{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":31254,"databundleVersionId":3103714,"sourceType":"competition"},{"sourceId":396802,"sourceType":"datasetVersion","datasetId":175990},{"sourceId":6437552,"sourceType":"datasetVersion","datasetId":3715198}],"dockerImageVersionId":30558,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-09-09T03:42:39.056335Z","iopub.execute_input":"2023-09-09T03:42:39.05681Z","iopub.status.idle":"2023-09-09T03:42:39.426357Z","shell.execute_reply.started":"2023-09-09T03:42:39.056779Z","shell.execute_reply":"2023-09-09T03:42:39.42534Z"},"trusted":true},"execution_count":1,"outputs":[]},{"cell_type":"code","source":"! pip install sentence_transformers","metadata":{"execution":{"iopub.status.busy":"2023-09-09T03:42:39.428369Z","iopub.execute_input":"2023-09-09T03:42:39.428915Z","iopub.status.idle":"2023-09-09T03:42:58.200475Z","shell.execute_reply.started":"2023-09-09T03:42:39.428881Z","shell.execute_reply":"2023-09-09T03:42:58.19928Z"},"trusted":true},"execution_count":2,"outputs":[{"name":"stdout","text":"Collecting sentence_transformers\n Downloading sentence-transformers-2.2.2.tar.gz (85 kB)\n\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.0/86.0 kB\u001b[0m \u001b[31m2.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25ldone\n\u001b[?25hRequirement already satisfied: transformers<5.0.0,>=4.6.0 in /opt/conda/lib/python3.10/site-packages (from sentence_transformers) (4.33.0)\nRequirement already satisfied: tqdm in /opt/conda/lib/python3.10/site-packages (from sentence_transformers) (4.66.1)\nRequirement already satisfied: torch>=1.6.0 in /opt/conda/lib/python3.10/site-packages (from sentence_transformers) (2.0.0)\nRequirement already satisfied: torchvision in /opt/conda/lib/python3.10/site-packages (from sentence_transformers) (0.15.1)\nRequirement already satisfied: numpy in /opt/conda/lib/python3.10/site-packages (from sentence_transformers) (1.23.5)\nRequirement already satisfied: scikit-learn in /opt/conda/lib/python3.10/site-packages (from sentence_transformers) (1.2.2)\nRequirement already satisfied: scipy in /opt/conda/lib/python3.10/site-packages (from sentence_transformers) (1.11.2)\nRequirement already satisfied: nltk in /opt/conda/lib/python3.10/site-packages (from sentence_transformers) (3.2.4)\nRequirement already satisfied: sentencepiece in /opt/conda/lib/python3.10/site-packages (from sentence_transformers) (0.1.99)\nRequirement already satisfied: huggingface-hub>=0.4.0 in /opt/conda/lib/python3.10/site-packages (from sentence_transformers) (0.16.4)\nRequirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.4.0->sentence_transformers) (3.12.2)\nRequirement already satisfied: fsspec in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.4.0->sentence_transformers) (2023.9.0)\nRequirement already satisfied: requests in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.4.0->sentence_transformers) (2.31.0)\nRequirement already satisfied: pyyaml>=5.1 in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.4.0->sentence_transformers) (6.0)\nRequirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.4.0->sentence_transformers) (4.6.3)\nRequirement already satisfied: packaging>=20.9 in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.4.0->sentence_transformers) (21.3)\nRequirement already satisfied: sympy in /opt/conda/lib/python3.10/site-packages (from torch>=1.6.0->sentence_transformers) (1.12)\nRequirement already satisfied: networkx in /opt/conda/lib/python3.10/site-packages (from torch>=1.6.0->sentence_transformers) (3.1)\nRequirement already satisfied: jinja2 in /opt/conda/lib/python3.10/site-packages (from torch>=1.6.0->sentence_transformers) (3.1.2)\nRequirement already satisfied: regex!=2019.12.17 in /opt/conda/lib/python3.10/site-packages (from transformers<5.0.0,>=4.6.0->sentence_transformers) (2023.6.3)\nRequirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /opt/conda/lib/python3.10/site-packages (from transformers<5.0.0,>=4.6.0->sentence_transformers) (0.13.3)\nRequirement already satisfied: safetensors>=0.3.1 in /opt/conda/lib/python3.10/site-packages (from transformers<5.0.0,>=4.6.0->sentence_transformers) (0.3.3)\nRequirement already satisfied: six in /opt/conda/lib/python3.10/site-packages (from nltk->sentence_transformers) (1.16.0)\nRequirement already satisfied: joblib>=1.1.1 in /opt/conda/lib/python3.10/site-packages (from scikit-learn->sentence_transformers) (1.3.2)\nRequirement already satisfied: threadpoolctl>=2.0.0 in /opt/conda/lib/python3.10/site-packages (from scikit-learn->sentence_transformers) (3.1.0)\nRequirement already satisfied: pillow!=8.3.*,>=5.3.0 in /opt/conda/lib/python3.10/site-packages (from torchvision->sentence_transformers) (9.5.0)\nRequirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /opt/conda/lib/python3.10/site-packages (from packaging>=20.9->huggingface-hub>=0.4.0->sentence_transformers) (3.0.9)\nRequirement already satisfied: MarkupSafe>=2.0 in /opt/conda/lib/python3.10/site-packages (from jinja2->torch>=1.6.0->sentence_transformers) (2.1.3)\nRequirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface-hub>=0.4.0->sentence_transformers) (3.1.0)\nRequirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface-hub>=0.4.0->sentence_transformers) (3.4)\nRequirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface-hub>=0.4.0->sentence_transformers) (1.26.15)\nRequirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface-hub>=0.4.0->sentence_transformers) (2023.7.22)\nRequirement already satisfied: mpmath>=0.19 in /opt/conda/lib/python3.10/site-packages (from sympy->torch>=1.6.0->sentence_transformers) (1.3.0)\nBuilding wheels for collected packages: sentence_transformers\n Building wheel for sentence_transformers (setup.py) ... \u001b[?25ldone\n\u001b[?25h Created wheel for sentence_transformers: filename=sentence_transformers-2.2.2-py3-none-any.whl size=125926 sha256=997dd45017a415c90c60b9ac7b81ca316afd36abd7129caa9e5362096c2d4f92\n Stored in directory: /root/.cache/pip/wheels/62/f2/10/1e606fd5f02395388f74e7462910fe851042f97238cbbd902f\nSuccessfully built sentence_transformers\nInstalling collected packages: sentence_transformers\nSuccessfully installed sentence_transformers-2.2.2\n","output_type":"stream"}]},{"cell_type":"code","source":"df = pd.read_csv('/kaggle/input/h-and-m-personalized-fashion-recommendations/articles.csv')","metadata":{"execution":{"iopub.status.busy":"2023-09-09T03:50:51.261768Z","iopub.execute_input":"2023-09-09T03:50:51.262164Z","iopub.status.idle":"2023-09-09T03:50:51.976901Z","shell.execute_reply.started":"2023-09-09T03:50:51.262129Z","shell.execute_reply":"2023-09-09T03:50:51.975826Z"},"trusted":true},"execution_count":22,"outputs":[]},{"cell_type":"code","source":"df","metadata":{"execution":{"iopub.status.busy":"2023-09-09T03:50:51.978932Z","iopub.execute_input":"2023-09-09T03:50:51.979383Z","iopub.status.idle":"2023-09-09T03:50:52.061374Z","shell.execute_reply.started":"2023-09-09T03:50:51.979347Z","shell.execute_reply":"2023-09-09T03:50:52.060462Z"},"trusted":true},"execution_count":23,"outputs":[{"execution_count":23,"output_type":"execute_result","data":{"text/plain":" article_id product_code prod_name product_type_no \\\n0 108775015 108775 Strap top 253 \n1 108775044 108775 Strap top 253 \n2 108775051 108775 Strap top (1) 253 \n3 110065001 110065 OP T-shirt (Idro) 306 \n4 110065002 110065 OP T-shirt (Idro) 306 \n... ... ... ... ... \n105537 953450001 953450 5pk regular Placement1 302 \n105538 953763001 953763 SPORT Malaga tank 253 \n105539 956217002 956217 Cartwheel dress 265 \n105540 957375001 957375 CLAIRE HAIR CLAW 72 \n105541 959461001 959461 Lounge dress 265 \n\n product_type_name product_group_name graphical_appearance_no \\\n0 Vest top Garment Upper body 1010016 \n1 Vest top Garment Upper body 1010016 \n2 Vest top Garment Upper body 1010017 \n3 Bra Underwear 1010016 \n4 Bra Underwear 1010016 \n... ... ... ... \n105537 Socks Socks & Tights 1010014 \n105538 Vest top Garment Upper body 1010016 \n105539 Dress Garment Full body 1010016 \n105540 Hair clip Accessories 1010016 \n105541 Dress Garment Full body 1010016 \n\n graphical_appearance_name colour_group_code colour_group_name ... \\\n0 Solid 9 Black ... \n1 Solid 10 White ... \n2 Stripe 11 Off White ... \n3 Solid 9 Black ... \n4 Solid 10 White ... \n... ... ... ... ... \n105537 Placement print 9 Black ... \n105538 Solid 9 Black ... \n105539 Solid 9 Black ... \n105540 Solid 9 Black ... \n105541 Solid 11 Off White ... \n\n department_name index_code index_name index_group_no \\\n0 Jersey Basic A Ladieswear 1 \n1 Jersey Basic A Ladieswear 1 \n2 Jersey Basic A Ladieswear 1 \n3 Clean Lingerie B Lingeries/Tights 1 \n4 Clean Lingerie B Lingeries/Tights 1 \n... ... ... ... ... \n105537 Socks Bin F Menswear 3 \n105538 Jersey A Ladieswear 1 \n105539 Jersey A Ladieswear 1 \n105540 Small Accessories D Divided 2 \n105541 Jersey A Ladieswear 1 \n\n index_group_name section_no section_name garment_group_no \\\n0 Ladieswear 16 Womens Everyday Basics 1002 \n1 Ladieswear 16 Womens Everyday Basics 1002 \n2 Ladieswear 16 Womens Everyday Basics 1002 \n3 Ladieswear 61 Womens Lingerie 1017 \n4 Ladieswear 61 Womens Lingerie 1017 \n... ... ... ... ... \n105537 Menswear 26 Men Underwear 1021 \n105538 Ladieswear 2 H&M+ 1005 \n105539 Ladieswear 18 Womens Trend 1005 \n105540 Divided 52 Divided Accessories 1019 \n105541 Ladieswear 18 Womens Trend 1005 \n\n garment_group_name detail_desc \n0 Jersey Basic Jersey top with narrow shoulder straps. \n1 Jersey Basic Jersey top with narrow shoulder straps. \n2 Jersey Basic Jersey top with narrow shoulder straps. \n3 Under-, Nightwear Microfibre T-shirt bra with underwired, moulde... \n4 Under-, Nightwear Microfibre T-shirt bra with underwired, moulde... \n... ... ... \n105537 Socks and Tights Socks in a fine-knit cotton blend with a small... \n105538 Jersey Fancy Loose-fitting sports vest top in ribbed fast-d... \n105539 Jersey Fancy Short, A-line dress in jersey with a round nec... \n105540 Accessories Large plastic hair claw. \n105541 Jersey Fancy Calf-length dress in ribbed jersey made from a... \n\n[105542 rows x 25 columns]","text/html":"
\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
article_idproduct_codeprod_nameproduct_type_noproduct_type_nameproduct_group_namegraphical_appearance_nographical_appearance_namecolour_group_codecolour_group_name...department_nameindex_codeindex_nameindex_group_noindex_group_namesection_nosection_namegarment_group_nogarment_group_namedetail_desc
0108775015108775Strap top253Vest topGarment Upper body1010016Solid9Black...Jersey BasicALadieswear1Ladieswear16Womens Everyday Basics1002Jersey BasicJersey top with narrow shoulder straps.
1108775044108775Strap top253Vest topGarment Upper body1010016Solid10White...Jersey BasicALadieswear1Ladieswear16Womens Everyday Basics1002Jersey BasicJersey top with narrow shoulder straps.
2108775051108775Strap top (1)253Vest topGarment Upper body1010017Stripe11Off White...Jersey BasicALadieswear1Ladieswear16Womens Everyday Basics1002Jersey BasicJersey top with narrow shoulder straps.
3110065001110065OP T-shirt (Idro)306BraUnderwear1010016Solid9Black...Clean LingerieBLingeries/Tights1Ladieswear61Womens Lingerie1017Under-, NightwearMicrofibre T-shirt bra with underwired, moulde...
4110065002110065OP T-shirt (Idro)306BraUnderwear1010016Solid10White...Clean LingerieBLingeries/Tights1Ladieswear61Womens Lingerie1017Under-, NightwearMicrofibre T-shirt bra with underwired, moulde...
..................................................................
1055379534500019534505pk regular Placement1302SocksSocks & Tights1010014Placement print9Black...Socks BinFMenswear3Menswear26Men Underwear1021Socks and TightsSocks in a fine-knit cotton blend with a small...
105538953763001953763SPORT Malaga tank253Vest topGarment Upper body1010016Solid9Black...JerseyALadieswear1Ladieswear2H&M+1005Jersey FancyLoose-fitting sports vest top in ribbed fast-d...
105539956217002956217Cartwheel dress265DressGarment Full body1010016Solid9Black...JerseyALadieswear1Ladieswear18Womens Trend1005Jersey FancyShort, A-line dress in jersey with a round nec...
105540957375001957375CLAIRE HAIR CLAW72Hair clipAccessories1010016Solid9Black...Small AccessoriesDDivided2Divided52Divided Accessories1019AccessoriesLarge plastic hair claw.
105541959461001959461Lounge dress265DressGarment Full body1010016Solid11Off White...JerseyALadieswear1Ladieswear18Womens Trend1005Jersey FancyCalf-length dress in ribbed jersey made from a...
\n

105542 rows × 25 columns

\n
"},"metadata":{}}]},{"cell_type":"code","source":"article_ids = df['article_id'].to_list()\n\nn = 500\n \n# printing n elements from list\narticle_ids= random.choices(article_ids, k=n)\nlen(article_ids)","metadata":{"execution":{"iopub.status.busy":"2023-09-09T04:08:31.028333Z","iopub.execute_input":"2023-09-09T04:08:31.028739Z","iopub.status.idle":"2023-09-09T04:08:31.044007Z","shell.execute_reply.started":"2023-09-09T04:08:31.028707Z","shell.execute_reply":"2023-09-09T04:08:31.042904Z"},"trusted":true},"execution_count":39,"outputs":[{"execution_count":39,"output_type":"execute_result","data":{"text/plain":"500"},"metadata":{}}]},{"cell_type":"code","source":"from sentence_transformers import SentenceTransformer\nfrom PIL import Image\n\nmodel = SentenceTransformer(\"clip-ViT-B-32\")","metadata":{"execution":{"iopub.status.busy":"2023-09-09T04:08:32.606899Z","iopub.execute_input":"2023-09-09T04:08:32.607259Z","iopub.status.idle":"2023-09-09T04:08:34.529317Z","shell.execute_reply.started":"2023-09-09T04:08:32.607229Z","shell.execute_reply":"2023-09-09T04:08:34.52831Z"},"trusted":true},"execution_count":40,"outputs":[]},{"cell_type":"code","source":"image = Image.open('/kaggle/input/fashion-product-images-small/images/10006.jpg')\nimage_embedding = model.encode(image)\nimage_embedding.shape","metadata":{"execution":{"iopub.status.busy":"2023-09-08T21:56:48.265832Z","iopub.execute_input":"2023-09-08T21:56:48.266266Z","iopub.status.idle":"2023-09-08T21:56:48.58579Z","shell.execute_reply.started":"2023-09-08T21:56:48.266234Z","shell.execute_reply":"2023-09-08T21:56:48.584948Z"},"trusted":true},"execution_count":11,"outputs":[{"output_type":"display_data","data":{"text/plain":"Batches: 0%| | 0/1 [00:00=1.49.1 in /opt/conda/lib/python3.10/site-packages (from pymilvus) (1.51.3)\nRequirement already satisfied: protobuf>=3.20.0 in /opt/conda/lib/python3.10/site-packages (from pymilvus) (3.20.3)\nCollecting environs<=9.5.0 (from pymilvus)\n Downloading environs-9.5.0-py2.py3-none-any.whl (12 kB)\nRequirement already satisfied: ujson>=2.0.0 in /opt/conda/lib/python3.10/site-packages (from pymilvus) (5.8.0)\nRequirement already satisfied: pandas>=1.2.4 in /opt/conda/lib/python3.10/site-packages (from pymilvus) (2.0.3)\nRequirement already satisfied: marshmallow>=3.0.0 in /opt/conda/lib/python3.10/site-packages (from environs<=9.5.0->pymilvus) (3.20.1)\nRequirement already satisfied: python-dotenv in /opt/conda/lib/python3.10/site-packages (from environs<=9.5.0->pymilvus) (1.0.0)\nRequirement already satisfied: python-dateutil>=2.8.2 in /opt/conda/lib/python3.10/site-packages (from pandas>=1.2.4->pymilvus) (2.8.2)\nRequirement already satisfied: pytz>=2020.1 in /opt/conda/lib/python3.10/site-packages (from pandas>=1.2.4->pymilvus) (2023.3)\nRequirement already satisfied: tzdata>=2022.1 in /opt/conda/lib/python3.10/site-packages (from pandas>=1.2.4->pymilvus) (2023.3)\nRequirement already satisfied: numpy>=1.21.0 in /opt/conda/lib/python3.10/site-packages (from pandas>=1.2.4->pymilvus) (1.23.5)\nRequirement already satisfied: packaging>=17.0 in /opt/conda/lib/python3.10/site-packages (from marshmallow>=3.0.0->environs<=9.5.0->pymilvus) (21.3)\nRequirement already satisfied: six>=1.5 in /opt/conda/lib/python3.10/site-packages (from python-dateutil>=2.8.2->pandas>=1.2.4->pymilvus) (1.16.0)\nRequirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /opt/conda/lib/python3.10/site-packages (from packaging>=17.0->marshmallow>=3.0.0->environs<=9.5.0->pymilvus) (3.0.9)\nInstalling collected packages: environs, pymilvus\nSuccessfully installed environs-9.5.0 pymilvus-2.3.0\n","output_type":"stream"}]},{"cell_type":"code","source":"import pickle\n\npickle_file_path =\"/kaggle/working/embedding3000.pickle\"\nwith open(pickle_file_path, 'wb') as pickle_file:\n pickle.dump(embeddings, pickle_file)\n","metadata":{"execution":{"iopub.status.busy":"2023-09-08T22:20:51.454004Z","iopub.execute_input":"2023-09-08T22:20:51.454376Z","iopub.status.idle":"2023-09-08T22:20:51.466851Z","shell.execute_reply.started":"2023-09-08T22:20:51.454328Z","shell.execute_reply":"2023-09-08T22:20:51.465562Z"},"trusted":true},"execution_count":19,"outputs":[]},{"cell_type":"code","source":"indices = df['id'][1:3001]\nind = []\nfor i in indices:\n ind.append(int(i[:-4]))\nindices = ind\npickle_file_path =\"/kaggle/working/indices3000.pickle\"\nwith open(pickle_file_path, 'wb') as pickle_file:\n pickle.dump(indices, pickle_file)","metadata":{"execution":{"iopub.status.busy":"2023-09-08T22:20:51.468792Z","iopub.execute_input":"2023-09-08T22:20:51.469178Z","iopub.status.idle":"2023-09-08T22:20:51.477964Z","shell.execute_reply.started":"2023-09-08T22:20:51.469147Z","shell.execute_reply":"2023-09-08T22:20:51.47704Z"},"trusted":true},"execution_count":20,"outputs":[]},{"cell_type":"code","source":"import configparser\nimport numpy as np\nimport pickle\nfrom pymilvus import connections, utility\nfrom pymilvus import Collection, DataType, FieldSchema, CollectionSchema\n\n\nif __name__ == '__main__':\n # Connect to Milvus\n \n # Check if the collection exists\n collection_name = \"lat_embedding\"\n check_collection = utility.has_collection(collection_name)\n \n if check_collection == True:\n # Load image embeddings from 'data.pickle'\n image_embeddings = embeddings\n print(image_embeddings.shape)\n image_embeddings = image_embeddings.tolist()\n indices = df['id'][1:100]\n ind = []\n for i in indices:\n print(i[:-4])\n ind.append(int(i[:-4]))\n indices = ind\n print(indices)\n \n for i,row in df.iterrows():\n if(indices[i] in df['id']):\n indices[i] = str(df[id]) + str(indices[i]) \n \n print(type(image_embeddings), len(image_embeddings))\n # Create a collection schema for image embeddings\n dim = 64 # Assuming the dimension of your embeddings\n image_embedding_field = FieldSchema(name=\"embedding\", dtype=DataType.FLOAT_VECTOR, dim=dim)\n primary_key_field = FieldSchema(name=\"primary_key\", dtype=DataType.INT64,is_primary=True, description=\"customized primary id\", dim=dim)\n schema = CollectionSchema(fields=[primary_key_field, image_embedding_field], auto_id=False, description=\"Image Embeddings\")\n\n # Create a new collection with the schema\n print(f\"Creating collection: {collection_name}\")\n collection = Collection(name=collection_name, schema=schema)\n \n primary_key = []\n for i in (indices):\n primary_key.append(i)\n \n embedding = []\n for i in image_embeddings:\n embedding.append(i)\n \n # Insert the data into the collection\n insert_entities = [primary_key, embedding]\n # print(insert_entities[0])\n ins_resp = collection.insert(insert_entities)\n print(f\"Inserted {len(insert_entities)} image embeddings.\")\n\n # Flush the collection\n print(\"Flushing the collection...\")\n collection.flush()\n print(\"Flushed.\")\n\n # Build index (you can specify appropriate index parameters here)\n index_params = {\"index_type\": \"HNSW\", \"metric_type\": \"L2\", \"params\": {\"M\": 32, \"efConstruction\": 200}}\n print(\"Building index...\")\n collection.create_index(field_name=image_embedding_field.name, index_params=index_params)\n print(\"Index built.\")\n\n # Disconnect from Milvus\n connections.disconnect(\"default\")\n\n","metadata":{"execution":{"iopub.status.busy":"2023-09-08T20:08:02.168478Z","iopub.execute_input":"2023-09-08T20:08:02.169198Z","iopub.status.idle":"2023-09-08T20:11:42.53715Z","shell.execute_reply.started":"2023-09-08T20:08:02.169169Z","shell.execute_reply":"2023-09-08T20:11:42.535497Z"},"trusted":true},"execution_count":38,"outputs":[{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mMilvusException\u001b[0m Traceback (most recent call last)"," \u001b[0;31m[... skipping hidden 1 frame]\u001b[0m\n","Cell \u001b[0;32mIn[38], line 13\u001b[0m\n\u001b[1;32m 12\u001b[0m collection_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlat_embedding\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m---> 13\u001b[0m check_collection \u001b[38;5;241m=\u001b[39m \u001b[43mutility\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mhas_collection\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcollection_name\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 15\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check_collection \u001b[38;5;241m==\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[1;32m 16\u001b[0m \u001b[38;5;66;03m# Load image embeddings from 'data.pickle'\u001b[39;00m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/orm/utility.py:433\u001b[0m, in \u001b[0;36mhas_collection\u001b[0;34m(collection_name, using, timeout)\u001b[0m\n\u001b[1;32m 415\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 416\u001b[0m \u001b[38;5;124;03mChecks whether a specified collection exists.\u001b[39;00m\n\u001b[1;32m 417\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 431\u001b[0m \u001b[38;5;124;03m >>> utility.has_collection(\"test_collection\")\u001b[39;00m\n\u001b[1;32m 432\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m--> 433\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_get_connection\u001b[49m\u001b[43m(\u001b[49m\u001b[43musing\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mhas_collection\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcollection_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/decorators.py:127\u001b[0m, in \u001b[0;36merror_handler..wrapper..handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 126\u001b[0m LOGGER\u001b[38;5;241m.\u001b[39merror(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRPC error: [\u001b[39m\u001b[38;5;132;01m{\u001b[39;00minner_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m], \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m, \u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 127\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m 128\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m grpc\u001b[38;5;241m.\u001b[39mFutureTimeoutError \u001b[38;5;28;01mas\u001b[39;00m e:\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/decorators.py:123\u001b[0m, in \u001b[0;36merror_handler..wrapper..handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 122\u001b[0m record_dict[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRPC start\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mstr\u001b[39m(datetime\u001b[38;5;241m.\u001b[39mdatetime\u001b[38;5;241m.\u001b[39mnow())\n\u001b[0;32m--> 123\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 124\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m MilvusException \u001b[38;5;28;01mas\u001b[39;00m e:\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/decorators.py:162\u001b[0m, in \u001b[0;36mtracing_request..wrapper..handler\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 161\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mset_onetime_request_id(req_id)\n\u001b[0;32m--> 162\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/decorators.py:81\u001b[0m, in \u001b[0;36mretry_on_rpc_failure..wrapper..handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 80\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m timeout(start_time):\n\u001b[0;32m---> 81\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m MilvusException(e\u001b[38;5;241m.\u001b[39mcode, \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mto_msg\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m, message=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;241m.\u001b[39mdetails()\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m 83\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m counter \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m3\u001b[39m:\n","\u001b[0;31mMilvusException\u001b[0m: >, message=Retry run out of 75 retry times, message=auth check failure, please check username and password are correct)>","\nThe above exception was the direct cause of the following exception:\n","\u001b[0;31mMilvusException\u001b[0m Traceback (most recent call last)"," \u001b[0;31m[... skipping hidden 1 frame]\u001b[0m\n","Cell \u001b[0;32mIn[38], line 13\u001b[0m\n\u001b[1;32m 12\u001b[0m collection_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlat_embedding\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m---> 13\u001b[0m check_collection \u001b[38;5;241m=\u001b[39m \u001b[43mutility\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mhas_collection\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcollection_name\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 15\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check_collection \u001b[38;5;241m==\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[1;32m 16\u001b[0m \u001b[38;5;66;03m# Load image embeddings from 'data.pickle'\u001b[39;00m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/orm/utility.py:433\u001b[0m, in \u001b[0;36mhas_collection\u001b[0;34m(collection_name, using, timeout)\u001b[0m\n\u001b[1;32m 415\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 416\u001b[0m \u001b[38;5;124;03mChecks whether a specified collection exists.\u001b[39;00m\n\u001b[1;32m 417\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 431\u001b[0m \u001b[38;5;124;03m >>> utility.has_collection(\"test_collection\")\u001b[39;00m\n\u001b[1;32m 432\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m--> 433\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_get_connection\u001b[49m\u001b[43m(\u001b[49m\u001b[43musing\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mhas_collection\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcollection_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/decorators.py:127\u001b[0m, in \u001b[0;36merror_handler..wrapper..handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 126\u001b[0m LOGGER\u001b[38;5;241m.\u001b[39merror(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRPC error: [\u001b[39m\u001b[38;5;132;01m{\u001b[39;00minner_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m], \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m, \u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 127\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m 128\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m grpc\u001b[38;5;241m.\u001b[39mFutureTimeoutError \u001b[38;5;28;01mas\u001b[39;00m e:\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/decorators.py:123\u001b[0m, in \u001b[0;36merror_handler..wrapper..handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 122\u001b[0m record_dict[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRPC start\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mstr\u001b[39m(datetime\u001b[38;5;241m.\u001b[39mdatetime\u001b[38;5;241m.\u001b[39mnow())\n\u001b[0;32m--> 123\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 124\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m MilvusException \u001b[38;5;28;01mas\u001b[39;00m e:\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/decorators.py:162\u001b[0m, in \u001b[0;36mtracing_request..wrapper..handler\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 161\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mset_onetime_request_id(req_id)\n\u001b[0;32m--> 162\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/decorators.py:81\u001b[0m, in \u001b[0;36mretry_on_rpc_failure..wrapper..handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 80\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m timeout(start_time):\n\u001b[0;32m---> 81\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m MilvusException(e\u001b[38;5;241m.\u001b[39mcode, \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mto_msg\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m, message=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;241m.\u001b[39mdetails()\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m 83\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m counter \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m3\u001b[39m:\n","\u001b[0;31mMilvusException\u001b[0m: >, message=Retry run out of 75 retry times, message=auth check failure, please check username and password are correct)>","\nThe above exception was the direct cause of the following exception:\n","\u001b[0;31mMilvusException\u001b[0m Traceback (most recent call last)","Cell \u001b[0;32mIn[38], line 13\u001b[0m\n\u001b[1;32m 8\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;18m__name__\u001b[39m \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124m__main__\u001b[39m\u001b[38;5;124m'\u001b[39m:\n\u001b[1;32m 9\u001b[0m \u001b[38;5;66;03m# Connect to Milvus\u001b[39;00m\n\u001b[1;32m 10\u001b[0m \n\u001b[1;32m 11\u001b[0m \u001b[38;5;66;03m# Check if the collection exists\u001b[39;00m\n\u001b[1;32m 12\u001b[0m collection_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlat_embedding\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m---> 13\u001b[0m check_collection \u001b[38;5;241m=\u001b[39m \u001b[43mutility\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mhas_collection\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcollection_name\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 15\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check_collection \u001b[38;5;241m==\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[1;32m 16\u001b[0m \u001b[38;5;66;03m# Load image embeddings from 'data.pickle'\u001b[39;00m\n\u001b[1;32m 17\u001b[0m image_embeddings \u001b[38;5;241m=\u001b[39m embeddings\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/orm/utility.py:433\u001b[0m, in \u001b[0;36mhas_collection\u001b[0;34m(collection_name, using, timeout)\u001b[0m\n\u001b[1;32m 414\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mhas_collection\u001b[39m(collection_name: \u001b[38;5;28mstr\u001b[39m, using: \u001b[38;5;28mstr\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdefault\u001b[39m\u001b[38;5;124m\"\u001b[39m, timeout: Optional[\u001b[38;5;28mfloat\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[1;32m 415\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 416\u001b[0m \u001b[38;5;124;03m Checks whether a specified collection exists.\u001b[39;00m\n\u001b[1;32m 417\u001b[0m \n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 431\u001b[0m \u001b[38;5;124;03m >>> utility.has_collection(\"test_collection\")\u001b[39;00m\n\u001b[1;32m 432\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[0;32m--> 433\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_get_connection\u001b[49m\u001b[43m(\u001b[49m\u001b[43musing\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mhas_collection\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcollection_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/decorators.py:127\u001b[0m, in \u001b[0;36merror_handler..wrapper..handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 125\u001b[0m record_dict[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRPC error\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mstr\u001b[39m(datetime\u001b[38;5;241m.\u001b[39mdatetime\u001b[38;5;241m.\u001b[39mnow())\n\u001b[1;32m 126\u001b[0m LOGGER\u001b[38;5;241m.\u001b[39merror(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRPC error: [\u001b[39m\u001b[38;5;132;01m{\u001b[39;00minner_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m], \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m, \u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 127\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m 128\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m grpc\u001b[38;5;241m.\u001b[39mFutureTimeoutError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 129\u001b[0m record_dict[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mgRPC timeout\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mstr\u001b[39m(datetime\u001b[38;5;241m.\u001b[39mdatetime\u001b[38;5;241m.\u001b[39mnow())\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/decorators.py:123\u001b[0m, in \u001b[0;36merror_handler..wrapper..handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 121\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 122\u001b[0m record_dict[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRPC start\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mstr\u001b[39m(datetime\u001b[38;5;241m.\u001b[39mdatetime\u001b[38;5;241m.\u001b[39mnow())\n\u001b[0;32m--> 123\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 124\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m MilvusException \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 125\u001b[0m record_dict[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRPC error\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mstr\u001b[39m(datetime\u001b[38;5;241m.\u001b[39mdatetime\u001b[38;5;241m.\u001b[39mnow())\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/decorators.py:162\u001b[0m, in \u001b[0;36mtracing_request..wrapper..handler\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 160\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m req_id:\n\u001b[1;32m 161\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mset_onetime_request_id(req_id)\n\u001b[0;32m--> 162\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m/opt/conda/lib/python3.10/site-packages/pymilvus/decorators.py:81\u001b[0m, in \u001b[0;36mretry_on_rpc_failure..wrapper..handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 79\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m 80\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m timeout(start_time):\n\u001b[0;32m---> 81\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m MilvusException(e\u001b[38;5;241m.\u001b[39mcode, \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mto_msg\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m, message=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;241m.\u001b[39mdetails()\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m 83\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m counter \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m3\u001b[39m:\n\u001b[1;32m 84\u001b[0m retry_msg \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m 85\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m[\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfunc\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m] retry:\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mcounter\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m, cost: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mback_off\u001b[38;5;132;01m:\u001b[39;00m\u001b[38;5;124m.2f\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124ms, \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 86\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mreason: <\u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;241m.\u001b[39mcode()\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m, \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;241m.\u001b[39mdetails()\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m>\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 87\u001b[0m )\n","\u001b[0;31mMilvusException\u001b[0m: >, message=Retry run out of 75 retry times, message=auth check failure, please check username and password are correct)>"],"ename":"MilvusException","evalue":">, message=Retry run out of 75 retry times, message=auth check failure, please check username and password are correct)>","output_type":"error"}]},{"cell_type":"code","source":"import os\nimport time\nfrom PIL import Image\nimport numpy as np\nimport tensorflow as tf\nimport tensorflow_hub as hub\nimport matplotlib.pyplot as plt\nos.environ[\"TFHUB_DOWNLOAD_PROGRESS\"] = \"True\"","metadata":{"execution":{"iopub.status.busy":"2023-09-08T23:54:04.572094Z","iopub.execute_input":"2023-09-08T23:54:04.572514Z","iopub.status.idle":"2023-09-08T23:54:05.005909Z","shell.execute_reply.started":"2023-09-08T23:54:04.572484Z","shell.execute_reply":"2023-09-08T23:54:05.004834Z"},"trusted":true},"execution_count":2,"outputs":[]},{"cell_type":"code","source":"def preprocess_image(image_path):\n \"\"\" Loads image from path and preprocesses to make it model ready\n Args:\n image_path: Path to the image file\n \"\"\"\n hr_image = tf.image.decode_image(tf.io.read_file(image_path))\n # If PNG, remove the alpha channel. The model only supports\n # images with 3 color channels.\n if hr_image.shape[-1] == 4:\n hr_image = hr_image[...,:-1]\n hr_size = (tf.convert_to_tensor(hr_image.shape[:-1]) // 4) * 4\n hr_image = tf.image.crop_to_bounding_box(hr_image, 0, 0, hr_size[0], hr_size[1])\n hr_image = tf.cast(hr_image, tf.float32)\n return tf.expand_dims(hr_image, 0)\n\ndef save_image(image, filename):\n \"\"\"\n Saves unscaled Tensor Images.\n Args:\n image: 3D image tensor. [height, width, channels]\n filename: Name of the file to save.\n \"\"\"\n if not isinstance(image, Image.Image):\n image = tf.clip_by_value(image, 0, 255)\n image = Image.fromarray(tf.cast(image, tf.uint8).numpy())\n image.save(\"%s.jpg\" % filename)\n print(\"Saved as %s.jpg\" % filename)","metadata":{"execution":{"iopub.status.busy":"2023-09-08T23:54:11.525998Z","iopub.execute_input":"2023-09-08T23:54:11.526906Z","iopub.status.idle":"2023-09-08T23:54:11.537575Z","shell.execute_reply.started":"2023-09-08T23:54:11.526865Z","shell.execute_reply":"2023-09-08T23:54:11.536279Z"},"trusted":true},"execution_count":3,"outputs":[]},{"cell_type":"code","source":"hr_image = preprocess_image('/kaggle/input/fashion-product-images-small/images/10004.jpg')","metadata":{"execution":{"iopub.status.busy":"2023-09-08T23:54:46.578554Z","iopub.execute_input":"2023-09-08T23:54:46.579456Z","iopub.status.idle":"2023-09-08T23:54:46.784348Z","shell.execute_reply.started":"2023-09-08T23:54:46.579408Z","shell.execute_reply":"2023-09-08T23:54:46.782746Z"},"trusted":true},"execution_count":5,"outputs":[]},{"cell_type":"code","source":"%matplotlib inline\ndef plot_image(image, title=\"\"):\n \"\"\"\n Plots images from image tensors.\n Args:\n image: 3D image tensor. [height, width, channels].\n title: Title to display in the plot.\n \"\"\"\n image = np.asarray(image)\n image = tf.clip_by_value(image, 0, 255)\n image = Image.fromarray(tf.cast(image, tf.uint8).numpy())\n plt.imshow(image)\n plt.axis(\"off\")\n plt.title(title)","metadata":{"execution":{"iopub.status.busy":"2023-09-08T23:55:12.982828Z","iopub.execute_input":"2023-09-08T23:55:12.983431Z","iopub.status.idle":"2023-09-08T23:55:12.993307Z","shell.execute_reply.started":"2023-09-08T23:55:12.983394Z","shell.execute_reply":"2023-09-08T23:55:12.992035Z"},"trusted":true},"execution_count":7,"outputs":[]},{"cell_type":"code","source":"# Plotting Original Resolution image\nplot_image(tf.squeeze(hr_image), title=\"Original Image\")\nsave_image(tf.squeeze(hr_image), filename=\"Original Image\")","metadata":{"execution":{"iopub.status.busy":"2023-09-08T23:55:14.140116Z","iopub.execute_input":"2023-09-08T23:55:14.140556Z","iopub.status.idle":"2023-09-08T23:55:14.396192Z","shell.execute_reply.started":"2023-09-08T23:55:14.140519Z","shell.execute_reply":"2023-09-08T23:55:14.395023Z"},"trusted":true},"execution_count":8,"outputs":[{"name":"stdout","text":"Saved as Original Image.jpg\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"SAVED_MODEL_PATH = \"https://tfhub.dev/captain-pool/esrgan-tf2/1\"\nmodel = hub.load(SAVED_MODEL_PATH)","metadata":{"execution":{"iopub.status.busy":"2023-09-08T23:55:53.888298Z","iopub.execute_input":"2023-09-08T23:55:53.888875Z","iopub.status.idle":"2023-09-08T23:56:01.874584Z","shell.execute_reply.started":"2023-09-08T23:55:53.888828Z","shell.execute_reply":"2023-09-08T23:56:01.873243Z"},"trusted":true},"execution_count":9,"outputs":[{"name":"stdout","text":"Downloaded https://tfhub.dev/captain-pool/esrgan-tf2/1, Total size: 20.60MB\n\n","output_type":"stream"}]},{"cell_type":"code","source":"start = time.time()\nfake_image = model(hr_image)\nfake_image = tf.squeeze(fake_image)\nprint(\"Time Taken: %f\" % (time.time() - start))","metadata":{"execution":{"iopub.status.busy":"2023-09-08T23:56:08.142949Z","iopub.execute_input":"2023-09-08T23:56:08.143413Z","iopub.status.idle":"2023-09-08T23:56:10.072793Z","shell.execute_reply.started":"2023-09-08T23:56:08.143378Z","shell.execute_reply":"2023-09-08T23:56:10.071839Z"},"trusted":true},"execution_count":10,"outputs":[{"name":"stdout","text":"Time Taken: 1.921365\n","output_type":"stream"}]},{"cell_type":"code","source":"# Plotting Super Resolution Image\nplot_image(tf.squeeze(fake_image), title=\"Super Resolution\")\nsave_image(tf.squeeze(fake_image), filename=\"Super Resolution\")","metadata":{"execution":{"iopub.status.busy":"2023-09-08T23:56:13.616189Z","iopub.execute_input":"2023-09-08T23:56:13.616657Z","iopub.status.idle":"2023-09-08T23:56:13.947642Z","shell.execute_reply.started":"2023-09-08T23:56:13.616621Z","shell.execute_reply":"2023-09-08T23:56:13.94641Z"},"trusted":true},"execution_count":11,"outputs":[{"name":"stdout","text":"Saved as Super Resolution.jpg\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"
","image/png":"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"},"metadata":{}}]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pip install git+https://va957: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@github.com/CompVis/dpt.git\n","metadata":{"execution":{"iopub.status.busy":"2023-09-09T00:12:03.387786Z","iopub.execute_input":"2023-09-09T00:12:03.389135Z","iopub.status.idle":"2023-09-09T00:12:06.024431Z","shell.execute_reply.started":"2023-09-09T00:12:03.389073Z","shell.execute_reply":"2023-09-09T00:12:06.022659Z"},"trusted":true},"execution_count":15,"outputs":[{"name":"stdout","text":"Collecting git+https://va957:****@github.com/CompVis/dpt.git\n Cloning https://va957:****@github.com/CompVis/dpt.git to /tmp/pip-req-build-2kp171xv\n Running command git clone --filter=blob:none --quiet 'https://va957:****@github.com/CompVis/dpt.git' /tmp/pip-req-build-2kp171xv\n remote: Repository not found.\n fatal: repository 'https://github.com/CompVis/dpt.git/' not found\n \u001b[1;31merror\u001b[0m: \u001b[1msubprocess-exited-with-error\u001b[0m\n \n \u001b[31m×\u001b[0m \u001b[32mgit clone --\u001b[0m\u001b[32mfilter\u001b[0m\u001b[32m=\u001b[0m\u001b[32mblob\u001b[0m\u001b[32m:none --quiet \u001b[0m\u001b[32m'https://va957:****@github.com/CompVis/dpt.git'\u001b[0m\u001b[32m \u001b[0m\u001b[32m/tmp/\u001b[0m\u001b[32mpip-req-build-2kp171xv\u001b[0m did not run successfully.\n \u001b[31m│\u001b[0m exit code: \u001b[1;36m128\u001b[0m\n \u001b[31m╰─>\u001b[0m See above for output.\n \n \u001b[1;35mnote\u001b[0m: This error originates from a subprocess, and is likely not a problem with pip.\n\u001b[1;31merror\u001b[0m: \u001b[1msubprocess-exited-with-error\u001b[0m\n\n\u001b[31m×\u001b[0m \u001b[32mgit clone --\u001b[0m\u001b[32mfilter\u001b[0m\u001b[32m=\u001b[0m\u001b[32mblob\u001b[0m\u001b[32m:none --quiet \u001b[0m\u001b[32m'https://va957:****@github.com/CompVis/dpt.git'\u001b[0m\u001b[32m \u001b[0m\u001b[32m/tmp/\u001b[0m\u001b[32mpip-req-build-2kp171xv\u001b[0m did not run successfully.\n\u001b[31m│\u001b[0m exit code: \u001b[1;36m128\u001b[0m\n\u001b[31m╰─>\u001b[0m See above for output.\n\n\u001b[1;35mnote\u001b[0m: This error originates from a subprocess, and is likely not a problem with pip.\nNote: you may need to restart the kernel to use updated packages.\n","output_type":"stream"}]},{"cell_type":"code","source":"import torch\nfrom torchvision.transforms import Compose, Resize, ToTensor\nfrom dpt.models import DPTDepthModel\n\n# Load a pre-trained model (you can choose different variants)\nmodel = DPTDepthModel.from_pretrained(\"dpt_hybrid\")\nmodel.eval() # Set the model to evaluation mode\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nfrom PIL import Image\n\ndef blind_inpaint_image(model, input_image_path):\n # Load the input image\n input_image = Image.open(input_image_path)\n\n # Apply transformations and convert to a tensor\n input_tensor = ToTensor()(Resize((384, 384))(input_image)).unsqueeze(0)\n\n # Create a binary mask with all ones (no missing information)\n mask_tensor = torch.ones_like(input_tensor)\n\n # Perform blind inpainting\n with torch.no_grad():\n output = model(input_tensor, mask_tensor)\n\n # Convert the output tensor to a PIL image\n output_image = Image.fromarray((output[0].permute(1, 2, 0).cpu().numpy() * 255).astype(np.uint8))\n\n return output_image\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from PIL import Image, ImageDraw\n\n# Load the original image\noriginal_image = Image.open('original_image.jpg')\n\n# Create a blank mask with the same dimensions as the original image\nmask = Image.new('L', original_image.size, 255) # 'L' mode is for grayscale, 255 represents white\n\n# Create a drawing context for the mask\ndraw = ImageDraw.Draw(mask)\n\n# Define the coordinates of the rectangle to mask (you can adjust these values)\nleft = 100\ntop = 100\nright = 300\nbottom = 300\n\n# Draw a black rectangle on the mask to hide the specified region\ndraw.rectangle([left, top, right, bottom], fill=0)\n\n# Apply the mask to the original image\nincomplete_image = Image.composite(original_image, Image.new('RGB', original_image.size), mask)\n\n# Save or display the incomplete image\nincomplete_image.save('incomplete_image.jpg')\nincomplete_image.show()\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"input_image_path = 'incomplete_image.jpg'\n\noutput_image = blind_inpaint_image(model, input_image_path)\n\n# Save or display the inpainted image\noutput_image.save('blind_inpainting_result.jpg')\noutput_image.show()\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}