{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":1800066,"sourceType":"datasetVersion","datasetId":1069809},{"sourceId":1800777,"sourceType":"datasetVersion","datasetId":1069787},{"sourceId":1800778,"sourceType":"datasetVersion","datasetId":1070222}],"dockerImageVersionId":30034,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"code","source":"!pip install --upgrade seaborn","metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"papermill":{"duration":9.633907,"end_time":"2021-01-01T09:44:53.448657","exception":false,"start_time":"2021-01-01T09:44:43.81475","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T14:57:19.147487Z","iopub.execute_input":"2024-04-13T14:57:19.147798Z","iopub.status.idle":"2024-04-13T14:57:28.279647Z","shell.execute_reply.started":"2024-04-13T14:57:19.147768Z","shell.execute_reply":"2024-04-13T14:57:28.278522Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import numpy as np, pandas as pd\nfrom glob import glob\nimport shutil, os\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import GroupKFold\nfrom tqdm.notebook import tqdm\nimport seaborn as sns","metadata":{"papermill":{"duration":0.926929,"end_time":"2021-01-01T09:44:54.403588","exception":false,"start_time":"2021-01-01T09:44:53.476659","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T14:57:36.662664Z","iopub.execute_input":"2024-04-13T14:57:36.663028Z","iopub.status.idle":"2024-04-13T14:57:37.447602Z","shell.execute_reply.started":"2024-04-13T14:57:36.662989Z","shell.execute_reply":"2024-04-13T14:57:37.446638Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dim = 256 #512, 256, 'original'\nfold = 4","metadata":{"execution":{"iopub.status.busy":"2024-04-13T14:57:49.791095Z","iopub.execute_input":"2024-04-13T14:57:49.791446Z","iopub.status.idle":"2024-04-13T14:57:49.795631Z","shell.execute_reply.started":"2024-04-13T14:57:49.791415Z","shell.execute_reply":"2024-04-13T14:57:49.794633Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df = pd.read_csv(f'../input/vinbigdata-{dim}-image-dataset/vinbigdata/train.csv')\ntrain_df.head()","metadata":{"papermill":{"duration":0.262045,"end_time":"2021-01-01T09:44:54.691965","exception":false,"start_time":"2021-01-01T09:44:54.42992","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T14:58:03.72695Z","iopub.execute_input":"2024-04-13T14:58:03.727327Z","iopub.status.idle":"2024-04-13T14:58:03.927638Z","shell.execute_reply.started":"2024-04-13T14:58:03.727294Z","shell.execute_reply":"2024-04-13T14:58:03.926852Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df['image_path'] = f'/kaggle/input/vinbigdata-{dim}-image-dataset/vinbigdata/train/'+train_df.image_id+('.png' if dim!='original' else '.jpg')\ntrain_df.head()","metadata":{"papermill":{"duration":0.086788,"end_time":"2021-01-01T09:44:54.805857","exception":false,"start_time":"2021-01-01T09:44:54.719069","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T14:58:07.346322Z","iopub.execute_input":"2024-04-13T14:58:07.346694Z","iopub.status.idle":"2024-04-13T14:58:07.406145Z","shell.execute_reply.started":"2024-04-13T14:58:07.346657Z","shell.execute_reply":"2024-04-13T14:58:07.40529Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Only 14 Class","metadata":{"papermill":{"duration":0.027478,"end_time":"2021-01-01T09:44:54.861374","exception":false,"start_time":"2021-01-01T09:44:54.833896","status":"completed"},"tags":[]}},{"cell_type":"code","source":"train_df = train_df[train_df.class_id!=14].reset_index(drop = True)","metadata":{"papermill":{"duration":0.05543,"end_time":"2021-01-01T09:44:54.944088","exception":false,"start_time":"2021-01-01T09:44:54.888658","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T14:58:12.368115Z","iopub.execute_input":"2024-04-13T14:58:12.368444Z","iopub.status.idle":"2024-04-13T14:58:12.395052Z","shell.execute_reply.started":"2024-04-13T14:58:12.368416Z","shell.execute_reply":"2024-04-13T14:58:12.394381Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Pre-Processing","metadata":{"papermill":{"duration":0.027303,"end_time":"2021-01-01T09:44:54.999199","exception":false,"start_time":"2021-01-01T09:44:54.971896","status":"completed"},"tags":[]}},{"cell_type":"code","source":"train_df['x_min'] = train_df.apply(lambda row: (row.x_min)/row.width, axis =1)\ntrain_df['y_min'] = train_df.apply(lambda row: (row.y_min)/row.height, axis =1)\n\ntrain_df['x_max'] = train_df.apply(lambda row: (row.x_max)/row.width, axis =1)\ntrain_df['y_max'] = train_df.apply(lambda row: (row.y_max)/row.height, axis =1)\n\ntrain_df['x_mid'] = train_df.apply(lambda row: (row.x_max+row.x_min)/2, axis =1)\ntrain_df['y_mid'] = train_df.apply(lambda row: (row.y_max+row.y_min)/2, axis =1)\n\ntrain_df['w'] = train_df.apply(lambda row: (row.x_max-row.x_min), axis =1)\ntrain_df['h'] = train_df.apply(lambda row: (row.y_max-row.y_min), axis =1)\n\ntrain_df['area'] = train_df['w']*train_df['h']\ntrain_df.head()","metadata":{"papermill":{"duration":7.821668,"end_time":"2021-01-01T09:45:02.854149","exception":false,"start_time":"2021-01-01T09:44:55.032481","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T14:58:14.181616Z","iopub.execute_input":"2024-04-13T14:58:14.181965Z","iopub.status.idle":"2024-04-13T14:58:22.630191Z","shell.execute_reply.started":"2024-04-13T14:58:14.181934Z","shell.execute_reply":"2024-04-13T14:58:22.629334Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"features = ['x_min', 'y_min', 'x_max', 'y_max', 'x_mid', 'y_mid', 'w', 'h', 'area']\nX = train_df[features]\ny = train_df['class_id']\nX.shape, y.shape","metadata":{"papermill":{"duration":0.040387,"end_time":"2021-01-01T09:45:02.923416","exception":false,"start_time":"2021-01-01T09:45:02.883029","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T14:58:26.911003Z","iopub.execute_input":"2024-04-13T14:58:26.911349Z","iopub.status.idle":"2024-04-13T14:58:26.921285Z","shell.execute_reply.started":"2024-04-13T14:58:26.911317Z","shell.execute_reply":"2024-04-13T14:58:26.920411Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class_ids, class_names = list(zip(*set(zip(train_df.class_id, train_df.class_name))))\nclasses = list(np.array(class_names)[np.argsort(class_ids)])\nclasses = list(map(lambda x: str(x), classes))\nclasses","metadata":{"papermill":{"duration":0.050418,"end_time":"2021-01-01T09:45:03.002944","exception":false,"start_time":"2021-01-01T09:45:02.952526","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T14:58:29.079422Z","iopub.execute_input":"2024-04-13T14:58:29.079786Z","iopub.status.idle":"2024-04-13T14:58:29.100689Z","shell.execute_reply.started":"2024-04-13T14:58:29.079751Z","shell.execute_reply":"2024-04-13T14:58:29.099887Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{"papermill":{"duration":0.028555,"end_time":"2021-01-01T09:45:03.060819","exception":false,"start_time":"2021-01-01T09:45:03.032264","status":"completed"},"tags":[]}},{"cell_type":"code","source":"","metadata":{"_kg_hide-output":true,"papermill":{"duration":79.550362,"end_time":"2021-01-01T09:46:22.640073","exception":false,"start_time":"2021-01-01T09:45:03.089711","status":"completed"},"tags":[],"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"papermill":{"duration":0.674101,"end_time":"2021-01-01T09:46:23.353693","exception":false,"start_time":"2021-01-01T09:46:22.679592","status":"completed"},"tags":[],"_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# BBox Location","metadata":{"papermill":{"duration":0.043674,"end_time":"2021-01-01T09:46:23.441245","exception":false,"start_time":"2021-01-01T09:46:23.397571","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"## x_mid Vs y_mid","metadata":{"papermill":{"duration":0.041604,"end_time":"2021-01-01T09:46:23.525588","exception":false,"start_time":"2021-01-01T09:46:23.483984","status":"completed"},"tags":[]}},{"cell_type":"code","source":"from scipy.stats import gaussian_kde\n\n\nx_val = train_df.x_mid.values\ny_val = train_df.y_mid.values\n\n# Calculate the point density\nxy = np.vstack([x_val,y_val])\nz = gaussian_kde(xy)(xy)\n\nfig, ax = plt.subplots(figsize = (10, 10))\nax.axis('off')\nax.scatter(x_val, y_val, c=z, s=100, cmap='viridis')\n# ax.set_xlabel('x_mid')\n# ax.set_ylabel('y_mid')\nplt.show()","metadata":{"papermill":{"duration":31.402628,"end_time":"2021-01-01T09:46:54.970613","exception":false,"start_time":"2021-01-01T09:46:23.567985","status":"completed"},"tags":[],"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-04-13T14:58:35.715893Z","iopub.execute_input":"2024-04-13T14:58:35.716262Z","iopub.status.idle":"2024-04-13T14:59:04.342887Z","shell.execute_reply.started":"2024-04-13T14:58:35.716224Z","shell.execute_reply":"2024-04-13T14:59:04.341997Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## bbox_w Vs bbox_h","metadata":{"papermill":{"duration":0.046802,"end_time":"2021-01-01T09:46:55.064644","exception":false,"start_time":"2021-01-01T09:46:55.017842","status":"completed"},"tags":[]}},{"cell_type":"code","source":"x_val = train_df.w.values\ny_val = train_df.h.values\n\n# Calculate the point density\nxy = np.vstack([x_val,y_val])\nz = gaussian_kde(xy)(xy)\n\nfig, ax = plt.subplots(figsize = (10, 10))\nax.axis('off')\nax.scatter(x_val, y_val, c=z, s=100, cmap='viridis')\n# ax.set_xlabel('bbox_width')\n# ax.set_ylabel('bbox_height')\nplt.show()","metadata":{"papermill":{"duration":30.485279,"end_time":"2021-01-01T09:47:25.596636","exception":false,"start_time":"2021-01-01T09:46:55.111357","status":"completed"},"tags":[],"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-04-13T07:56:54.48283Z","iopub.execute_input":"2024-04-13T07:56:54.483202Z","iopub.status.idle":"2024-04-13T07:57:27.063058Z","shell.execute_reply.started":"2024-04-13T07:56:54.483171Z","shell.execute_reply":"2024-04-13T07:57:27.061992Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Image Aspect Ratio","metadata":{"papermill":{"duration":0.090619,"end_time":"2021-01-01T09:47:25.783368","exception":false,"start_time":"2021-01-01T09:47:25.692749","status":"completed"},"tags":[]}},{"cell_type":"code","source":"x_val = train_df.width.values\ny_val = train_df.height.values\n\n# Calculate the point density\nxy = np.vstack([x_val,y_val])\nz = gaussian_kde(xy)(xy)\n\nfig, ax = plt.subplots(figsize = (10, 10))\nax.axis('off')\nax.scatter(x_val, y_val, c=z, s=100, cmap='viridis')\n# ax.set_xlabel('image_width')\n# ax.set_ylabel('image_height')\nplt.show()","metadata":{"papermill":{"duration":30.131145,"end_time":"2021-01-01T09:47:56.005954","exception":false,"start_time":"2021-01-01T09:47:25.874809","status":"completed"},"tags":[],"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-04-13T07:57:31.785089Z","iopub.execute_input":"2024-04-13T07:57:31.785463Z","iopub.status.idle":"2024-04-13T07:58:04.507524Z","shell.execute_reply.started":"2024-04-13T07:57:31.785431Z","shell.execute_reply":"2024-04-13T07:58:04.506516Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Split","metadata":{"papermill":{"duration":0.052492,"end_time":"2021-01-01T09:47:56.110766","exception":false,"start_time":"2021-01-01T09:47:56.058274","status":"completed"},"tags":[]}},{"cell_type":"code","source":"gkf  = GroupKFold(n_splits = 5)\ntrain_df['fold'] = -1\nfor fold, (train_idx, val_idx) in enumerate(gkf.split(train_df, groups = train_df.image_id.tolist())):\n    train_df.loc[val_idx, 'fold'] = fold\ntrain_df.head()","metadata":{"papermill":{"duration":0.134603,"end_time":"2021-01-01T09:47:56.297774","exception":false,"start_time":"2021-01-01T09:47:56.163171","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T14:59:24.459681Z","iopub.execute_input":"2024-04-13T14:59:24.460069Z","iopub.status.idle":"2024-04-13T14:59:24.538914Z","shell.execute_reply.started":"2024-04-13T14:59:24.460034Z","shell.execute_reply":"2024-04-13T14:59:24.537999Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_files = []\nval_files   = []\nval_files += list(train_df[train_df.fold==fold].image_path.unique())\ntrain_files += list(train_df[train_df.fold!=fold].image_path.unique())\nlen(train_files), len(val_files)","metadata":{"papermill":{"duration":0.086817,"end_time":"2021-01-01T09:47:56.443789","exception":false,"start_time":"2021-01-01T09:47:56.356972","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T14:59:28.516598Z","iopub.execute_input":"2024-04-13T14:59:28.516938Z","iopub.status.idle":"2024-04-13T14:59:28.543981Z","shell.execute_reply.started":"2024-04-13T14:59:28.516909Z","shell.execute_reply":"2024-04-13T14:59:28.543083Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Copying Files","metadata":{"papermill":{"duration":0.083752,"end_time":"2021-01-01T09:47:56.584924","exception":false,"start_time":"2021-01-01T09:47:56.501172","status":"completed"},"tags":[]}},{"cell_type":"code","source":"os.makedirs('/kaggle/working/vinbigdata/labels/train', exist_ok = True)\nos.makedirs('/kaggle/working/vinbigdata/labels/val', exist_ok = True)\nos.makedirs('/kaggle/working/vinbigdata/images/train', exist_ok = True)\nos.makedirs('/kaggle/working/vinbigdata/images/val', exist_ok = True)\nlabel_dir = '/kaggle/input/vinbigdata-yolo-labels-dataset/labels'\nfor file in tqdm(train_files):\n    shutil.copy(file, '/kaggle/working/vinbigdata/images/train')\n    filename = file.split('/')[-1].split('.')[0]\n    shutil.copy(os.path.join(label_dir, filename+'.txt'), '/kaggle/working/vinbigdata/labels/train')\n    \nfor file in tqdm(val_files):\n    shutil.copy(file, '/kaggle/working/vinbigdata/images/val')\n    filename = file.split('/')[-1].split('.')[0]\n    shutil.copy(os.path.join(label_dir, filename+'.txt'), '/kaggle/working/vinbigdata/labels/val')","metadata":{"papermill":{"duration":124.654777,"end_time":"2021-01-01T09:50:01.331041","exception":false,"start_time":"2021-01-01T09:47:56.676264","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T15:00:03.781776Z","iopub.execute_input":"2024-04-13T15:00:03.782152Z","iopub.status.idle":"2024-04-13T15:01:12.940317Z","shell.execute_reply.started":"2024-04-13T15:00:03.78212Z","shell.execute_reply":"2024-04-13T15:01:12.939592Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Get Class Name","metadata":{"papermill":{"duration":0.068822,"end_time":"2021-01-01T09:50:01.458337","exception":false,"start_time":"2021-01-01T09:50:01.389515","status":"completed"},"tags":[]}},{"cell_type":"code","source":"class_ids, class_names = list(zip(*set(zip(train_df.class_id, train_df.class_name))))\nclasses = list(np.array(class_names)[np.argsort(class_ids)])\nclasses = list(map(lambda x: str(x), classes))\nclasses","metadata":{"papermill":{"duration":0.082234,"end_time":"2021-01-01T09:50:01.601574","exception":false,"start_time":"2021-01-01T09:50:01.51934","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T15:01:21.905671Z","iopub.execute_input":"2024-04-13T15:01:21.906064Z","iopub.status.idle":"2024-04-13T15:01:21.928614Z","shell.execute_reply.started":"2024-04-13T15:01:21.906026Z","shell.execute_reply":"2024-04-13T15:01:21.927868Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{"papermill":{"duration":0.056257,"end_time":"2021-01-01T09:50:01.716608","exception":false,"start_time":"2021-01-01T09:50:01.660351","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"# YOLOv5 Stuff","metadata":{"papermill":{"duration":0.055699,"end_time":"2021-01-01T09:50:01.82747","exception":false,"start_time":"2021-01-01T09:50:01.771771","status":"completed"},"tags":[]}},{"cell_type":"code","source":"from os import listdir\nfrom os.path import isfile, join\nimport yaml\n\ncwd = '/kaggle/working/'\n\nwith open(join( cwd , 'train.txt'), 'w') as f:\n    for path in glob('/kaggle/working/vinbigdata/images/train/*'):\n        f.write(path+'\\n')\n            \nwith open(join( cwd , 'val.txt'), 'w') as f:\n    for path in glob('/kaggle/working/vinbigdata/images/val/*'):\n        f.write(path+'\\n')\n\ndata = dict(\n    train =  join( cwd , 'train.txt') ,\n    val   =  join( cwd , 'val.txt' ),\n    nc    = 14,\n    names = classes\n    )\n\nwith open(join( cwd , 'vinbigdata.yaml'), 'w') as outfile:\n    yaml.dump(data, outfile, default_flow_style=False)\n\nf = open(join( cwd , 'vinbigdata.yaml'), 'r')\nprint('\\nyaml:')\nprint(f.read())","metadata":{"papermill":{"duration":0.113001,"end_time":"2021-01-01T09:50:01.996448","exception":false,"start_time":"2021-01-01T09:50:01.883447","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T15:01:30.870427Z","iopub.execute_input":"2024-04-13T15:01:30.870764Z","iopub.status.idle":"2024-04-13T15:01:30.942694Z","shell.execute_reply.started":"2024-04-13T15:01:30.870735Z","shell.execute_reply":"2024-04-13T15:01:30.941748Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# https://www.kaggle.com/ultralytics/yolov5\n# !git clone https://github.com/ultralytics/yolov5  # clone repo\n# %cd yolov5\nshutil.copytree('/kaggle/input/yolov5-official-v31-dataset/yolov5', '/kaggle/working/yolov5')\nos.chdir('/kaggle/working/yolov5')\n# %pip install -qr requirements.txt # install dependencies\n\nimport torch\nfrom IPython.display import Image, clear_output  # to display images\n\nclear_output()\nprint('Setup complete. Using torch %s %s' % (torch.__version__, torch.cuda.get_device_properties(0) if torch.cuda.is_available() else 'CPU'))","metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","papermill":{"duration":6.702428,"end_time":"2021-01-01T09:50:08.784153","exception":false,"start_time":"2021-01-01T09:50:02.081725","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T15:01:35.012728Z","iopub.execute_input":"2024-04-13T15:01:35.013065Z","iopub.status.idle":"2024-04-13T15:01:36.818968Z","shell.execute_reply.started":"2024-04-13T15:01:35.013035Z","shell.execute_reply":"2024-04-13T15:01:36.818124Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images/\nImage(filename='runs/detect/exp/zidane.jpg', width=600)","metadata":{"papermill":{"duration":10.410768,"end_time":"2021-01-01T09:50:19.303402","exception":false,"start_time":"2021-01-01T09:50:08.892634","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T15:01:45.018208Z","iopub.execute_input":"2024-04-13T15:01:45.018536Z","iopub.status.idle":"2024-04-13T15:01:53.878008Z","shell.execute_reply.started":"2024-04-13T15:01:45.018507Z","shell.execute_reply":"2024-04-13T15:01:53.877183Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Pretrained Checkpoints:\n\n| Model | AP<sup>val</sup> | AP<sup>test</sup> | AP<sub>50</sub> | Speed<sub>GPU</sub> | FPS<sub>GPU</sub> || params | FLOPS |\n|---------- |------ |------ |------ | -------- | ------| ------ |------  |  :------: |\n| [YOLOv5s](https://github.com/ultralytics/yolov5/releases/tag/v3.0)    | 37.0     | 37.0     | 56.2     | **2.4ms** | **416** || 7.5M   | 13.2B\n| [YOLOv5m](https://github.com/ultralytics/yolov5/releases/tag/v3.0)    | 44.3     | 44.3     | 63.2     | 3.4ms     | 294     || 21.8M  | 39.4B\n| [YOLOv5l](https://github.com/ultralytics/yolov5/releases/tag/v3.0)    | 47.7     | 47.7     | 66.5     | 4.4ms     | 227     || 47.8M  | 88.1B\n| [YOLOv5x](https://github.com/ultralytics/yolov5/releases/tag/v3.0)    | **49.2** | **49.2** | **67.7** | 6.9ms     | 145     || 89.0M  | 166.4B\n| | | | | | || |\n| [YOLOv5x](https://github.com/ultralytics/yolov5/releases/tag/v3.0) + TTA|**50.8**| **50.8** | **68.9** | 25.5ms    | 39      || 89.0M  | 354.3B\n| | | | | | || |\n| [YOLOv3-SPP](https://github.com/ultralytics/yolov5/releases/tag/v3.0) | 45.6     | 45.5     | 65.2     | 4.5ms     | 222     || 63.0M  | 118.0B","metadata":{"papermill":{"duration":0.064911,"end_time":"2021-01-01T09:50:19.435746","exception":false,"start_time":"2021-01-01T09:50:19.370835","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"# Selecting Models\nIn this notebok I'm using `v5s`. To select your prefered model just replace `--cfg models/yolov5s.yaml --weights yolov5s.pt` with the following command:\n* `v5s` : `--cfg models/yolov5s.yaml --weights yolov5s.pt`\n* `v5m` : `--cfg models/yolov5m.yaml --weights yolov5m.pt`\n* `v5l` : `--cfg models/yolov5l.yaml --weights yolov5l.pt`\n* `v5x` : `--cfg models/yolov5x.yaml --weights yolov5x.pt`","metadata":{"papermill":{"duration":0.064016,"end_time":"2021-01-01T09:50:19.564859","exception":false,"start_time":"2021-01-01T09:50:19.500843","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"# Train","metadata":{"papermill":{"duration":0.064553,"end_time":"2021-01-01T09:50:19.6938","exception":false,"start_time":"2021-01-01T09:50:19.629247","status":"completed"},"tags":[]}},{"cell_type":"code","source":"# !WANDB_MODE=\"dryrun\" python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --nosave --cache \n!WANDB_MODE=\"dryrun\" python train.py --img 640 --batch 16 --epochs 30 --data /kaggle/working/vinbigdata.yaml --weights yolov5x.pt --cache","metadata":{"papermill":{"duration":19916.498298,"end_time":"2021-01-01T15:22:16.289734","exception":false,"start_time":"2021-01-01T09:50:19.791436","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T15:02:06.129588Z","iopub.execute_input":"2024-04-13T15:02:06.129942Z","iopub.status.idle":"2024-04-13T17:39:46.808123Z","shell.execute_reply.started":"2024-04-13T15:02:06.129908Z","shell.execute_reply":"2024-04-13T17:39:46.807265Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Class Distribution","metadata":{"papermill":{"duration":4.919442,"end_time":"2021-01-01T15:22:26.398681","exception":false,"start_time":"2021-01-01T15:22:21.479239","status":"completed"},"tags":[]}},{"cell_type":"code","source":"plt.figure(figsize = (20,20))\nplt.axis('off')\nplt.imshow(plt.imread('runs/train/exp/labels_correlogram.jpg'));","metadata":{"papermill":{"duration":6.511035,"end_time":"2021-01-01T15:22:37.753063","exception":false,"start_time":"2021-01-01T15:22:31.242028","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T17:41:00.716035Z","iopub.execute_input":"2024-04-13T17:41:00.716427Z","iopub.status.idle":"2024-04-13T17:41:01.535872Z","shell.execute_reply.started":"2024-04-13T17:41:00.716391Z","shell.execute_reply":"2024-04-13T17:41:01.534895Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize = (20,20))\nplt.axis('off')\nplt.imshow(plt.imread('runs/train/exp/labels.jpg'));","metadata":{"papermill":{"duration":5.977042,"end_time":"2021-01-01T15:22:48.614609","exception":false,"start_time":"2021-01-01T15:22:42.637567","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T17:41:06.200377Z","iopub.execute_input":"2024-04-13T17:41:06.200746Z","iopub.status.idle":"2024-04-13T17:41:06.853505Z","shell.execute_reply.started":"2024-04-13T17:41:06.200706Z","shell.execute_reply":"2024-04-13T17:41:06.852748Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Batch Image","metadata":{"papermill":{"duration":5.378338,"end_time":"2021-01-01T15:22:59.482837","exception":false,"start_time":"2021-01-01T15:22:54.104499","status":"completed"},"tags":[]}},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nplt.figure(figsize = (15, 15))\nplt.imshow(plt.imread('runs/train/exp/train_batch0.jpg'))\n\nplt.figure(figsize = (15, 15))\nplt.imshow(plt.imread('runs/train/exp/train_batch1.jpg'))\n\nplt.figure(figsize = (15, 15))\nplt.imshow(plt.imread('runs/train/exp/train_batch2.jpg'))","metadata":{"papermill":{"duration":7.317416,"end_time":"2021-01-01T15:23:11.777544","exception":false,"start_time":"2021-01-01T15:23:04.460128","status":"completed"},"tags":[],"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-04-13T17:41:10.187662Z","iopub.execute_input":"2024-04-13T17:41:10.188119Z","iopub.status.idle":"2024-04-13T17:41:11.980756Z","shell.execute_reply.started":"2024-04-13T17:41:10.188077Z","shell.execute_reply":"2024-04-13T17:41:11.979857Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# GT Vs Pred","metadata":{}},{"cell_type":"code","source":"fig, ax = plt.subplots(3, 2, figsize = (2*5,3*5), constrained_layout = True)\nfor row in range(3):\n    ax[row][0].imshow(plt.imread(f'runs/train/exp/test_batch{row}_labels.jpg'))\n    ax[row][0].set_xticks([])\n    ax[row][0].set_yticks([])\n    ax[row][0].set_title(f'runs/train/exp/test_batch{row}_labels.jpg', fontsize = 12)\n    \n    ax[row][1].imshow(plt.imread(f'runs/train/exp/test_batch{row}_pred.jpg'))\n    ax[row][1].set_xticks([])\n    ax[row][1].set_yticks([])\n    ax[row][1].set_title(f'runs/train/exp/test_batch{row}_pred.jpg', fontsize = 12)","metadata":{"papermill":{"duration":6.453975,"end_time":"2021-01-01T15:23:23.514717","exception":false,"start_time":"2021-01-01T15:23:17.060742","status":"completed"},"tags":[],"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-04-13T17:41:15.375145Z","iopub.execute_input":"2024-04-13T17:41:15.375488Z","iopub.status.idle":"2024-04-13T17:41:17.047161Z","shell.execute_reply.started":"2024-04-13T17:41:15.375458Z","shell.execute_reply":"2024-04-13T17:41:17.046353Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# (Loss, Map) Vs Epoch","metadata":{}},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\nfig, ax = plt.subplots(3, 2, figsize=(2*5, 3*5), constrained_layout=True)\nfor row in range(3):\n    ax[row][0].imshow(plt.imread(f'runs/train/exp/test_batch{row}_labels.jpg'))\n    ax[row][0].set_xticks([])\n    ax[row][0].set_yticks([])\n    ax[row][0].set_title(f'runs/train/exp/test_batch{row}_labels.jpg', fontsize=12)\n    \n    ax[row][1].imshow(plt.imread(f'runs/train/exp/test_batch{row}_pred.jpg'))\n    ax[row][1].set_xticks([])\n    ax[row][1].set_yticks([])\n    ax[row][1].set_title(f'runs/train/exp/test_batch{row}_pred.jpg', fontsize=12)\n\n# Save the figure\nfig.savefig('/kaggle/working/your_figure_name.png')\n","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-04-13T17:45:19.471033Z","iopub.execute_input":"2024-04-13T17:45:19.471396Z","iopub.status.idle":"2024-04-13T17:45:21.621597Z","shell.execute_reply.started":"2024-04-13T17:45:19.471361Z","shell.execute_reply":"2024-04-13T17:45:21.620622Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Confusion Matrix","metadata":{}},{"cell_type":"code","source":"!zip -r runs.zip runs/\n","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-04-13T17:46:38.197539Z","iopub.execute_input":"2024-04-13T17:46:38.197965Z","iopub.status.idle":"2024-04-13T17:46:55.944729Z","shell.execute_reply.started":"2024-04-13T17:46:38.197927Z","shell.execute_reply":"2024-04-13T17:46:55.943622Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Inference","metadata":{"papermill":{"duration":4.941983,"end_time":"2021-01-01T15:23:33.765831","exception":false,"start_time":"2021-01-01T15:23:28.823848","status":"completed"},"tags":[]}},{"cell_type":"code","source":"!python detect.py --weights 'runs/train/exp/weights/best.pt'\\\n--img 640\\\n--conf 0.15\\\n--iou 0.5\\\n--source /kaggle/working/vinbigdata/images/val\\\n--exist-ok","metadata":{"_kg_hide-output":true,"papermill":{"duration":10.763143,"end_time":"2021-01-01T15:23:49.800461","exception":false,"start_time":"2021-01-01T15:23:39.037318","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-13T17:48:25.124863Z","iopub.execute_input":"2024-04-13T17:48:25.125248Z","iopub.status.idle":"2024-04-13T17:49:18.898068Z","shell.execute_reply.started":"2024-04-13T17:48:25.125212Z","shell.execute_reply":"2024-04-13T17:49:18.896966Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Inference Plot","metadata":{"papermill":{"duration":5.225725,"end_time":"2021-01-01T15:24:00.706026","exception":false,"start_time":"2021-01-01T15:23:55.480301","status":"completed"},"tags":[]}},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nfrom mpl_toolkits.axes_grid1 import ImageGrid\nimport numpy as np\nimport random\nimport cv2\nfrom glob import glob\nfrom tqdm import tqdm\n\nfiles = glob('runs/detect/exp/*')\nfor _ in range(3):\n    row = 4\n    col = 4\n    grid_files = random.sample(files, row*col)\n    images     = []\n    for image_path in tqdm(grid_files):\n        img          = cv2.cvtColor(cv2.imread(image_path), cv2.COLOR_BGR2RGB)\n        images.append(img)\n\n    fig = plt.figure(figsize=(col*5, row*5))\n    grid = ImageGrid(fig, 111,  # similar to subplot(111)\n                     nrows_ncols=(col, row),  # creates 2x2 grid of axes\n                     axes_pad=0.05,  # pad between axes in inch.\n                     )\n\n    for ax, im in zip(grid, images):\n        # Iterating over the grid returns the Axes.\n        ax.imshow(im)\n        ax.set_xticks([])\n        ax.set_yticks([])\n    plt.show()","metadata":{"papermill":{"duration":5.31015,"end_time":"2021-01-01T15:24:11.211904","exception":false,"start_time":"2021-01-01T15:24:05.901754","status":"completed"},"tags":[],"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-04-13T17:49:27.602134Z","iopub.execute_input":"2024-04-13T17:49:27.602516Z","iopub.status.idle":"2024-04-13T17:49:32.559806Z","shell.execute_reply.started":"2024-04-13T17:49:27.602475Z","shell.execute_reply":"2024-04-13T17:49:32.558482Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"shutil.rmtree('/kaggle/working/vinbigdata')\nshutil.rmtree('runs/detect')\nfor file in (glob('runs/train/exp/**/*.png', recursive = True)+glob('runs/train/exp/**/*.jpg', recursive = True)):\n    os.remove(file)","metadata":{"papermill":{"duration":5.709202,"end_time":"2021-01-01T15:24:22.413173","exception":false,"start_time":"2021-01-01T15:24:16.703971","status":"completed"},"tags":[],"_kg_hide-input":true,"_kg_hide-output":true,"execution":{"iopub.status.busy":"2024-04-13T17:49:35.898413Z","iopub.execute_input":"2024-04-13T17:49:35.898786Z","iopub.status.idle":"2024-04-13T17:49:36.242242Z","shell.execute_reply.started":"2024-04-13T17:49:35.89875Z","shell.execute_reply":"2024-04-13T17:49:36.241286Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}