1 line
48 KiB
Plaintext
1 line
48 KiB
Plaintext
|
{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.12.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceType":"datasetVersion","sourceId":3771150,"datasetId":2004518,"databundleVersionId":3825728}],"dockerImageVersionId":31329,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"!pip install -q ultralytics","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2026-05-03T10:28:09.186553Z","iopub.execute_input":"2026-05-03T10:28:09.186784Z","iopub.status.idle":"2026-05-03T10:28:15.175437Z","shell.execute_reply.started":"2026-05-03T10:28:09.186760Z","shell.execute_reply":"2026-05-03T10:28:15.174587Z"}},"outputs":[{"name":"stdout","text":"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m20.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n\u001b[?25h","output_type":"stream"}],"execution_count":1},{"cell_type":"markdown","source":"# Dataset - SKU110K *(most popular)*\n- 11,762 shelf images with ~1.2million annotated products.\n- Dense shelf scenarios\n- [on Github](http://github.com/eg4000/SKU110K_CVPR19) | [on Kaggle](https://www.kaggle.com/datasets/thedatasith/sku110k-annotations)\n\nOther datasets to check:\n- Grocery Store Dataset (Grozi-120)\n- WebMarket\n- RPC (Retail Product Checkout)","metadata":{}},{"cell_type":"code","source":"import os\n\nBASE_PATH = \"/kaggle/input/datasets/thedatasith/sku110k-annotations\"\nDATASET_FOLDER = None\n\n# find SKU110K_fixed folder\nfor item in os.listdir(BASE_PATH):\n if \"SKU110K\" in item:\n DATASET_FOLDER = os.path.join(BASE_PATH, item)\n break\n\nprint(\"📁 Dataset folder:\", DATASET_FOLDER)\n\nfor root, dirs, files in os.walk(DATASET_FOLDER):\n level = root.replace(DATASET_FOLDER, '').count(os.sep)\n indent = ' ' * 2 * level\n print(f\"{indent}📁 {os.path.basename(root)}/\")\n for f in files[:5]:\n print(f\"{indent} 📄 {f}\")\n if level >= 2:\n break","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-05-03T10:28:15.180147Z","iopub.execute_input":"2026-05-03T10:28:15.180435Z","iopub.status.idle":"2026-05-03T10:28:18.766862Z","shell.execute_reply.started":"2026-05-03T10:28:15.180387Z","shell.execute_reply":"2026-05-03T10:28:18.766011Z"}},"outputs":[{"name":"stdout","text":"📁 Dataset folder: /kaggle/input/datasets/thedatasith/sku110k-annotations/SKU110K_fixed\n📁 SKU110K_fixed/\n 📁 labels/\n 📁 val/\n 📄 val_30.txt\n 📄 val_216.txt\n 📄 val_16.txt\n 📄 val_499.txt\n 📄 val_180.txt\n","output_type":"stream"}],"execution_count":2},{"cell_type":"code","source":"import yaml\n\nYAML_PATH = BASE_PATH + \"/data_kaggle.yaml\"\n\nwith open(YAML_PATH, \"r\") as f:\n data = yaml.safe_load(f)\n\nprint(\"Classes:\", data.get(\"names\"))\nprint(\"Number of classes:\", len(data.get(\"names\", [])))\nprint(\"Train path:\", data.get(\"train\"))\nprint(\"Val path:\", data.get(\"val\"))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-05-03T10:28:18.768355Z","iopub.execute_input":"2026-05-03T10:28:18.768863Z","iopub.status.idle":"2026-05-03T10:28:18.803040Z","shell.execute_reply.started":"2026-05-03T10:28:18.768833Z","shell.execute_reply":"2026-05-03T10:28:18.802326Z"}},"outputs":[{"name":"stdout","text":"Classes: ['object']\nNumber of classes: 1\nTrain path: train\nVal path: val\n","output_type":"stream"}],"execution_count":3},{"cell_type":"code","source":"import yaml\n\nYAML_PATH = BASE_PATH + \"/data_kaggle.yaml\"\n\nwith o
|