my-asu-archive/CSE515_MWDB_Project
1
0
Fork 0
mirror of https://github.com/20kaushik02/CSE515_MWDB_Project.git synced 2025-12-06 09:24:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' of https://github.com/20kaushik02/CSE515_MWDB_Project into task9

Browse Source
This commit is contained in:
pranavbrkr 2023-10-13 11:32:41 -07:00
commit 950d4237b3
5 changed files with 158 additions and 174 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
Phase 2/requirements.txt
View File

@ -11,3 +11,4 @@ ipython
notebook
ipykernel
python-dotenv
tensorly

52
Phase 2/task_4.ipynb Normal file
View File

@ -0,0 +1,52 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from utils import *\n",
"warnings.filterwarnings('ignore')\n",
"%matplotlib inline\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"fd_collection = getCollection(\"team_5_mwdb_phase_2\", \"fd_collection\")\n"
]
},
{
"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": "3.10.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}

64
Phase 2/task_4.py Normal file
View File

@ -0,0 +1,64 @@
import json
import tensorly as tl
import numpy as np
from pymongo import MongoClient
from phase1_mongodb import *
client = MongoClient()
client = MongoClient(host="localhost", port=27017)
# Select the database
db = client.Multimedia_Web_DBs
caltechDataset = loadDataset()
num_labels = 101
# Fetch all documents from the collection and then sort them by "_id"
feature_descriptors = list(db.Feature_Descriptors.find({}))
feature_descriptors = sorted(list(db.Feature_Descriptors.find({})), key=lambda x: x["_id"], reverse=False)
label_ids = [x["label"] for x in feature_descriptors]
def compute_cp_decomposition(feature_model, rank):
label_vectors = [(x["label"], x[feature_model]) for x in feature_descriptors if x["_id"] % 2 == 0]
num_labels = 101
tensor_shape = (len(label_vectors), len(feature_descriptors[0][feature_model]), num_labels)
tensor = np.zeros(tensor_shape)
for id in range(len(label_vectors)):
label = label_vectors[id][0]
tensor[id, :, label] = label_vectors[id][1]
weights, factors = tl.decomposition.parafac(tensor, rank=rank, normalize_factors=True)
return weights, factors
def main():
# Step 4: Perform CP-decomposition (parafac) to extract latent semantics
features = ['color_moments', 'hog', 'layer3', 'avgpool', 'fc']
# User input for feature model to extract
print("1: Color moments")
print("2: HOG")
print("3: Resnet50 Avgpool layer")
print("4: Resnet50 Layer 3")
print("5: Resnet50 FC layer")
feature_model = features[int(input("Select the feature model: ")) - 1]
k = int(input("Enter k: "))
weights, factors = compute_cp_decomposition(feature_model, k)
k_latent_semantics = list(zip(label_ids, factors[0].tolist()))
k_latent_semantics_display = sorted(list(zip(label_ids, factors[0].tolist())), key = lambda x: x[1][0], reverse = True)
k_latent_semantics_display = [{"_id": item[0], "semantics": item[1]} for item in k_latent_semantics_display]
filename = f'{feature_model}-CP-semantics-{k}.json'
k_latent_semantics = [{"_id": item[0], "semantics": item[1]} for item in k_latent_semantics]
with open(filename, 'w', encoding='utf-8') as f:
json.dump(k_latent_semantics, f, ensure_ascii = False)
print(k_latent_semantics_display)
if __name__ == "__main__":
main()

160
Phase 2/task_5.ipynb
View File

@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 19,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -13,7 +13,7 @@
},
{
"cell_type": "code",
"execution_count": 20,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -22,159 +22,9 @@
},
{
"cell_type": "code",
"execution_count": 21,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Applying kmeans on the given similarity matrix to get 10 latent semantics (showing only top 10 label-weight pairs for each latent semantic)...\n",
"Initialized centroids\n",
"Iteration 0\n",
"Iteration 1\n",
"Iteration 2\n",
"Iteration 3\n",
"Iteration 4\n",
"Iteration 5\n",
"Iteration 6\n",
"Iteration 7\n",
"Iteration 8\n",
"Iteration 9\n",
"Iteration 10\n",
"Iteration 11\n",
"Iter 11 - Converged\n",
"Latent semantic no. 0\n",
"label\t84\t-\tWeight\t16.953715652557495\n",
"label\t34\t-\tWeight\t17.25164883471016\n",
"label\t1\t-\tWeight\t17.379970016799952\n",
"label\t72\t-\tWeight\t17.439397073433092\n",
"label\t32\t-\tWeight\t17.447297173030393\n",
"label\t31\t-\tWeight\t17.448932606262144\n",
"label\t40\t-\tWeight\t17.561159943630802\n",
"label\t79\t-\tWeight\t17.572813876633166\n",
"label\t5\t-\tWeight\t17.721278660592027\n",
"label\t56\t-\tWeight\t17.731177291838822\n",
"Latent semantic no. 1\n",
"label\t84\t-\tWeight\t19.27643729221191\n",
"label\t5\t-\tWeight\t19.449814613173483\n",
"label\t32\t-\tWeight\t19.684592406270944\n",
"label\t63\t-\tWeight\t19.911988624963808\n",
"label\t79\t-\tWeight\t19.930151237028223\n",
"label\t38\t-\tWeight\t19.948477661871497\n",
"label\t89\t-\tWeight\t19.965086791647906\n",
"label\t94\t-\tWeight\t19.990956583854018\n",
"label\t72\t-\tWeight\t19.99680017871235\n",
"label\t45\t-\tWeight\t20.058898160614795\n",
"Latent semantic no. 2\n",
"label\t0\t-\tWeight\tnan\n",
"label\t1\t-\tWeight\tnan\n",
"label\t2\t-\tWeight\tnan\n",
"label\t3\t-\tWeight\tnan\n",
"label\t4\t-\tWeight\tnan\n",
"label\t5\t-\tWeight\tnan\n",
"label\t6\t-\tWeight\tnan\n",
"label\t7\t-\tWeight\tnan\n",
"label\t8\t-\tWeight\tnan\n",
"label\t9\t-\tWeight\tnan\n",
"Latent semantic no. 3\n",
"label\t0\t-\tWeight\tnan\n",
"label\t1\t-\tWeight\tnan\n",
"label\t2\t-\tWeight\tnan\n",
"label\t3\t-\tWeight\tnan\n",
"label\t4\t-\tWeight\tnan\n",
"label\t5\t-\tWeight\tnan\n",
"label\t6\t-\tWeight\tnan\n",
"label\t7\t-\tWeight\tnan\n",
"label\t8\t-\tWeight\tnan\n",
"label\t9\t-\tWeight\tnan\n",
"Latent semantic no. 4\n",
"label\t32\t-\tWeight\t18.607843379925203\n",
"label\t89\t-\tWeight\t18.671771165930238\n",
"label\t84\t-\tWeight\t18.83858895833768\n",
"label\t79\t-\tWeight\t18.84775924713071\n",
"label\t55\t-\tWeight\t18.88614269359777\n",
"label\t34\t-\tWeight\t18.891433443455583\n",
"label\t11\t-\tWeight\t19.034715149675442\n",
"label\t63\t-\tWeight\t19.042445031693624\n",
"label\t5\t-\tWeight\t19.075471660855772\n",
"label\t59\t-\tWeight\t19.096232354525338\n",
"Latent semantic no. 5\n",
"label\t88\t-\tWeight\t17.332684081151356\n",
"label\t100\t-\tWeight\t17.414638052725692\n",
"label\t89\t-\tWeight\t17.64193670680817\n",
"label\t46\t-\tWeight\t17.663677856892257\n",
"label\t5\t-\tWeight\t17.750606635854105\n",
"label\t11\t-\tWeight\t17.921812162626082\n",
"label\t17\t-\tWeight\t17.99728875058849\n",
"label\t64\t-\tWeight\t18.20535869665654\n",
"label\t84\t-\tWeight\t18.280826365832894\n",
"label\t59\t-\tWeight\t18.48939095974247\n",
"Latent semantic no. 6\n",
"label\t0\t-\tWeight\tnan\n",
"label\t1\t-\tWeight\tnan\n",
"label\t2\t-\tWeight\tnan\n",
"label\t3\t-\tWeight\tnan\n",
"label\t4\t-\tWeight\tnan\n",
"label\t5\t-\tWeight\tnan\n",
"label\t6\t-\tWeight\tnan\n",
"label\t7\t-\tWeight\tnan\n",
"label\t8\t-\tWeight\tnan\n",
"label\t9\t-\tWeight\tnan\n",
"Latent semantic no. 7\n",
"label\t59\t-\tWeight\t19.676597202857955\n",
"label\t72\t-\tWeight\t19.687934144875545\n",
"label\t89\t-\tWeight\t19.830805124280474\n",
"label\t90\t-\tWeight\t20.021426354120276\n",
"label\t77\t-\tWeight\t20.05776182294002\n",
"label\t34\t-\tWeight\t20.058245159709028\n",
"label\t70\t-\tWeight\t20.117786048649382\n",
"label\t68\t-\tWeight\t20.139598145778074\n",
"label\t88\t-\tWeight\t20.185751240083068\n",
"label\t38\t-\tWeight\t20.208902223231863\n",
"Latent semantic no. 8\n",
"label\t0\t-\tWeight\tnan\n",
"label\t1\t-\tWeight\tnan\n",
"label\t2\t-\tWeight\tnan\n",
"label\t3\t-\tWeight\tnan\n",
"label\t4\t-\tWeight\tnan\n",
"label\t5\t-\tWeight\tnan\n",
"label\t6\t-\tWeight\tnan\n",
"label\t7\t-\tWeight\tnan\n",
"label\t8\t-\tWeight\tnan\n",
"label\t9\t-\tWeight\tnan\n",
"Latent semantic no. 9\n",
"label\t0\t-\tWeight\tnan\n",
"label\t1\t-\tWeight\tnan\n",
"label\t2\t-\tWeight\tnan\n",
"label\t3\t-\tWeight\tnan\n",
"label\t4\t-\tWeight\tnan\n",
"label\t5\t-\tWeight\tnan\n",
"label\t6\t-\tWeight\tnan\n",
"label\t7\t-\tWeight\tnan\n",
"label\t8\t-\tWeight\tnan\n",
"label\t9\t-\tWeight\tnan\n"
]
},
{
"ename": "TypeError",
"evalue": "Object of type ndarray is not JSON serializable",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32me:\\Fall 23\\CSE 515 - Multimedia and web databases\\CSE515_MWDB_Project\\Phase 2\\task_5.ipynb Cell 3\u001b[0m line \u001b[0;36m1\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/task_5.ipynb#W6sZmlsZQ%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:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task_5.ipynb#W6sZmlsZQ%3D%3D?line=9'>10</a>\u001b[0m \u001b[39minput\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/task_5.ipynb#W6sZmlsZQ%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:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task_5.ipynb#W6sZmlsZQ%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:/e%3A/Fall%2023/CSE%20515%20-%20Multimedia%20and%20web%20databases/CSE515_MWDB_Project/Phase%202/task_5.ipynb#W6sZmlsZQ%3D%3D?line=12'>13</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/task_5.ipynb#W6sZmlsZQ%3D%3D?line=13'>14</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/task_5.ipynb#W6sZmlsZQ%3D%3D?line=15'>16</a>\u001b[0m label_sim_matrix \u001b[39m=\u001b[39m find_label_label_similarity(fd_collection,selected_feature_model)\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/task_5.ipynb#W6sZmlsZQ%3D%3D?line=17'>18</a>\u001b[0m extract_latent_semantics_from_sim_matrix(\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/task_5.ipynb#W6sZmlsZQ%3D%3D?line=18'>19</a>\u001b[0m label_sim_matrix,\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/task_5.ipynb#W6sZmlsZQ%3D%3D?line=19'>20</a>\u001b[0m selected_feature_model,\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/task_5.ipynb#W6sZmlsZQ%3D%3D?line=20'>21</a>\u001b[0m \u001b[39m\"\u001b[39;49m\u001b[39mlabel\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/task_5.ipynb#W6sZmlsZQ%3D%3D?line=21'>22</a>\u001b[0m k,\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/task_5.ipynb#W6sZmlsZQ%3D%3D?line=22'>23</a>\u001b[0m selected_dim_reduction_method,\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/task_5.ipynb#W6sZmlsZQ%3D%3D?line=23'>24</a>\u001b[0m top_images\u001b[39m=\u001b[39;49m\u001b[39m10\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/task_5.ipynb#W6sZmlsZQ%3D%3D?line=24'>25</a>\u001b[0m )\n",
"File \u001b[1;32me:\\Fall 23\\CSE 515 - Multimedia and web databases\\CSE515_MWDB_Project\\Phase 2\\utils.py:1193\u001b[0m, in \u001b[0;36mextract_latent_semantics_from_sim_matrix\u001b[1;34m(sim_matrix, feature_model, sim_type, k, dim_reduction_method, top_images)\u001b[0m\n\u001b[0;32m 1187\u001b[0m \u001b[39mfor\u001b[39;00m label \u001b[39min\u001b[39;00m \u001b[39mrange\u001b[39m(num_labels):\n\u001b[0;32m 1188\u001b[0m \u001b[39m# get representative vectors for the label\u001b[39;00m\n\u001b[0;32m 1189\u001b[0m label_mean_vectors\u001b[39m.\u001b[39mappend(\n\u001b[0;32m 1190\u001b[0m calculate_label_representatives(fd_collection, label, feature_model)\n\u001b[0;32m 1191\u001b[0m )\n\u001b[1;32m-> 1193\u001b[0m label_sim_matrix \u001b[39m=\u001b[39m np\u001b[39m.\u001b[39mzeros((num_labels, num_labels))\n\u001b[0;32m 1195\u001b[0m \u001b[39m# Calculate half and fill the other\u001b[39;00m\n\u001b[0;32m 1196\u001b[0m \u001b[39mfor\u001b[39;00m i \u001b[39min\u001b[39;00m \u001b[39mrange\u001b[39m(num_labels):\n",
"File \u001b[1;32mc:\\Users\\Pranav\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\json\\__init__.py:179\u001b[0m, in \u001b[0;36mdump\u001b[1;34m(obj, fp, skipkeys, ensure_ascii, check_circular, allow_nan, cls, indent, separators, default, sort_keys, **kw)\u001b[0m\n\u001b[0;32m 173\u001b[0m iterable \u001b[39m=\u001b[39m \u001b[39mcls\u001b[39m(skipkeys\u001b[39m=\u001b[39mskipkeys, ensure_ascii\u001b[39m=\u001b[39mensure_ascii,\n\u001b[0;32m 174\u001b[0m check_circular\u001b[39m=\u001b[39mcheck_circular, allow_nan\u001b[39m=\u001b[39mallow_nan, indent\u001b[39m=\u001b[39mindent,\n\u001b[0;32m 175\u001b[0m separators\u001b[39m=\u001b[39mseparators,\n\u001b[0;32m 176\u001b[0m default\u001b[39m=\u001b[39mdefault, sort_keys\u001b[39m=\u001b[39msort_keys, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkw)\u001b[39m.\u001b[39miterencode(obj)\n\u001b[0;32m 177\u001b[0m \u001b[39m# could accelerate with writelines in some versions of Python, at\u001b[39;00m\n\u001b[0;32m 178\u001b[0m \u001b[39m# a debuggability cost\u001b[39;00m\n\u001b[1;32m--> 179\u001b[0m \u001b[39mfor\u001b[39;49;00m chunk \u001b[39min\u001b[39;49;00m iterable:\n\u001b[0;32m 180\u001b[0m fp\u001b[39m.\u001b[39;49mwrite(chunk)\n",
"File \u001b[1;32mc:\\Users\\Pranav\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\json\\encoder.py:432\u001b[0m, in \u001b[0;36m_make_iterencode.<locals>._iterencode\u001b[1;34m(o, _current_indent_level)\u001b[0m\n\u001b[0;32m 430\u001b[0m \u001b[39myield from\u001b[39;00m _iterencode_list(o, _current_indent_level)\n\u001b[0;32m 431\u001b[0m \u001b[39melif\u001b[39;00m \u001b[39misinstance\u001b[39m(o, \u001b[39mdict\u001b[39m):\n\u001b[1;32m--> 432\u001b[0m \u001b[39myield from\u001b[39;00m _iterencode_dict(o, _current_indent_level)\n\u001b[0;32m 433\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m 434\u001b[0m \u001b[39mif\u001b[39;00m markers \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n",
"File \u001b[1;32mc:\\Users\\Pranav\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\json\\encoder.py:406\u001b[0m, in \u001b[0;36m_make_iterencode.<locals>._iterencode_dict\u001b[1;34m(dct, _current_indent_level)\u001b[0m\n\u001b[0;32m 404\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m 405\u001b[0m chunks \u001b[39m=\u001b[39m _iterencode(value, _current_indent_level)\n\u001b[1;32m--> 406\u001b[0m \u001b[39myield from\u001b[39;00m chunks\n\u001b[0;32m 407\u001b[0m \u001b[39mif\u001b[39;00m newline_indent \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[0;32m 408\u001b[0m _current_indent_level \u001b[39m-\u001b[39m\u001b[39m=\u001b[39m \u001b[39m1\u001b[39m\n",
"File \u001b[1;32mc:\\Users\\Pranav\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\json\\encoder.py:326\u001b[0m, in \u001b[0;36m_make_iterencode.<locals>._iterencode_list\u001b[1;34m(lst, _current_indent_level)\u001b[0m\n\u001b[0;32m 324\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m 325\u001b[0m chunks \u001b[39m=\u001b[39m _iterencode(value, _current_indent_level)\n\u001b[1;32m--> 326\u001b[0m \u001b[39myield from\u001b[39;00m chunks\n\u001b[0;32m 327\u001b[0m \u001b[39mif\u001b[39;00m newline_indent \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[0;32m 328\u001b[0m _current_indent_level \u001b[39m-\u001b[39m\u001b[39m=\u001b[39m \u001b[39m1\u001b[39m\n",
"File \u001b[1;32mc:\\Users\\Pranav\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\json\\encoder.py:439\u001b[0m, in \u001b[0;36m_make_iterencode.<locals>._iterencode\u001b[1;34m(o, _current_indent_level)\u001b[0m\n\u001b[0;32m 437\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39m\"\u001b[39m\u001b[39mCircular reference detected\u001b[39m\u001b[39m\"\u001b[39m)\n\u001b[0;32m 438\u001b[0m markers[markerid] \u001b[39m=\u001b[39m o\n\u001b[1;32m--> 439\u001b[0m o \u001b[39m=\u001b[39m _default(o)\n\u001b[0;32m 440\u001b[0m \u001b[39myield from\u001b[39;00m _iterencode(o, _current_indent_level)\n\u001b[0;32m 441\u001b[0m \u001b[39mif\u001b[39;00m markers \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n",
"File \u001b[1;32mc:\\Users\\Pranav\\AppData\\Local\\Programs\\Python\\Python311\\Lib\\json\\encoder.py:180\u001b[0m, in \u001b[0;36mJSONEncoder.default\u001b[1;34m(self, o)\u001b[0m\n\u001b[0;32m 161\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mdefault\u001b[39m(\u001b[39mself\u001b[39m, o):\n\u001b[0;32m 162\u001b[0m \u001b[39m \u001b[39m\u001b[39m\"\"\"Implement this method in a subclass such that it returns\u001b[39;00m\n\u001b[0;32m 163\u001b[0m \u001b[39m a serializable object for ``o``, or calls the base implementation\u001b[39;00m\n\u001b[0;32m 164\u001b[0m \u001b[39m (to raise a ``TypeError``).\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 178\u001b[0m \n\u001b[0;32m 179\u001b[0m \u001b[39m \"\"\"\u001b[39;00m\n\u001b[1;32m--> 180\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mTypeError\u001b[39;00m(\u001b[39mf\u001b[39m\u001b[39m'\u001b[39m\u001b[39mObject of type \u001b[39m\u001b[39m{\u001b[39;00mo\u001b[39m.\u001b[39m\u001b[39m__class__\u001b[39m\u001b[39m.\u001b[39m\u001b[39m__name__\u001b[39m\u001b[39m}\u001b[39;00m\u001b[39m \u001b[39m\u001b[39m'\u001b[39m\n\u001b[0;32m 181\u001b[0m \u001b[39mf\u001b[39m\u001b[39m'\u001b[39m\u001b[39mis not JSON serializable\u001b[39m\u001b[39m'\u001b[39m)\n",
"\u001b[1;31mTypeError\u001b[0m: Object of type ndarray is not JSON serializable"
]
}
],
"outputs": [],
"source": [
"selected_feature_model = valid_feature_models[\n",
" str(input(\"Enter feature model - one of \" + str(list(valid_feature_models.keys()))))\n",
@ -200,7 +50,7 @@
" k,\n",
" selected_dim_reduction_method,\n",
" top_images=10,\n",
")\n"
")"
]
},
{

51
Phase 2/utils.py
View File

@ -18,6 +18,8 @@ import torchvision.transforms as transforms
from torchvision.datasets import Caltech101
from torchvision.models import resnet50, ResNet50_Weights
import tensorly as tl
# OS and env
import json
from os import getenv
@ -58,6 +60,8 @@ def loadDataset(dataset):
dataset = loadDataset(Caltech101)
NUM_LABELS = 101
NUM_IMAGES = 4339
class GridPartition:
@ -1054,7 +1058,7 @@ def extract_latent_semantics_from_sim_matrix(
"semantic-feature": V_T.tolist(),
}
# for each latent semantic, sort imageID-weight pairs by weights in descending order
# for each latent semantic, sort object-weight pairs by weights in descending order
displayed_latent_semantics = [
sorted(
list(zip(feature_ids, latent_semantic)),
@ -1089,7 +1093,7 @@ def extract_latent_semantics_from_sim_matrix(
"semantic-feature": H.tolist(),
}
# for each latent semantic, sort imageID-weight pairs by weights in descending order
# for each latent semantic, sort object-weight pairs by weights in descending order
displayed_latent_semantics = [
sorted(
list(zip(feature_ids, latent_semantic)),
@ -1122,7 +1126,7 @@ def extract_latent_semantics_from_sim_matrix(
"semantic-feature": K.tolist(),
}
# for each latent semantic, sort imageID-weight pairs by weights in descending order
# for each latent semantic, sort object-weight pairs by weights in descending order
displayed_latent_semantics = [
sorted(
list(zip(feature_ids, latent_semantic)),
@ -1140,10 +1144,10 @@ def extract_latent_semantics_from_sim_matrix(
all_latent_semantics = {
"image-semantic": Y.tolist(),
"semantic-feature": list(CC.values()),
"semantic-feature": CC.tolist(),
}
# for each latent semantic, sort imageID-weight pairs by weights in descending order
# for each latent semantic, sort object-weight pairs by weights in ascending order
displayed_latent_semantics = [
sorted(
list(zip(feature_ids, latent_semantic)),
@ -1152,9 +1156,8 @@ def extract_latent_semantics_from_sim_matrix(
)[:top_images]
for latent_semantic in Y.T
]
if valid_dim_reduction_methods[dim_reduction_method] == 4:
print("Note: for K-Means we display distances, in ascending order")
for idx, latent_semantic in enumerate(displayed_latent_semantics):
print(f"Latent semantic no. {idx}")
for obj_id, weight in latent_semantic:
@ -1185,19 +1188,17 @@ def find_label_label_similarity(fd_collection, feature_model):
label_sim_matrix = []
label_mean_vectors = []
num_labels = 101
for label in range(num_labels):
for label in range(NUM_LABELS):
# get representative vectors for the label
label_mean_vectors.append(
calculate_label_representatives(fd_collection, label, feature_model)
)
label_sim_matrix = np.zeros((num_labels, num_labels))
label_sim_matrix = np.zeros((NUM_LABELS, NUM_LABELS))
# Calculate half and fill the other
for i in range(num_labels):
for j in range(i + 1, num_labels):
for i in range(NUM_LABELS):
for j in range(i + 1, NUM_LABELS):
# Note: lower the value, lower the distance => higher the similarity
label_sim_matrix[i][j] = label_sim_matrix[j][i] = feature_distance_matches[
feature_model
@ -1219,14 +1220,30 @@ def find_image_image_similarity(fd_collection, feature_model):
).flatten() # get the specific feature model's feature vector
for img_fds in fd_collection.find() # repeat for all images
]
num_images = len(feature_vectors)
image_sim_matrix = np.zeros((num_images, num_images))
image_sim_matrix = np.zeros((NUM_IMAGES, NUM_IMAGES))
# Calculate half and fill the other
for i in range(num_images):
for j in range(i + 1, num_images):
for i in range(NUM_IMAGES):
for j in range(i + 1, NUM_IMAGES):
# Note: lower the value, lower the distance => higher the similarity
image_sim_matrix[i][j] = image_sim_matrix[j][i] = feature_distance_matches[
feature_model
](np.array(feature_vectors[i]), np.array(feature_vectors[j]))
return image_sim_matrix
def compute_cp_decomposition(fd_collection, feature_model, rank):
assert (
feature_model in valid_feature_models.values()
), "feature_model should be one of " + str(list(valid_feature_models.keys()))
all_images = list(fd_collection.find())
# (images, features, labels)
data_tensor_shape = (NUM_IMAGES, len(all_images[0][feature_model]), NUM_LABELS)
data_tensor = np.zeros(data_tensor_shape)
for id in range(NUM_IMAGES):
label = all_images[id]["true_label"]
data_tensor[id, :, label] = all_images[id][feature_model]
weights_tensor, factor_matrices = tl.decomposition.parafac(data_tensor, rank=rank, normalize_factors=True)
return weights_tensor, factor_matrices