{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "QquaYpB00hfs"
},
"source": [
"[](http://edenlibrary.ai/)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "yp-OgP370hft"
},
"source": [
"## Instructions\n",
"To run any of Eden's notebooks, please check the guides on our [Wiki page](https://github.com/Eden-Library-AI/eden_library_notebooks/wiki). \n",
"There you will find instructions on how to deploy the notebooks on [your local system](https://github.com/Eden-Library-AI/eden_library_notebooks/wiki/Deploy-Notebooks-Locally), on [Google Colab](https://github.com/Eden-Library-AI/eden_library_notebooks/wiki/Deploy-Notebooks-on-GColab), or on [MyBinder](https://github.com/Eden-Library-AI/eden_library_notebooks/wiki/Deploy-Notebooks-on-MyBinder), as well as other useful links, troubleshooting tips, and more.\n",
"\n",
"**Note:** If you find any issues while executing the notebook, don't hesitate to open an issue on Github. We will try to reply as soon as possible."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "dwqUKc-L0hft"
},
"source": [
"## Background\n",
"\n",
"In this notebook, **CLIP** model is going to be used to extract meaningful visual features from agricultural data. Then, on the top of those features, a linear model is trained to create the final classifier (Linear Probe). CLIP (Contrastive Language–Image Pre-training) is a model developed by OpenAI, designed to understand and generate content across both visual (images) and textual (language) modalities. It represents a significant step in the evolution of foundation models, particularly in the realm of multimodal AI.\n",
"\n",
"### Defintions\n",
"**Foundation models** refer to a class of large-scale machine learning models that are trained on a broad range of data sources to acquire a wide set of capabilities. These models can be adapted or fine-tuned for various specific tasks and applications. On the other hand, \n",
"\n",
"**Multimodality** in machine learning refers to models that can understand, interpret, or generate data from multiple different modalities, such as text, images, audio, and video.\n",
"\n",
"**Linear Probe** involves training a simple linear model, like logistic regression, on the features extracted from one of the layers of a pre-trained neural network. The objective is to see how well these features can be used for a specific task, such as classification.\n",
"\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "_6aZBfhYzysx"
},
"source": [
"#### Special Dependencies\n",
"- CLIP"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "sL9-RlDay_ok"
},
"outputs": [],
"source": [
"!pip install -q git+https://github.com/openai/CLIP.git"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "vyIF86zz0hfu"
},
"source": [
"#### Library Imports"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "hj9NVykKZM_z",
"outputId": "c8fa2042-3453-4ae9-cea5-682dc7beb354"
},
"outputs": [],
"source": [
"import torch\n",
"from torch.utils.data import Dataset\n",
"from torch.utils.data import DataLoader\n",
"from torchvision import transforms\n",
"\n",
"from pathlib import Path\n",
"\n",
"import clip\n",
"\n",
"import numpy as np\n",
"import os\n",
"import cv2\n",
"from tqdm import tqdm\n",
"from glob import glob\n",
"\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.metrics import accuracy_score\n",
"from sklearn.manifold import TSNE\n",
"import matplotlib.pyplot as plt\n",
"\n",
"SEED = 2023"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "uuV03GcT0hfv"
},
"source": [
"#### Auxiliar functions\n",
"Check the docstrings for more information."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"id": "DxKW-6Wdy_om"
},
"outputs": [],
"source": [
"def read_data(path_list, im_size=(224, 224)):\n",
" \"\"\"\n",
" Given the list of paths where the images are stored ,\n",
" and the size for image decimation , it returns 2 Numpy Arrays\n",
" with the images and labels.\n",
"\n",
" Parameters:\n",
" path_list (List[String]): The list of paths to the images.\n",
" im_size (Tuple): The height and width values.\n",
"\n",
" Returns:\n",
" X (ndarray): Images\n",
" y (ndarray): Labels\n",
" \"\"\"\n",
" X = []\n",
" y = []\n",
"\n",
" # Extract filenames of the datasets we ingest and create a label dictionary\n",
" tag2idx = {tag.split(os.path.sep)[-1]: i for i, tag in enumerate(path_list)}\n",
"\n",
" for path in path_list:\n",
" for im_file in tqdm(glob(path + \"*/*\")): # Read all files in path\n",
" try:\n",
" # os.path.separator is OS agnostic (either '/' or '\\'),[-2] to grab folder name\n",
" label = im_file.split(os.path.sep)[-2]\n",
" im = cv2.imread(im_file, cv2.IMREAD_COLOR)\n",
" # By default OpenCV reads with BGR format, convert to RGB\n",
" im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)\n",
" # Resize to appropriate dimensions\n",
" im = cv2.resize(im, im_size, interpolation=cv2.INTER_AREA)\n",
" X.append(im/255.0)\n",
" y.append(tag2idx[label]) # Append the label name to y\n",
" except Exception as e:\n",
" # In case annotations or metadata are found\n",
" print(e)\n",
"\n",
" X = np.array(X) # Convert list to numpy array.\n",
" y = np.array(y).astype(np.uint8)\n",
"\n",
" return X, y"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Important function\n",
"It extracts the visual features"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"def get_features(dataset, batch_size=32):\n",
" \"\"\"\n",
" This function uses CLIP to extract the visual features from the images.\n",
" \"\"\"\n",
" all_features = []\n",
" all_labels = []\n",
"\n",
" with torch.no_grad():\n",
" for images, labels in tqdm(DataLoader(dataset, batch_size=batch_size)):\n",
" features = model.encode_image(images.to(device))\n",
"\n",
" all_features.append(features)\n",
" all_labels.append(labels)\n",
"\n",
" return torch.cat(all_features).cpu().numpy(), \\\n",
" torch.cat(all_labels).cpu().numpy()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Auxiliar Class"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"class WeedIdentificationDataset(Dataset):\n",
" def __init__(self, x, y, transforms=None):\n",
" super(WeedIdentificationDataset, self).__init__()\n",
" self.x = x\n",
" self.y = y\n",
" self.transforms = transforms\n",
"\n",
" def __len__(self):\n",
" return len(self.x)\n",
"\n",
" def __getitem__(self, idx):\n",
" images = self.x[idx]\n",
" labels = self.y[idx]\n",
"\n",
" if self.transforms:\n",
" images = self.transforms(images)\n",
"\n",
" return images, labels"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "gFfTG8Ga_Ibb"
},
"source": [
"#### Experimental Constants"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"id": "ZKt2BjIry_on",
"outputId": "dfbc6d44-a429-410a-c322-7ed37367a978"
},
"outputs": [],
"source": [
"# Eden datasets we will work on\n",
"PATH_LIST = [\n",
" \"Black nightsade-Solanum nigrum-220519-Weed-zz\",\n",
" \"Tomato-Solanum lycopersicum-240519-Healthy-zz\"\n",
"]\n",
"\n",
"IM_SIZE = (224, 224)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "IPE0KaIa_PHw"
},
"source": [
"#### Loading images"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
" 85%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉ | 105/124 [00:21<00:03, 4.78it/s]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"OpenCV(4.8.1) /io/opencv/modules/imgproc/src/color.cpp:182: error: (-215:Assertion failed) !_src.empty() in function 'cvtColor'\n",
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 124/124 [00:25<00:00, 4.87it/s]\n",
" 45%|█████████████████████████████████████████████████████████████████████████████████████████████████████████▋ | 90/201 [00:29<00:36, 3.07it/s]Corrupt JPEG data: 65 extraneous bytes before marker 0xd9\n",
" 87%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▍ | 174/201 [00:57<00:08, 3.06it/s]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"OpenCV(4.8.1) /io/opencv/modules/imgproc/src/color.cpp:182: error: (-215:Assertion failed) !_src.empty() in function 'cvtColor'\n",
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 201/201 [01:05<00:00, 3.06it/s]\n"
]
}
],
"source": [
"i = 0\n",
"for path in PATH_LIST:\n",
" # Define paths in an OS agnostic way.\n",
" PATH_LIST[i] = str(\n",
" Path(Path.cwd()).parents[0].joinpath(\"eden_library_datasets\").joinpath(path)\n",
" )\n",
" i += 1\n",
"x, y = read_data(PATH_LIST, IM_SIZE)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "KWLBTyor0hfy"
},
"source": [
"#### Setting CUDA configuration if available"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"id": "qeZd9vwYjgMK",
"outputId": "ae2d8ea5-99fa-4306-9e5f-310e09850d5d"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"cuda\n"
]
}
],
"source": [
"# Using CUDA if available\n",
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
"print(device)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Data preprocessing\n",
"1. Train-test splitting\n",
"2. Tensors creation\n",
"3. Dataset creation from tensors with normalization"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"id": "LITwAemvy_oo",
"outputId": "4d932929-2925-4658-8e75-3afba016b9e2"
},
"outputs": [],
"source": [
"x_train, x_test, y_train, y_test = train_test_split(\n",
" x, y, test_size = 0.25, shuffle=True, stratify=y, random_state=SEED\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"x_train = torch.tensor(x_train, dtype=torch.float32).permute(0, 3, 1, 2)\n",
"x_test = torch.tensor(x_test, dtype=torch.float32).permute(0, 3, 1, 2)"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [],
"source": [
"naive_preprocess = transforms.Compose([\n",
" transforms.Normalize(mean=(0.48145466, 0.4578275, 0.40821073),\n",
" std=(0.26862954, 0.26130258, 0.27577711))\n",
"]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"train = WeedIdentificationDataset(x_train, y_train, naive_preprocess)\n",
"test = WeedIdentificationDataset(x_test, y_test, naive_preprocess)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Loading CLIP model"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [],
"source": [
"model, preprocess = clip.load(\"ViT-B/32\", device)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Phase 1: Feature Extraction"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:00<00:00, 34.30it/s]\n",
"100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:00<00:00, 41.36it/s]\n"
]
}
],
"source": [
"train_features, train_labels = get_features(train)\n",
"test_features, test_labels = get_features(test)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "o6PCyK070zSJ"
},
"source": [
"### Phase 2: Linear Probe"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.metrics import accuracy_score"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {
"id": "9EU5EFw9y_oo",
"outputId": "c75ea4ef-05cb-4c3a-da6f-3bd0f3d64413"
},
"outputs": [
{
"data": {
"text/html": [
"
LogisticRegression()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
LogisticRegression()
"
],
"text/plain": [
"LogisticRegression()"
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Perform logistic regression\n",
"classifier = LogisticRegression()\n",
"classifier.fit(train_features, train_labels)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "NM62xxmx03kZ"
},
"source": [
"### Evaluation"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [],
"source": [
"predictions = classifier.predict(test_features)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"id": "QFwneMLKy_oo",
"outputId": "52097280-3438-4160-c0c7-258773ea26ed"
},
"outputs": [
{
"data": {
"text/plain": [
"1.0"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"accuracy_score(test_labels, predictions)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Images represetation\n",
"We are using the t-SNE algorithm to project the original dimensions into a 2 or 3 dimensional space. **t-Distributed Stochastic Neighbor Embedding (t-SNE)** is a machine learning algorithm used mainly for the visualization of high-dimensional data. It's particularly useful in the fields of data science and machine learning for understanding complex datasets. t-SNE is a form of manifold learning. It works by capturing the local structure of the high-dimensional space and then revealing these structures in a lower-dimensional space, often revealing clusters or groupings in the data. The key feature of t-SNE is its ability to preserve local structures and relationships between points. Similar data points in the high-dimensional space will be close to each other in the low-dimensional space. The resulting visualization often shows distinct clusters, which can be extremely useful for exploratory data analysis, identifying patterns, or even for communicating findings."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### CLIP representation"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 3 Dimensions"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/borjaeg/anaconda3/envs/paper_pytorch_transformers/lib/python3.9/site-packages/sklearn/manifold/_t_sne.py:800: FutureWarning: The default initialization in TSNE will change from 'random' to 'pca' in 1.2.\n",
" warnings.warn(\n",
"/home/borjaeg/anaconda3/envs/paper_pytorch_transformers/lib/python3.9/site-packages/sklearn/manifold/_t_sne.py:810: FutureWarning: The default learning rate in TSNE will change from 200.0 to 'auto' in 1.2.\n",
" warnings.warn(\n"
]
}
],
"source": [
"tsne = TSNE(n_components = 3, random_state=0)\n",
"projections = tsne.fit_transform(train_features)"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"