy download en_core_web_sm
+spacy_eng = spacy.load("en_core_web_sm")
 
 
 class Vocabulary:
@@ -130,7 +142,10 @@ def get_loader(
 
 if __name__ == "__main__":
     transform = transforms.Compose(
-        [transforms.Resize((224, 224)), transforms.ToTensor(),]
+        [
+            transforms.Resize((224, 224)),
+            transforms.ToTensor(),
+        ]
     )
 
     loader, dataset = get_loader(

ML/Pytorch/Basics/lightning_simple_CNN.py

@@ -0,0 +1,190 @@
+"""
+Simple pytorch lightning example
+"""
+
+# Imports
+import torch
+import torch.nn.functional as F  # Parameterless functions, like (some) activation functions
+import torchvision.datasets as datasets  # Standard datasets
+import torchvision.transforms as transforms  # Transformations we can perform on our dataset for augmentation
+from torch import optim  # For optimizers like SGD, Adam, etc.
+from torch import nn  # All neural network modules
+from torch.utils.data import (
+    DataLoader,
+)  # Gives easier dataset managment by creating mini batches etc.
+from tqdm import tqdm  # For nice progress bar!
+import pytorch_lightning as pl
+import torchmetrics
+from pytorch_lightning.callbacks import Callback, EarlyStopping
+
+
+precision = "medium"
+torch.set_float32_matmul_precision(precision)
+criterion = nn.CrossEntropyLoss()
+
+
+## use 20% of training data for validation
+# train_set_size = int(len(train_dataset) * 0.8)
+# valid_set_size = len(train_dataset) - train_set_size
+#
+## split the train set into two
+# seed = torch.Generator().manual_seed(42)
+# train_dataset, val_dataset = torch.utils.data.random_split(
+#    train_dataset, [train_set_size, valid_set_size], generator=seed
+# )
+
+
+class CNNLightning(pl.LightningModule):
+    def __init__(self, lr=3e-4, in_channels=1, num_classes=10):
+        super().__init__()
+        self.lr = lr
+        self.train_acc = torchmetrics.Accuracy(task="multiclass", num_classes=10)
+        self.test_acc = torchmetrics.Accuracy(task="multiclass", num_classes=10)
+        self.conv1 = nn.Conv2d(
+            in_channels=in_channels,
+            out_channels=8,
+            kernel_size=3,
+            stride=1,
+            padding=1,
+        )
+        self.pool = nn.MaxPool2d(kernel_size=2, stride=2)
+        self.conv2 = nn.Conv2d(
+            in_channels=8,
+            out_channels=16,
+            kernel_size=3,
+            stride=1,
+            padding=1,
+        )
+        self.fc1 = nn.Linear(16 * 7 * 7, num_classes)
+        self.lr = lr
+
+    def training_step(self, batch, batch_idx):
+        x, y = batch
+        y_hat = self._common_step(x, batch_idx)
+        loss = criterion(y_hat, y)
+        accuracy = self.train_acc(y_hat, y)
+        self.log(
+            "train_acc_step",
+            self.train_acc,
+            on_step=True,
+            on_epoch=False,
+            prog_bar=True,
+        )
+        return loss
+
+    def training_epoch_end(self, outputs):
+        self.train_acc.reset()
+
+    def test_step(self, batch, batch_idx):
+        x, y = batch
+        y_hat = self._common_step(x, batch_idx)
+        loss = F.cross_entropy(y_hat, y)
+        accuracy = self.test_acc(y_hat, y)
+        self.log("test_loss", loss, on_step=True)
+        self.log("test_acc", accuracy, on_step=True)
+
+    def validation_step(self, batch, batch_idx):
+        x, y = batch
+        y_hat = self._common_step(x, batch_idx)
+        loss = F.cross_entropy(y_hat, y)
+        accuracy = self.test_acc(y_hat, y)
+        self.log("val_loss", loss, on_step=True)
+        self.log("val_acc", accuracy, on_step=True)
+
+    def predict_step(self, batch, batch_idx):
+        x, y = batch
+        y_hat = self._common_step(x)
+        return y_hat
+
+    def _common_step(self, x, batch_idx):
+        x = self.pool(F.relu(self.conv1(x)))
+        x = self.pool(F.relu(self.conv2(x)))
+        x = x.reshape(x.shape[0], -1)
+        y_hat = self.fc1(x)
+        return y_hat
+
+    def configure_optimizers(self):
+        optimizer = optim.Adam(self.parameters(), lr=self.lr)
+        return optimizer
+
+
+class MNISTDataModule(pl.LightningDataModule):
+    def __init__(self, batch_size=512):
+        super().__init__()
+        self.batch_size = batch_size
+
+    def setup(self, stage):
+        mnist_full = train_dataset = datasets.MNIST(
+            root="dataset/", train=True, transform=transforms.ToTensor(), download=True
+        )
+        self.mnist_test = datasets.MNIST(
+            root="dataset/", train=False, transform=transforms.ToTensor(), download=True
+        )
+        self.mnist_train, self.mnist_val = torch.utils.data.random_split(
+            mnist_full, [55000, 5000]
+        )
+
+    def train_dataloader(self):
+        return DataLoader(
+            self.mnist_train,
+            batch_size=self.batch_size,
+            num_workers=6,
+            shuffle=True,
+        )
+
+    def val_dataloader(self):
+        return DataLoader(
+            self.mnist_val, batch_size=self.batch_size, num_workers=2, shuffle=False
+        )
+
+    def test_dataloader(self):
+        return DataLoader(
+            self.mnist_test, batch_size=self.batch_size, num_workers=2, shuffle=False
+        )
+
+
+class MyPrintingCallback(Callback):
+    def on_train_start(self, trainer, pl_module):
+        print("Training is starting")
+
+    def on_train_end(self, trainer, pl_module):
+        print("Training is ending")
+
+
+# Set device
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Load Data
+if __name__ == "__main__":
+    # Initialize network
+    model_lightning = CNNLightning()
+
+    trainer = pl.Trainer(
+        #fast_dev_run=True,
+        # overfit_batches=3,
+        max_epochs=5,
+        precision=16,
+        accelerator="gpu",
+        devices=[0,1],
+        callbacks=[EarlyStopping(monitor="val_loss", mode="min")],
+        auto_lr_find=True,
+        enable_model_summary=True,
+        profiler="simple",
+        strategy="deepspeed_stage_1",
+        # accumulate_grad_batches=2,
+        # auto_scale_batch_size="binsearch",
+        # log_every_n_steps=1,
+    )
+
+    dm = MNISTDataModule()
+
+    # trainer tune first to find best batch size and lr
+    trainer.tune(model_lightning, dm)
+
+    trainer.fit(
+        model=model_lightning,
+        datamodule=dm,
+    )
+
+    # test model on test loader from LightningDataModule
+    trainer.test(model=model_lightning, datamodule=dm)

ML/Pytorch/Basics/pytorch_bidirectional_lstm.py

@@ -1,15 +1,17 @@
 """
 Example code of a simple bidirectional LSTM on the MNIST dataset.
+Note that using RNNs on image data is not the best idea, but it is a 
+good example to show how to use RNNs that still generalizes to other tasks.
 
 Programmed by Aladdin Persson <aladdin.persson at hotmail dot com>
 *    2020-05-09 Initial coding
+*    2022-12-16 Updated with more detailed comments, docstrings to functions, and checked code still functions as intended.
 
 """
 
 
 # Imports
 import torch
-import torchvision
 import torch.nn as nn  # All neural network modules, nn.Linear, nn.Conv2d, BatchNorm, Loss functions
 import torch.optim as optim  # For all Optimization algorithms, SGD, Adam, etc.
 import torch.nn.functional as F  # All functions that don't have any parameters
@@ -18,9 +20,10 @@ from torch.utils.data import (
 )  # Gives easier dataset managment and creates mini batches
 import torchvision.datasets as datasets  # Has standard datasets we can import in a nice way
 import torchvision.transforms as transforms  # Transformations we can perform on our dataset
+from tqdm import tqdm  # progress bar
 
 # Set device
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+device = "cuda" if torch.cuda.is_available() else "cpu"
 
 # Hyperparameters
 input_size = 28
@@ -28,7 +31,7 @@ sequence_length = 28
 num_layers = 2
 hidden_size = 256
 num_classes = 10
-learning_rate = 0.001
+learning_rate = 3e-4
 batch_size = 64
 num_epochs = 2
 
@@ -47,7 +50,7 @@ class BRNN(nn.Module):
         h0 = torch.zeros(self.num_layers * 2, x.size(0), self.hidden_size).to(device)
         c0 = torch.zeros(self.num_layers * 2, x.size(0), self.hidden_size).to(device)
 
-        out, _ = self.lstm(x, (h0, c0))
+        out, _ = self.lstm(x)
         out = self.fc(out[:, -1, :])
 
         return out
@@ -74,7 +77,7 @@ optimizer = optim.Adam(model.parameters(), lr=learning_rate)
 
 # Train Network
 for epoch in range(num_epochs):
-    for batch_idx, (data, targets) in enumerate(train_loader):
+    for batch_idx, (data, targets) in enumerate(tqdm(train_loader)):
         # Get data to cuda if possible
         data = data.to(device=device).squeeze(1)
         targets = targets.to(device=device)
@@ -90,9 +93,8 @@ for epoch in range(num_epochs):
         # gradient descent or adam step
         optimizer.step()
 
+
 # Check accuracy on training & test to see how good our model
-
-
 def check_accuracy(loader, model):
     if loader.dataset.train:
         print("Checking accuracy on training data")

ML/Pytorch/Basics/pytorch_init_weights.py

@@ -1,12 +1,16 @@
 """
 Example code of how to initialize weights for a simple CNN network.
+Usually this is not needed as default initialization is usually good,
+but sometimes it can be useful to initialize weights in a specific way.
+This way of doing it should generalize to other network types just make 
+sure to specify and change the modules you wish to modify.
 
 Video explanation: https://youtu.be/xWQ-p_o0Uik
 Got any questions leave a comment on youtube :)
 
 Programmed by Aladdin Persson <aladdin.persson at hotmail dot com>
 *    2020-04-10 Initial coding
-
+*    2022-12-16 Updated with more detailed comments, and checked code still functions as intended.
 """
 
 # Imports
@@ -20,17 +24,17 @@ class CNN(nn.Module):
         self.conv1 = nn.Conv2d(
             in_channels=in_channels,
             out_channels=6,
-            kernel_size=(3, 3),
-            stride=(1, 1),
-            padding=(1, 1),
+            kernel_size=3,
+            stride=1,
+            padding=1,
         )
         self.pool = nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2))
         self.conv2 = nn.Conv2d(
             in_channels=6,
             out_channels=16,
-            kernel_size=(3, 3),
-            stride=(1, 1),
-            padding=(1, 1),
+            kernel_size=3,
+            stride=1,
+            padding=1,
         )
         self.fc1 = nn.Linear(16 * 7 * 7, num_classes)
         self.initialize_weights()