add imbalanced classes video code and kaggle cat vs dog

Author: aladdinpersson

.github/FUNDING.yml

@@ -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/Logistic Regression on EfficientNet Features.ipynb

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

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

@@ -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/config.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