mirror of
https://github.com/20kaushik02/CSE515_MWDB_Project.git
synced 2025-12-06 11:54:07 +00:00
refactored pranav's task 3 code
changed latent semantic storage, LDA is latent dirichlet allocation and image-weight arrangement is reversed
This commit is contained in:
parent
5580611ba4
commit
78be91a0ca
@ -1,218 +0,0 @@
|
|||||||
{
|
|
||||||
"cells": [
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 1,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"ename": "ModuleNotFoundError",
|
|
||||||
"evalue": "No module named 'task0a'",
|
|
||||||
"output_type": "error",
|
|
||||||
"traceback": [
|
|
||||||
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
|
||||||
"\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
|
|
||||||
"\u001b[1;32me:\\Fall 23\\CSE 515 - Multimedia and web databases\\CSE515_MWDB_Project\\Phase 2\\task1.ipynb Cell 1\u001b[0m line \u001b[0;36m4\n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W0sZmlsZQ%3D%3D?line=1'>2</a>\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mmath\u001b[39;00m\n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W0sZmlsZQ%3D%3D?line=2'>3</a>\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mmatplotlib\u001b[39;00m\u001b[39m.\u001b[39;00m\u001b[39mpyplot\u001b[39;00m \u001b[39mas\u001b[39;00m \u001b[39mplt\u001b[39;00m\n\u001b[1;32m----> <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W0sZmlsZQ%3D%3D?line=3'>4</a>\u001b[0m \u001b[39mfrom\u001b[39;00m \u001b[39mtask0a\u001b[39;00m \u001b[39mimport\u001b[39;00m \u001b[39m*\u001b[39m\n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W0sZmlsZQ%3D%3D?line=4'>5</a>\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mscipy\u001b[39;00m\n",
|
|
||||||
"\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'task0a'"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"from pymongo import MongoClient\n",
|
|
||||||
"import math\n",
|
|
||||||
"import matplotlib.pyplot as plt\n",
|
|
||||||
"# This was imported for the loadDataset function in the cell below\n",
|
|
||||||
"from task0a import *\n",
|
|
||||||
"import scipy"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 2,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"ename": "NameError",
|
|
||||||
"evalue": "name 'loadDataset' is not defined",
|
|
||||||
"output_type": "error",
|
|
||||||
"traceback": [
|
|
||||||
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
|
||||||
"\u001b[1;31mNameError\u001b[0m Traceback (most recent call last)",
|
|
||||||
"\u001b[1;32me:\\Fall 23\\CSE 515 - Multimedia and web databases\\CSE515_MWDB_Project\\Phase 2\\task1.ipynb Cell 2\u001b[0m line \u001b[0;36m7\n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W1sZmlsZQ%3D%3D?line=3'>4</a>\u001b[0m \u001b[39m# Select the database\u001b[39;00m\n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W1sZmlsZQ%3D%3D?line=4'>5</a>\u001b[0m db \u001b[39m=\u001b[39m client\u001b[39m.\u001b[39mMultimedia_Web_DBs\n\u001b[1;32m----> <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W1sZmlsZQ%3D%3D?line=6'>7</a>\u001b[0m caltechDataset \u001b[39m=\u001b[39m loadDataset()\n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W1sZmlsZQ%3D%3D?line=8'>9</a>\u001b[0m \u001b[39m# Fetch all documents from the collection and then sort them by \"_id\"\u001b[39;00m\n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W1sZmlsZQ%3D%3D?line=9'>10</a>\u001b[0m feature_descriptors \u001b[39m=\u001b[39m \u001b[39mlist\u001b[39m(db\u001b[39m.\u001b[39mCaltech101_Feature_Descriptors\u001b[39m.\u001b[39mfind({}))\n",
|
|
||||||
"\u001b[1;31mNameError\u001b[0m: name 'loadDataset' is not defined"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"client = MongoClient()\n",
|
|
||||||
"client = MongoClient(host=\"localhost\", port=27017)\n",
|
|
||||||
"\n",
|
|
||||||
"# Select the database\n",
|
|
||||||
"db = client.Multimedia_Web_DBs\n",
|
|
||||||
"\n",
|
|
||||||
"# This function was the part of task 1 in my project directory. \n",
|
|
||||||
"# caltechDataset is in format (_id, image_pixels, label)\n",
|
|
||||||
"caltechDataset = loadDataset()\n",
|
|
||||||
"\n",
|
|
||||||
"# Fetch all documents from the collection and then sort them by \"_id\"\n",
|
|
||||||
"feature_descriptors = list(db.Caltech101_Feature_Descriptors.find({}))\n",
|
|
||||||
"feature_descriptors = sorted(list(db.Caltech101_Feature_Descriptors.find({})), key=lambda x: x[\"_id\"], reverse=False)\n",
|
|
||||||
"\n",
|
|
||||||
"num_labels = 101"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 3,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"def calculate_label_means(l, feature_model):\n",
|
|
||||||
" \n",
|
|
||||||
" # Just picking the feature vector for that particular label from even _id rows in the dataset\n",
|
|
||||||
" label_vectors = [x[feature_model] for x in feature_descriptors if x[\"label\"] == l and x[\"_id\"] % 2 == 0]\n",
|
|
||||||
" \n",
|
|
||||||
" label_mean_vector = [sum(col)/len(col) for col in zip(*label_vectors)]\n",
|
|
||||||
" return label_mean_vector"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 4,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"def findKRelevantImages(mean_vector, feature_model, l):\n",
|
|
||||||
"\n",
|
|
||||||
" # Same as in above function, but took ids as well.\n",
|
|
||||||
" # Redundant step.\n",
|
|
||||||
" label_vectors = [(x[\"_id\"], x[feature_model]) for x in feature_descriptors if x[\"_id\"] % 2 == 0]\n",
|
|
||||||
"\n",
|
|
||||||
" n = len(label_vectors)\n",
|
|
||||||
"\n",
|
|
||||||
" similarities = []\n",
|
|
||||||
"\n",
|
|
||||||
" # Use the appropriate similarity based on feature model selected by the user\n",
|
|
||||||
" match feature_model:\n",
|
|
||||||
"\n",
|
|
||||||
" case \"color_moments\":\n",
|
|
||||||
"\n",
|
|
||||||
" for i in range(n):\n",
|
|
||||||
" similarities.append({\"_id\": label_vectors[i][0], \"similarity\": math.dist(mean_vector, label_vectors[i][1])})\n",
|
|
||||||
" similarities = sorted(similarities, key=lambda x: x[\"similarity\"], reverse=False)\n",
|
|
||||||
"\n",
|
|
||||||
" case \"hog\":\n",
|
|
||||||
"\n",
|
|
||||||
" for i in range(n):\n",
|
|
||||||
" similarities.append({\"_id\": label_vectors[i][0], \"similarity\": (np.dot(mean_vector, label_vectors[i][1]) / (np.linalg.norm(mean_vector) * np.linalg.norm(label_vectors[i][1])))})\n",
|
|
||||||
" similarities = sorted(similarities, key=lambda x: x[\"similarity\"], reverse=True)\n",
|
|
||||||
" \n",
|
|
||||||
" case \"layer3\" | \"avgpool\" | \"fc\":\n",
|
|
||||||
"\n",
|
|
||||||
" for i in range(n):\n",
|
|
||||||
" similarities.append({\"_id\": label_vectors[i][0], \"similarity\": scipy.stats.pearsonr(mean_vector, label_vectors[i][1]).statistic})\n",
|
|
||||||
" similarities = sorted(similarities, key=lambda x: x[\"similarity\"], reverse=True)\n",
|
|
||||||
" \n",
|
|
||||||
" return similarities\n"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 5,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"def main():\n",
|
|
||||||
"\n",
|
|
||||||
" # Load dataset\n",
|
|
||||||
"\n",
|
|
||||||
" # User input for Image ID\n",
|
|
||||||
" l = int(input(\"Enter query label: \"))\n",
|
|
||||||
" k = int(input(\"Enter k: \"))\n",
|
|
||||||
"\n",
|
|
||||||
" features = ['color_moments', 'hog', 'layer3', 'avgpool', 'fc']\n",
|
|
||||||
"\n",
|
|
||||||
" # User input for feature model to extract\n",
|
|
||||||
" print(\"1: Color moments\")\n",
|
|
||||||
" print(\"2: HOG\")\n",
|
|
||||||
" print(\"3: Resnet50 Avgpool layer\")\n",
|
|
||||||
" print(\"4: Resnet50 Layer 3\")\n",
|
|
||||||
" print(\"5: Resnet50 FC layer\")\n",
|
|
||||||
" feature_model = features[int(input(\"Select the feature model: \")) - 1]\n",
|
|
||||||
"\n",
|
|
||||||
" mean_vector = calculate_label_means(l, feature_model)\n",
|
|
||||||
"\n",
|
|
||||||
" similar_images = findKRelevantImages(mean_vector, feature_model, l)\n",
|
|
||||||
"\n",
|
|
||||||
" for i in range(k):\n",
|
|
||||||
" print(similar_images[i])\n",
|
|
||||||
"\n",
|
|
||||||
" # Show the \"k relevant images\"\n",
|
|
||||||
" fig, axes = plt.subplots(1, k, figsize=(15, 5))\n",
|
|
||||||
"\n",
|
|
||||||
" for i in range(k):\n",
|
|
||||||
" # caltechDataset[similar_images[i][\"_id\"]][1] because\n",
|
|
||||||
" # similar_images[i][\"_id\"] will provide me the image id\n",
|
|
||||||
" # [1] will be image pixel values since caltechDataset is in format (id, pixels, label)\n",
|
|
||||||
" axes[i].imshow(caltechDataset[similar_images[i][\"_id\"]][1].permute(1, 2, 0))\n",
|
|
||||||
" axes[i].set_title(f'id: {similar_images[i][\"_id\"]}')\n",
|
|
||||||
"\n",
|
|
||||||
" # Show the figure with all the images\n",
|
|
||||||
" plt.show()"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": 6,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [
|
|
||||||
{
|
|
||||||
"ename": "KeyboardInterrupt",
|
|
||||||
"evalue": "Interrupted by user",
|
|
||||||
"output_type": "error",
|
|
||||||
"traceback": [
|
|
||||||
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
|
||||||
"\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
|
|
||||||
"\u001b[1;32me:\\Fall 23\\CSE 515 - Multimedia and web databases\\CSE515_MWDB_Project\\Phase 2\\task1.ipynb Cell 6\u001b[0m line \u001b[0;36m2\n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W5sZmlsZQ%3D%3D?line=0'>1</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39m__name__\u001b[39m \u001b[39m==\u001b[39m \u001b[39m\"\u001b[39m\u001b[39m__main__\u001b[39m\u001b[39m\"\u001b[39m:\n\u001b[1;32m----> <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W5sZmlsZQ%3D%3D?line=1'>2</a>\u001b[0m main()\n",
|
|
||||||
"\u001b[1;32me:\\Fall 23\\CSE 515 - Multimedia and web databases\\CSE515_MWDB_Project\\Phase 2\\task1.ipynb Cell 6\u001b[0m line \u001b[0;36m6\n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W5sZmlsZQ%3D%3D?line=0'>1</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mmain\u001b[39m():\n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W5sZmlsZQ%3D%3D?line=1'>2</a>\u001b[0m \n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W5sZmlsZQ%3D%3D?line=2'>3</a>\u001b[0m \u001b[39m# Load dataset\u001b[39;00m\n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W5sZmlsZQ%3D%3D?line=3'>4</a>\u001b[0m \n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W5sZmlsZQ%3D%3D?line=4'>5</a>\u001b[0m \u001b[39m# User input for Image ID\u001b[39;00m\n\u001b[1;32m----> <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W5sZmlsZQ%3D%3D?line=5'>6</a>\u001b[0m l \u001b[39m=\u001b[39m \u001b[39mint\u001b[39m(\u001b[39minput\u001b[39;49m(\u001b[39m\"\u001b[39;49m\u001b[39mEnter query label: \u001b[39;49m\u001b[39m\"\u001b[39;49m))\n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W5sZmlsZQ%3D%3D?line=6'>7</a>\u001b[0m k \u001b[39m=\u001b[39m \u001b[39mint\u001b[39m(\u001b[39minput\u001b[39m(\u001b[39m\"\u001b[39m\u001b[39mEnter k: \u001b[39m\u001b[39m\"\u001b[39m))\n\u001b[0;32m <a href='vscode-notebook-cell:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task1.ipynb#W5sZmlsZQ%3D%3D?line=8'>9</a>\u001b[0m features \u001b[39m=\u001b[39m [\u001b[39m'\u001b[39m\u001b[39mcolor_moments\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mhog\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mlayer3\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mavgpool\u001b[39m\u001b[39m'\u001b[39m, \u001b[39m'\u001b[39m\u001b[39mfc\u001b[39m\u001b[39m'\u001b[39m]\n",
|
|
||||||
"File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python311\\site-packages\\ipykernel\\kernelbase.py:1202\u001b[0m, in \u001b[0;36mKernel.raw_input\u001b[1;34m(self, prompt)\u001b[0m\n\u001b[0;32m 1200\u001b[0m msg \u001b[39m=\u001b[39m \u001b[39m\"\u001b[39m\u001b[39mraw_input was called, but this frontend does not support input requests.\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m 1201\u001b[0m \u001b[39mraise\u001b[39;00m StdinNotImplementedError(msg)\n\u001b[1;32m-> 1202\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_input_request(\n\u001b[0;32m 1203\u001b[0m \u001b[39mstr\u001b[39;49m(prompt),\n\u001b[0;32m 1204\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_parent_ident[\u001b[39m\"\u001b[39;49m\u001b[39mshell\u001b[39;49m\u001b[39m\"\u001b[39;49m],\n\u001b[0;32m 1205\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mget_parent(\u001b[39m\"\u001b[39;49m\u001b[39mshell\u001b[39;49m\u001b[39m\"\u001b[39;49m),\n\u001b[0;32m 1206\u001b[0m password\u001b[39m=\u001b[39;49m\u001b[39mFalse\u001b[39;49;00m,\n\u001b[0;32m 1207\u001b[0m )\n",
|
|
||||||
"File \u001b[1;32m~\\AppData\\Roaming\\Python\\Python311\\site-packages\\ipykernel\\kernelbase.py:1245\u001b[0m, in \u001b[0;36mKernel._input_request\u001b[1;34m(self, prompt, ident, parent, password)\u001b[0m\n\u001b[0;32m 1242\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mKeyboardInterrupt\u001b[39;00m:\n\u001b[0;32m 1243\u001b[0m \u001b[39m# re-raise KeyboardInterrupt, to truncate traceback\u001b[39;00m\n\u001b[0;32m 1244\u001b[0m msg \u001b[39m=\u001b[39m \u001b[39m\"\u001b[39m\u001b[39mInterrupted by user\u001b[39m\u001b[39m\"\u001b[39m\n\u001b[1;32m-> 1245\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mKeyboardInterrupt\u001b[39;00m(msg) \u001b[39mfrom\u001b[39;00m \u001b[39mNone\u001b[39;00m\n\u001b[0;32m 1246\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mException\u001b[39;00m:\n\u001b[0;32m 1247\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mlog\u001b[39m.\u001b[39mwarning(\u001b[39m\"\u001b[39m\u001b[39mInvalid Message:\u001b[39m\u001b[39m\"\u001b[39m, exc_info\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m)\n",
|
|
||||||
"\u001b[1;31mKeyboardInterrupt\u001b[0m: Interrupted by user"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
],
|
|
||||||
"source": [
|
|
||||||
"if __name__ == \"__main__\":\n",
|
|
||||||
" main()"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": null,
|
|
||||||
"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": "3.11.4"
|
|
||||||
}
|
|
||||||
},
|
|
||||||
"nbformat": 4,
|
|
||||||
"nbformat_minor": 2
|
|
||||||
}
|
|
||||||
142
Phase 2/task3.ipynb
Normal file
142
Phase 2/task3.ipynb
Normal file
@ -0,0 +1,142 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"import json\n",
|
||||||
|
"from pymongo import MongoClient\n",
|
||||||
|
"from task0a import *\n",
|
||||||
|
"import scipy\n",
|
||||||
|
"import numpy as np\n",
|
||||||
|
"from sklearn.decomposition import NMF\n",
|
||||||
|
"from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
|
||||||
|
"from sklearn.cluster import KMeans\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"client = MongoClient()\n",
|
||||||
|
"client = MongoClient(host=\"localhost\", port=27017)\n",
|
||||||
|
"\n",
|
||||||
|
"# Select the database\n",
|
||||||
|
"db = client.Multimedia_Web_DBs\n",
|
||||||
|
"\n",
|
||||||
|
"# Fetch all documents from the collection and then sort them by \"_id\"\n",
|
||||||
|
"feature_descriptors = list(db.Caltech101_Feature_Descriptors.find({}))\n",
|
||||||
|
"feature_descriptors = sorted(list(db.Caltech101_Feature_Descriptors.find({})), key=lambda x: x[\"_id\"], reverse=False)\n",
|
||||||
|
"\n",
|
||||||
|
"num_labels = 101"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"def extractKLatentSemantics(k, feature_model, dim_reduction):\n",
|
||||||
|
"\n",
|
||||||
|
" feature_vectors = [x[feature_model] for x in feature_descriptors if x[\"_id\"] % 2 == 0]\n",
|
||||||
|
" feature_labels = [x[\"label\"] for x in feature_descriptors if x[\"_id\"] % 2 == 0]\n",
|
||||||
|
" feature_ids = [x[\"_id\"] for x in feature_descriptors if x[\"_id\"] % 2 == 0]\n",
|
||||||
|
"\n",
|
||||||
|
" filename = ''\n",
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
" match dim_reduction:\n",
|
||||||
|
"\n",
|
||||||
|
" case 1:\n",
|
||||||
|
" filename = f'{feature_model}-svd-semantics.json'\n",
|
||||||
|
" U, S, Vh = scipy.sparse.linalg.svds(np.array(feature_vectors), k=k)\n",
|
||||||
|
" k_latent_semantics = sorted(list(zip(feature_ids, U.tolist())), key = lambda x: x[1][0], reverse = True)\n",
|
||||||
|
"\n",
|
||||||
|
" case 2:\n",
|
||||||
|
" filename = f'{feature_model}-nnmf-semantics.json'\n",
|
||||||
|
" model = NMF(n_components = k, init = 'random', solver = 'cd', alpha_H = 0.01, alpha_W = 0.01, max_iter = 10000)\n",
|
||||||
|
" min_value = np.min(feature_vectors)\n",
|
||||||
|
" feature_vectors_shifted = feature_vectors - min_value\n",
|
||||||
|
" U = model.fit_transform(np.array(feature_vectors_shifted))\n",
|
||||||
|
" k_latent_semantics = sorted(list(zip(feature_ids, U.tolist())), key = lambda x: x[1][0], reverse = True)\n",
|
||||||
|
"\n",
|
||||||
|
" case 3:\n",
|
||||||
|
" filename = f'{feature_model}-lda-semantics.json'\n",
|
||||||
|
" U = LinearDiscriminantAnalysis(n_components = k).fit_transform(feature_vectors, feature_labels)\n",
|
||||||
|
" k_latent_semantics = sorted(list(zip(feature_ids, U.tolist())), key = lambda x: x[1][0], reverse = True)\n",
|
||||||
|
"\n",
|
||||||
|
" case 4:\n",
|
||||||
|
" filename = f'{feature_model}-kmeans-semantics.json'\n",
|
||||||
|
" kmeans = KMeans(n_clusters = k)\n",
|
||||||
|
" kmeans.fit(feature_vectors)\n",
|
||||||
|
" U = kmeans.transform(feature_vectors)\n",
|
||||||
|
" k_latent_semantics = sorted(list(zip(feature_ids, U.tolist())), key = lambda x: x[1][0], reverse = True)\n",
|
||||||
|
" \n",
|
||||||
|
" k_latent_semantics = [{\"_id\": item[0], \"semantics\": item[1]} for item in k_latent_semantics]\n",
|
||||||
|
" with open(filename, 'w', encoding='utf-8') as f:\n",
|
||||||
|
" json.dump(k_latent_semantics, f, ensure_ascii = False)\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"def main():\n",
|
||||||
|
"\n",
|
||||||
|
" # Load dataset\n",
|
||||||
|
"\n",
|
||||||
|
" # User input for Image ID\n",
|
||||||
|
" k = int(input(\"Enter k: \"))\n",
|
||||||
|
"\n",
|
||||||
|
" features = ['color_moments', 'hog', 'layer3', 'avgpool', 'fc']\n",
|
||||||
|
"\n",
|
||||||
|
" # User input for feature model to extract\n",
|
||||||
|
" print(\"\\n1: Color moments\")\n",
|
||||||
|
" print(\"2: HOG\")\n",
|
||||||
|
" print(\"3: Resnet50 Avgpool layer\")\n",
|
||||||
|
" print(\"4: Resnet50 Layer 3\")\n",
|
||||||
|
" print(\"5: Resnet50 FC layer\")\n",
|
||||||
|
" feature_model = features[int(input(\"Select the feature model: \")) - 1]\n",
|
||||||
|
"\n",
|
||||||
|
" print(\"\\n1. SVD\")\n",
|
||||||
|
" print(\"2. NNMF\")\n",
|
||||||
|
" print(\"3. LDA\")\n",
|
||||||
|
" print(\"4. k-means\")\n",
|
||||||
|
" dim_reduction = int(input(\"Select the dimensionality reduction technique: \"))\n",
|
||||||
|
"\n",
|
||||||
|
" extractKLatentSemantics(k, feature_model, dim_reduction)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"if __name__ == \"__main__\":\n",
|
||||||
|
" main()"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"metadata": {
|
||||||
|
"language_info": {
|
||||||
|
"name": "python"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nbformat": 4,
|
||||||
|
"nbformat_minor": 2
|
||||||
|
}
|
||||||
@ -2,126 +2,82 @@
|
|||||||
"cells": [
|
"cells": [
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": null,
|
"execution_count": 4,
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
"import json\n",
|
"from utils import *\n",
|
||||||
"from pymongo import MongoClient\n",
|
"warnings.filterwarnings('ignore')\n",
|
||||||
"from task0a import *\n",
|
"%matplotlib inline"
|
||||||
"import scipy\n",
|
|
||||||
"import numpy as np\n",
|
|
||||||
"from sklearn.decomposition import NMF\n",
|
|
||||||
"from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
|
|
||||||
"from sklearn.cluster import KMeans\n"
|
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": null,
|
"execution_count": 5,
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
"client = MongoClient()\n",
|
"fd_collection = getCollection(\"team_5_mwdb_phase_2\", \"fd_collection\")\n"
|
||||||
"client = MongoClient(host=\"localhost\", port=27017)\n",
|
|
||||||
"\n",
|
|
||||||
"# Select the database\n",
|
|
||||||
"db = client.Multimedia_Web_DBs\n",
|
|
||||||
"\n",
|
|
||||||
"# Fetch all documents from the collection and then sort them by \"_id\"\n",
|
|
||||||
"feature_descriptors = list(db.Caltech101_Feature_Descriptors.find({}))\n",
|
|
||||||
"feature_descriptors = sorted(list(db.Caltech101_Feature_Descriptors.find({})), key=lambda x: x[\"_id\"], reverse=False)\n",
|
|
||||||
"\n",
|
|
||||||
"num_labels = 101"
|
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": null,
|
"execution_count": 7,
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"Applying lda on the fc_fd space to get 10 latent semantics (showing only top 10 image-weight pairs for each latent semantic)...\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"ename": "KeyboardInterrupt",
|
||||||
|
"evalue": "",
|
||||||
|
"output_type": "error",
|
||||||
|
"traceback": [
|
||||||
|
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
|
||||||
|
"\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
|
||||||
|
"\u001b[1;32mc:\\Kaushik\\ASU\\CSE 515 - Multimedia and Web Databases\\Project\\Phase 2\\task_3.ipynb Cell 3\u001b[0m line \u001b[0;36m1\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_3.ipynb#W2sZmlsZQ%3D%3D?line=6'>7</a>\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39m\"\u001b[39m\u001b[39mk should be a positive integer\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_3.ipynb#W2sZmlsZQ%3D%3D?line=8'>9</a>\u001b[0m selected_dim_reduction_method \u001b[39m=\u001b[39m \u001b[39mstr\u001b[39m(\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_3.ipynb#W2sZmlsZQ%3D%3D?line=9'>10</a>\u001b[0m \u001b[39minput\u001b[39m(\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_3.ipynb#W2sZmlsZQ%3D%3D?line=10'>11</a>\u001b[0m \u001b[39m\"\u001b[39m\u001b[39mEnter dimensionality reduction method - one of \u001b[39m\u001b[39m\"\u001b[39m\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_3.ipynb#W2sZmlsZQ%3D%3D?line=11'>12</a>\u001b[0m \u001b[39m+\u001b[39m \u001b[39mstr\u001b[39m(\u001b[39mlist\u001b[39m(valid_dim_reduction_methods\u001b[39m.\u001b[39mkeys()))\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_3.ipynb#W2sZmlsZQ%3D%3D?line=12'>13</a>\u001b[0m )\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_3.ipynb#W2sZmlsZQ%3D%3D?line=13'>14</a>\u001b[0m )\n\u001b[1;32m---> <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_3.ipynb#W2sZmlsZQ%3D%3D?line=15'>16</a>\u001b[0m extract_latent_semantics(\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_3.ipynb#W2sZmlsZQ%3D%3D?line=16'>17</a>\u001b[0m fd_collection,\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_3.ipynb#W2sZmlsZQ%3D%3D?line=17'>18</a>\u001b[0m k,\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_3.ipynb#W2sZmlsZQ%3D%3D?line=18'>19</a>\u001b[0m selected_feature_model,\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_3.ipynb#W2sZmlsZQ%3D%3D?line=19'>20</a>\u001b[0m selected_dim_reduction_method,\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_3.ipynb#W2sZmlsZQ%3D%3D?line=20'>21</a>\u001b[0m top_images\u001b[39m=\u001b[39;49m\u001b[39m10\u001b[39;49m,\n\u001b[0;32m <a href='vscode-notebook-cell:/c%3A/Kaushik/ASU/CSE%20515%20-%20Multimedia%20and%20Web%20Databases/Project/Phase%202/task_3.ipynb#W2sZmlsZQ%3D%3D?line=21'>22</a>\u001b[0m )\n",
|
||||||
|
"File \u001b[1;32mc:\\Kaushik\\ASU\\CSE 515 - Multimedia and Web Databases\\Project\\Phase 2\\utils.py:674\u001b[0m, in \u001b[0;36mextract_latent_semantics\u001b[1;34m(fd_collection, k, feature_model, dim_reduction_method, top_images)\u001b[0m\n\u001b[0;32m 669\u001b[0m \u001b[39m# unsupervised LDA to extract topics (Latent Dirichlet Allocation)\u001b[39;00m\n\u001b[0;32m 670\u001b[0m \u001b[39m# Note: LDA takes a bit of time\u001b[39;00m\n\u001b[0;32m 671\u001b[0m \u001b[39mcase\u001b[39;00m \u001b[39m3\u001b[39m:\n\u001b[0;32m 672\u001b[0m \u001b[39m# LDA requires non-negative input data\u001b[39;00m\n\u001b[0;32m 673\u001b[0m \u001b[39m# so shift the input by subtracting the smallest value\u001b[39;00m\n\u001b[1;32m--> 674\u001b[0m min_value \u001b[39m=\u001b[39m np\u001b[39m.\u001b[39mmin(feature_vectors)\n\u001b[0;32m 675\u001b[0m feature_vectors_shifted \u001b[39m=\u001b[39m feature_vectors \u001b[39m-\u001b[39m min_value\n\u001b[0;32m 677\u001b[0m model \u001b[39m=\u001b[39m LatentDirichletAllocation(n_components\u001b[39m=\u001b[39mk, learning_method\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39monline\u001b[39m\u001b[39m\"\u001b[39m, verbose\u001b[39m=\u001b[39m\u001b[39m4\u001b[39m)\n",
|
||||||
|
"File \u001b[1;32mc:\\Users\\rknar\\.pyenv\\pyenv-win\\versions\\3.10.5\\lib\\site-packages\\sklearn\\base.py:1151\u001b[0m, in \u001b[0;36m_fit_context.<locals>.decorator.<locals>.wrapper\u001b[1;34m(estimator, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1144\u001b[0m estimator\u001b[39m.\u001b[39m_validate_params()\n\u001b[0;32m 1146\u001b[0m \u001b[39mwith\u001b[39;00m config_context(\n\u001b[0;32m 1147\u001b[0m skip_parameter_validation\u001b[39m=\u001b[39m(\n\u001b[0;32m 1148\u001b[0m prefer_skip_nested_validation \u001b[39mor\u001b[39;00m global_skip_validation\n\u001b[0;32m 1149\u001b[0m )\n\u001b[0;32m 1150\u001b[0m ):\n\u001b[1;32m-> 1151\u001b[0m \u001b[39mreturn\u001b[39;00m fit_method(estimator, \u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n",
|
||||||
|
"File \u001b[1;32mc:\\Users\\rknar\\.pyenv\\pyenv-win\\versions\\3.10.5\\lib\\site-packages\\sklearn\\decomposition\\_lda.py:665\u001b[0m, in \u001b[0;36mLatentDirichletAllocation.fit\u001b[1;34m(self, X, y)\u001b[0m\n\u001b[0;32m 663\u001b[0m \u001b[39mif\u001b[39;00m learning_method \u001b[39m==\u001b[39m \u001b[39m\"\u001b[39m\u001b[39monline\u001b[39m\u001b[39m\"\u001b[39m:\n\u001b[0;32m 664\u001b[0m \u001b[39mfor\u001b[39;00m idx_slice \u001b[39min\u001b[39;00m gen_batches(n_samples, batch_size):\n\u001b[1;32m--> 665\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_em_step(\n\u001b[0;32m 666\u001b[0m X[idx_slice, :],\n\u001b[0;32m 667\u001b[0m total_samples\u001b[39m=\u001b[39;49mn_samples,\n\u001b[0;32m 668\u001b[0m batch_update\u001b[39m=\u001b[39;49m\u001b[39mFalse\u001b[39;49;00m,\n\u001b[0;32m 669\u001b[0m parallel\u001b[39m=\u001b[39;49mparallel,\n\u001b[0;32m 670\u001b[0m )\n\u001b[0;32m 671\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m 672\u001b[0m \u001b[39m# batch update\u001b[39;00m\n\u001b[0;32m 673\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_em_step(\n\u001b[0;32m 674\u001b[0m X, total_samples\u001b[39m=\u001b[39mn_samples, batch_update\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m, parallel\u001b[39m=\u001b[39mparallel\n\u001b[0;32m 675\u001b[0m )\n",
|
||||||
|
"File \u001b[1;32mc:\\Users\\rknar\\.pyenv\\pyenv-win\\versions\\3.10.5\\lib\\site-packages\\sklearn\\decomposition\\_lda.py:524\u001b[0m, in \u001b[0;36mLatentDirichletAllocation._em_step\u001b[1;34m(self, X, total_samples, batch_update, parallel)\u001b[0m\n\u001b[0;32m 497\u001b[0m \u001b[39m\u001b[39m\u001b[39m\"\"\"EM update for 1 iteration.\u001b[39;00m\n\u001b[0;32m 498\u001b[0m \n\u001b[0;32m 499\u001b[0m \u001b[39mupdate `_component` by batch VB or online VB.\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 520\u001b[0m \u001b[39m Unnormalized document topic distribution.\u001b[39;00m\n\u001b[0;32m 521\u001b[0m \u001b[39m\"\"\"\u001b[39;00m\n\u001b[0;32m 523\u001b[0m \u001b[39m# E-step\u001b[39;00m\n\u001b[1;32m--> 524\u001b[0m _, suff_stats \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_e_step(\n\u001b[0;32m 525\u001b[0m X, cal_sstats\u001b[39m=\u001b[39;49m\u001b[39mTrue\u001b[39;49;00m, random_init\u001b[39m=\u001b[39;49m\u001b[39mTrue\u001b[39;49;00m, parallel\u001b[39m=\u001b[39;49mparallel\n\u001b[0;32m 526\u001b[0m )\n\u001b[0;32m 528\u001b[0m \u001b[39m# M-step\u001b[39;00m\n\u001b[0;32m 529\u001b[0m \u001b[39mif\u001b[39;00m batch_update:\n",
|
||||||
|
"File \u001b[1;32mc:\\Users\\rknar\\.pyenv\\pyenv-win\\versions\\3.10.5\\lib\\site-packages\\sklearn\\decomposition\\_lda.py:467\u001b[0m, in \u001b[0;36mLatentDirichletAllocation._e_step\u001b[1;34m(self, X, cal_sstats, random_init, parallel)\u001b[0m\n\u001b[0;32m 465\u001b[0m \u001b[39mif\u001b[39;00m parallel \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[0;32m 466\u001b[0m parallel \u001b[39m=\u001b[39m Parallel(n_jobs\u001b[39m=\u001b[39mn_jobs, verbose\u001b[39m=\u001b[39m\u001b[39mmax\u001b[39m(\u001b[39m0\u001b[39m, \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mverbose \u001b[39m-\u001b[39m \u001b[39m1\u001b[39m))\n\u001b[1;32m--> 467\u001b[0m results \u001b[39m=\u001b[39m parallel(\n\u001b[0;32m 468\u001b[0m delayed(_update_doc_distribution)(\n\u001b[0;32m 469\u001b[0m X[idx_slice, :],\n\u001b[0;32m 470\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mexp_dirichlet_component_,\n\u001b[0;32m 471\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mdoc_topic_prior_,\n\u001b[0;32m 472\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mmax_doc_update_iter,\n\u001b[0;32m 473\u001b[0m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mmean_change_tol,\n\u001b[0;32m 474\u001b[0m cal_sstats,\n\u001b[0;32m 475\u001b[0m random_state,\n\u001b[0;32m 476\u001b[0m )\n\u001b[0;32m 477\u001b[0m \u001b[39mfor\u001b[39;49;00m idx_slice \u001b[39min\u001b[39;49;00m gen_even_slices(X\u001b[39m.\u001b[39;49mshape[\u001b[39m0\u001b[39;49m], n_jobs)\n\u001b[0;32m 478\u001b[0m )\n\u001b[0;32m 480\u001b[0m \u001b[39m# merge result\u001b[39;00m\n\u001b[0;32m 481\u001b[0m doc_topics, sstats_list \u001b[39m=\u001b[39m \u001b[39mzip\u001b[39m(\u001b[39m*\u001b[39mresults)\n",
|
||||||
|
"File \u001b[1;32mc:\\Users\\rknar\\.pyenv\\pyenv-win\\versions\\3.10.5\\lib\\site-packages\\sklearn\\utils\\parallel.py:65\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[1;34m(self, iterable)\u001b[0m\n\u001b[0;32m 60\u001b[0m config \u001b[39m=\u001b[39m get_config()\n\u001b[0;32m 61\u001b[0m iterable_with_config \u001b[39m=\u001b[39m (\n\u001b[0;32m 62\u001b[0m (_with_config(delayed_func, config), args, kwargs)\n\u001b[0;32m 63\u001b[0m \u001b[39mfor\u001b[39;00m delayed_func, args, kwargs \u001b[39min\u001b[39;00m iterable\n\u001b[0;32m 64\u001b[0m )\n\u001b[1;32m---> 65\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39msuper\u001b[39;49m()\u001b[39m.\u001b[39;49m\u001b[39m__call__\u001b[39;49m(iterable_with_config)\n",
|
||||||
|
"File \u001b[1;32mc:\\Users\\rknar\\.pyenv\\pyenv-win\\versions\\3.10.5\\lib\\site-packages\\joblib\\parallel.py:1863\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[1;34m(self, iterable)\u001b[0m\n\u001b[0;32m 1861\u001b[0m output \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_get_sequential_output(iterable)\n\u001b[0;32m 1862\u001b[0m \u001b[39mnext\u001b[39m(output)\n\u001b[1;32m-> 1863\u001b[0m \u001b[39mreturn\u001b[39;00m output \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mreturn_generator \u001b[39melse\u001b[39;00m \u001b[39mlist\u001b[39;49m(output)\n\u001b[0;32m 1865\u001b[0m \u001b[39m# Let's create an ID that uniquely identifies the current call. If the\u001b[39;00m\n\u001b[0;32m 1866\u001b[0m \u001b[39m# call is interrupted early and that the same instance is immediately\u001b[39;00m\n\u001b[0;32m 1867\u001b[0m \u001b[39m# re-used, this id will be used to prevent workers that were\u001b[39;00m\n\u001b[0;32m 1868\u001b[0m \u001b[39m# concurrently finalizing a task from the previous call to run the\u001b[39;00m\n\u001b[0;32m 1869\u001b[0m \u001b[39m# callback.\u001b[39;00m\n\u001b[0;32m 1870\u001b[0m \u001b[39mwith\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_lock:\n",
|
||||||
|
"File \u001b[1;32mc:\\Users\\rknar\\.pyenv\\pyenv-win\\versions\\3.10.5\\lib\\site-packages\\joblib\\parallel.py:1792\u001b[0m, in \u001b[0;36mParallel._get_sequential_output\u001b[1;34m(self, iterable)\u001b[0m\n\u001b[0;32m 1790\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mn_dispatched_batches \u001b[39m+\u001b[39m\u001b[39m=\u001b[39m \u001b[39m1\u001b[39m\n\u001b[0;32m 1791\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mn_dispatched_tasks \u001b[39m+\u001b[39m\u001b[39m=\u001b[39m \u001b[39m1\u001b[39m\n\u001b[1;32m-> 1792\u001b[0m res \u001b[39m=\u001b[39m func(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n\u001b[0;32m 1793\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mn_completed_tasks \u001b[39m+\u001b[39m\u001b[39m=\u001b[39m \u001b[39m1\u001b[39m\n\u001b[0;32m 1794\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mprint_progress()\n",
|
||||||
|
"File \u001b[1;32mc:\\Users\\rknar\\.pyenv\\pyenv-win\\versions\\3.10.5\\lib\\site-packages\\sklearn\\utils\\parallel.py:127\u001b[0m, in \u001b[0;36m_FuncWrapper.__call__\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 125\u001b[0m config \u001b[39m=\u001b[39m {}\n\u001b[0;32m 126\u001b[0m \u001b[39mwith\u001b[39;00m config_context(\u001b[39m*\u001b[39m\u001b[39m*\u001b[39mconfig):\n\u001b[1;32m--> 127\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mfunction(\u001b[39m*\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n",
|
||||||
|
"File \u001b[1;32mc:\\Users\\rknar\\.pyenv\\pyenv-win\\versions\\3.10.5\\lib\\site-packages\\sklearn\\decomposition\\_lda.py:144\u001b[0m, in \u001b[0;36m_update_doc_distribution\u001b[1;34m(X, exp_topic_word_distr, doc_topic_prior, max_doc_update_iter, mean_change_tol, cal_sstats, random_state)\u001b[0m\n\u001b[0;32m 140\u001b[0m last_d \u001b[39m=\u001b[39m doc_topic_d\n\u001b[0;32m 142\u001b[0m \u001b[39m# The optimal phi_{dwk} is proportional to\u001b[39;00m\n\u001b[0;32m 143\u001b[0m \u001b[39m# exp(E[log(theta_{dk})]) * exp(E[log(beta_{dw})]).\u001b[39;00m\n\u001b[1;32m--> 144\u001b[0m norm_phi \u001b[39m=\u001b[39m np\u001b[39m.\u001b[39;49mdot(exp_doc_topic_d, exp_topic_word_d) \u001b[39m+\u001b[39m eps\n\u001b[0;32m 146\u001b[0m doc_topic_d \u001b[39m=\u001b[39m exp_doc_topic_d \u001b[39m*\u001b[39m np\u001b[39m.\u001b[39mdot(cnts \u001b[39m/\u001b[39m norm_phi, exp_topic_word_d\u001b[39m.\u001b[39mT)\n\u001b[0;32m 147\u001b[0m \u001b[39m# Note: adds doc_topic_prior to doc_topic_d, in-place.\u001b[39;00m\n",
|
||||||
|
"File \u001b[1;32m<__array_function__ internals>:180\u001b[0m, in \u001b[0;36mdot\u001b[1;34m(*args, **kwargs)\u001b[0m\n",
|
||||||
|
"\u001b[1;31mKeyboardInterrupt\u001b[0m: "
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
"source": [
|
"source": [
|
||||||
"def extractKLatentSemantics(k, feature_model, dim_reduction):\n",
|
"selected_feature_model = valid_feature_models[\n",
|
||||||
|
" str(input(\"Enter feature model - one of \" + str(list(valid_feature_models.keys()))))\n",
|
||||||
|
"]\n",
|
||||||
"\n",
|
"\n",
|
||||||
" feature_vectors = [x[feature_model] for x in feature_descriptors if x[\"_id\"] % 2 == 0]\n",
|
"k = int(input(\"Enter value of k: \"))\n",
|
||||||
" feature_labels = [x[\"label\"] for x in feature_descriptors if x[\"_id\"] % 2 == 0]\n",
|
"if k < 1:\n",
|
||||||
" feature_ids = [x[\"_id\"] for x in feature_descriptors if x[\"_id\"] % 2 == 0]\n",
|
" raise ValueError(\"k should be a positive integer\")\n",
|
||||||
"\n",
|
"\n",
|
||||||
" filename = ''\n",
|
"selected_dim_reduction_method = str(\n",
|
||||||
|
" input(\n",
|
||||||
|
" \"Enter dimensionality reduction method - one of \"\n",
|
||||||
|
" + str(list(valid_dim_reduction_methods.keys()))\n",
|
||||||
|
" )\n",
|
||||||
|
")\n",
|
||||||
"\n",
|
"\n",
|
||||||
"\n",
|
"extract_latent_semantics(\n",
|
||||||
" match dim_reduction:\n",
|
" fd_collection,\n",
|
||||||
"\n",
|
" k,\n",
|
||||||
" case 1:\n",
|
" selected_feature_model,\n",
|
||||||
" filename = f'{feature_model}-svd-semantics.json'\n",
|
" selected_dim_reduction_method,\n",
|
||||||
" U, S, Vh = scipy.sparse.linalg.svds(np.array(feature_vectors), k=k)\n",
|
" top_images=10,\n",
|
||||||
" k_latent_semantics = sorted(list(zip(feature_ids, U.tolist())), key = lambda x: x[1][0], reverse = True)\n",
|
")\n"
|
||||||
"\n",
|
|
||||||
" case 2:\n",
|
|
||||||
" filename = f'{feature_model}-nnmf-semantics.json'\n",
|
|
||||||
" model = NMF(n_components = k, init = 'random', solver = 'cd', alpha_H = 0.01, alpha_W = 0.01, max_iter = 10000)\n",
|
|
||||||
" min_value = np.min(feature_vectors)\n",
|
|
||||||
" feature_vectors_shifted = feature_vectors - min_value\n",
|
|
||||||
" U = model.fit_transform(np.array(feature_vectors_shifted))\n",
|
|
||||||
" k_latent_semantics = sorted(list(zip(feature_ids, U.tolist())), key = lambda x: x[1][0], reverse = True)\n",
|
|
||||||
"\n",
|
|
||||||
" case 3:\n",
|
|
||||||
" filename = f'{feature_model}-lda-semantics.json'\n",
|
|
||||||
" U = LinearDiscriminantAnalysis(n_components = k).fit_transform(feature_vectors, feature_labels)\n",
|
|
||||||
" k_latent_semantics = sorted(list(zip(feature_ids, U.tolist())), key = lambda x: x[1][0], reverse = True)\n",
|
|
||||||
"\n",
|
|
||||||
" case 4:\n",
|
|
||||||
" filename = f'{feature_model}-kmeans-semantics.json'\n",
|
|
||||||
" kmeans = KMeans(n_clusters = k)\n",
|
|
||||||
" kmeans.fit(feature_vectors)\n",
|
|
||||||
" U = kmeans.transform(feature_vectors)\n",
|
|
||||||
" k_latent_semantics = sorted(list(zip(feature_ids, U.tolist())), key = lambda x: x[1][0], reverse = True)\n",
|
|
||||||
" \n",
|
|
||||||
" k_latent_semantics = [{\"_id\": item[0], \"semantics\": item[1]} for item in k_latent_semantics]\n",
|
|
||||||
" with open(filename, 'w', encoding='utf-8') as f:\n",
|
|
||||||
" json.dump(k_latent_semantics, f, ensure_ascii = False)\n"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": null,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"def main():\n",
|
|
||||||
"\n",
|
|
||||||
" # Load dataset\n",
|
|
||||||
"\n",
|
|
||||||
" # User input for Image ID\n",
|
|
||||||
" k = int(input(\"Enter k: \"))\n",
|
|
||||||
"\n",
|
|
||||||
" features = ['color_moments', 'hog', 'layer3', 'avgpool', 'fc']\n",
|
|
||||||
"\n",
|
|
||||||
" # User input for feature model to extract\n",
|
|
||||||
" print(\"\\n1: Color moments\")\n",
|
|
||||||
" print(\"2: HOG\")\n",
|
|
||||||
" print(\"3: Resnet50 Avgpool layer\")\n",
|
|
||||||
" print(\"4: Resnet50 Layer 3\")\n",
|
|
||||||
" print(\"5: Resnet50 FC layer\")\n",
|
|
||||||
" feature_model = features[int(input(\"Select the feature model: \")) - 1]\n",
|
|
||||||
"\n",
|
|
||||||
" print(\"\\n1. SVD\")\n",
|
|
||||||
" print(\"2. NNMF\")\n",
|
|
||||||
" print(\"3. LDA\")\n",
|
|
||||||
" print(\"4. k-means\")\n",
|
|
||||||
" dim_reduction = int(input(\"Select the dimensionality reduction technique: \"))\n",
|
|
||||||
"\n",
|
|
||||||
" extractKLatentSemantics(k, feature_model, dim_reduction)"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"cell_type": "code",
|
|
||||||
"execution_count": null,
|
|
||||||
"metadata": {},
|
|
||||||
"outputs": [],
|
|
||||||
"source": [
|
|
||||||
"if __name__ == \"__main__\":\n",
|
|
||||||
" main()"
|
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
@ -133,8 +89,22 @@
|
|||||||
}
|
}
|
||||||
],
|
],
|
||||||
"metadata": {
|
"metadata": {
|
||||||
|
"kernelspec": {
|
||||||
|
"display_name": "Python 3",
|
||||||
|
"language": "python",
|
||||||
|
"name": "python3"
|
||||||
|
},
|
||||||
"language_info": {
|
"language_info": {
|
||||||
"name": "python"
|
"codemirror_mode": {
|
||||||
|
"name": "ipython",
|
||||||
|
"version": 3
|
||||||
|
},
|
||||||
|
"file_extension": ".py",
|
||||||
|
"mimetype": "text/x-python",
|
||||||
|
"name": "python",
|
||||||
|
"nbconvert_exporter": "python",
|
||||||
|
"pygments_lexer": "ipython3",
|
||||||
|
"version": "3.10.5"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"nbformat": 4,
|
"nbformat": 4,
|
||||||
|
|||||||
154
Phase 2/utils.py
154
Phase 2/utils.py
@ -4,6 +4,11 @@ import math
|
|||||||
import cv2
|
import cv2
|
||||||
import numpy as np
|
import numpy as np
|
||||||
from scipy.stats import pearsonr
|
from scipy.stats import pearsonr
|
||||||
|
from scipy.sparse.linalg import svds
|
||||||
|
from sklearn.decomposition import NMF
|
||||||
|
from sklearn.decomposition import LatentDirichletAllocation
|
||||||
|
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
|
||||||
|
from sklearn.cluster import KMeans
|
||||||
|
|
||||||
# Torch
|
# Torch
|
||||||
import torch
|
import torch
|
||||||
@ -12,6 +17,7 @@ from torchvision.datasets import Caltech101
|
|||||||
from torchvision.models import resnet50, ResNet50_Weights
|
from torchvision.models import resnet50, ResNet50_Weights
|
||||||
|
|
||||||
# OS and env
|
# OS and env
|
||||||
|
import json
|
||||||
from os import getenv
|
from os import getenv
|
||||||
from dotenv import load_dotenv
|
from dotenv import load_dotenv
|
||||||
import warnings
|
import warnings
|
||||||
@ -566,3 +572,151 @@ def show_similar_images_for_label(
|
|||||||
f"Plots/Label_{target_label}_{feature_model}_{distance_measure.__name__}_k{k}.png"
|
f"Plots/Label_{target_label}_{feature_model}_{distance_measure.__name__}_k{k}.png"
|
||||||
)
|
)
|
||||||
plt.show()
|
plt.show()
|
||||||
|
|
||||||
|
|
||||||
|
valid_dim_reduction_methods = {
|
||||||
|
"svd": 1,
|
||||||
|
"nmf": 2,
|
||||||
|
"lda": 3,
|
||||||
|
"kmeans": 4,
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def extract_latent_semantics(
|
||||||
|
fd_collection, k, feature_model, dim_reduction_method, top_images=None
|
||||||
|
):
|
||||||
|
"""
|
||||||
|
Extract latent semantics for entire collection at once for a given feature_model and dim_reduction_method, and display the imageID-semantic weight pairs
|
||||||
|
|
||||||
|
Leave `top_images` blank to display all imageID-weight pairs
|
||||||
|
"""
|
||||||
|
|
||||||
|
assert (
|
||||||
|
feature_model in valid_feature_models.values()
|
||||||
|
), "feature_model should be one of " + str(list(valid_feature_models.keys()))
|
||||||
|
assert (
|
||||||
|
dim_reduction_method in valid_dim_reduction_methods.keys()
|
||||||
|
), "dim_reduction_method should be one of " + str(
|
||||||
|
list(valid_dim_reduction_methods.keys())
|
||||||
|
)
|
||||||
|
|
||||||
|
all_images = list(fd_collection.find())
|
||||||
|
feature_vectors = np.array([img[feature_model] for img in all_images])
|
||||||
|
feature_labels = [img["true_label"] for img in all_images]
|
||||||
|
feature_ids = [img["image_id"] for img in all_images]
|
||||||
|
|
||||||
|
top_img_str = ""
|
||||||
|
if top_images is not None:
|
||||||
|
top_img_str = f" (showing only top {top_images} image-weight pairs for each latent semantic)"
|
||||||
|
print(
|
||||||
|
"Applying {} on the {} space to get {} latent semantics{}...".format(
|
||||||
|
dim_reduction_method, feature_model, k, top_img_str
|
||||||
|
)
|
||||||
|
)
|
||||||
|
|
||||||
|
displayed_latent_semantics = {}
|
||||||
|
all_latent_semantics = {}
|
||||||
|
|
||||||
|
match valid_dim_reduction_methods[dim_reduction_method]:
|
||||||
|
# singular value decomposition
|
||||||
|
# sparse version of SVD to get only k singular values
|
||||||
|
case 1:
|
||||||
|
U, S, V_T = svds(feature_vectors, k=k)
|
||||||
|
|
||||||
|
all_latent_semantics = {
|
||||||
|
"image-semantic": U.tolist(),
|
||||||
|
"semantics-core": S.tolist(),
|
||||||
|
"semantic-feature": V_T.tolist(),
|
||||||
|
}
|
||||||
|
|
||||||
|
# for each latent semantic, sort imageID-weight pairs by weights in descending order
|
||||||
|
displayed_latent_semantics = [
|
||||||
|
sorted(
|
||||||
|
list(zip(feature_ids, latent_semantic)),
|
||||||
|
key=lambda x: x[1],
|
||||||
|
reverse=True,
|
||||||
|
)[:top_images]
|
||||||
|
for latent_semantic in U.T
|
||||||
|
]
|
||||||
|
|
||||||
|
# non-negative matrix factorization
|
||||||
|
case 2:
|
||||||
|
# NNMF requires non-negative input data
|
||||||
|
# so shift the input by subtracting the smallest value
|
||||||
|
min_value = np.min(feature_vectors)
|
||||||
|
feature_vectors_shifted = feature_vectors - min_value
|
||||||
|
|
||||||
|
model = NMF(
|
||||||
|
n_components=k,
|
||||||
|
init="random",
|
||||||
|
solver="cd",
|
||||||
|
alpha_H=0.01,
|
||||||
|
alpha_W=0.01,
|
||||||
|
max_iter=10000,
|
||||||
|
)
|
||||||
|
model.fit(feature_vectors_shifted)
|
||||||
|
|
||||||
|
W = model.transform(feature_vectors_shifted)
|
||||||
|
H = model.components_
|
||||||
|
|
||||||
|
all_latent_semantics = {"image-semantic": W, "semantic-feature": H}
|
||||||
|
|
||||||
|
# for each latent semantic, sort imageID-weight pairs by weights in descending order
|
||||||
|
displayed_latent_semantics = [
|
||||||
|
sorted(
|
||||||
|
list(zip(feature_ids, latent_semantic)),
|
||||||
|
key=lambda x: x[1],
|
||||||
|
reverse=True,
|
||||||
|
)[:top_images]
|
||||||
|
for latent_semantic in W.T
|
||||||
|
]
|
||||||
|
|
||||||
|
# unsupervised LDA to extract topics (Latent Dirichlet Allocation)
|
||||||
|
# Note: LDA takes a bit of time
|
||||||
|
case 3:
|
||||||
|
# LDA requires non-negative input data
|
||||||
|
# so shift the input by subtracting the smallest value
|
||||||
|
min_value = np.min(feature_vectors)
|
||||||
|
feature_vectors_shifted = feature_vectors - min_value
|
||||||
|
|
||||||
|
model = LatentDirichletAllocation(
|
||||||
|
n_components=k, learning_method="online", verbose=4
|
||||||
|
)
|
||||||
|
model.fit(feature_vectors_shifted)
|
||||||
|
|
||||||
|
# K (k x fd_dim) is the factor matrix for latent semantic-feature pairs
|
||||||
|
K = model.components_
|
||||||
|
# X (4339 x k) is the other factor matrix for image ID-latent semantic pairs
|
||||||
|
X = model.transform(feature_vectors_shifted)
|
||||||
|
|
||||||
|
all_latent_semantics = {"image-semantic": X, "semantic-feature": K}
|
||||||
|
|
||||||
|
# for each latent semantic, sort imageID-weight pairs by weights in descending order
|
||||||
|
displayed_latent_semantics = [
|
||||||
|
sorted(
|
||||||
|
list(zip(feature_ids, latent_semantic)),
|
||||||
|
key=lambda x: x[1],
|
||||||
|
reverse=True,
|
||||||
|
)[:top_images]
|
||||||
|
for latent_semantic in X.T
|
||||||
|
]
|
||||||
|
|
||||||
|
# k-means clustering to reduce to k clusters/dimensions
|
||||||
|
case 4:
|
||||||
|
model = KMeans(n_clusters=k).fit(feature_vectors)
|
||||||
|
CC = model.cluster_centers_
|
||||||
|
U = model.transform(feature_vectors)
|
||||||
|
|
||||||
|
all_latent_semantics = {"image-semantic": U, "semantic_feature": CC}
|
||||||
|
|
||||||
|
for idx, latent_semantic in enumerate(displayed_latent_semantics):
|
||||||
|
print(f"Latent semantic no. {idx}")
|
||||||
|
for image_id, weight in latent_semantic:
|
||||||
|
print(f"Image_ID\t{image_id}\t-\tWeight\t{weight}")
|
||||||
|
|
||||||
|
with open(
|
||||||
|
f"{feature_model}-{dim_reduction_method}-{k}-semantics.json",
|
||||||
|
"w",
|
||||||
|
encoding="utf-8",
|
||||||
|
) as output_file:
|
||||||
|
json.dump(all_latent_semantics, output_file, ensure_ascii=False)
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user