{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"!pip install --upgrade seaborn\n\nimport 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\n\ndim = 512 #512, 256, 'original'\nfold = 4\n\ntrain_df = pd.read_csv(f'../input/vinbigdata-{dim}-image-dataset/vinbigdata/train.csv')\ntrain_df.head()\n\ntrain_df['image_path'] = f'/kaggle/input/vinbigdata-{dim}-image-dataset/vinbigdata/train/'+train_df.image_id+('.png' if dim!='original' else '.jpg')\n\ntrain_df = train_df[train_df.class_id!=14].reset_index(drop = True)\n\ntrain_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']\n\nfeatures = ['x_min', 'y_min', 'x_max', 'y_max', 'x_mid', 'y_mid', 'w', 'h', 'area']\nX = train_df[features]\ny = train_df['class_id']\n\nclass_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))\n\ngkf  = 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\n\ntrain_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())\n\nos.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')\n\nclass_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))\n\nfrom 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')\n\n# 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'))\n\n!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images/\nImage(filename='runs/detect/exp/zidane.jpg', width=600)\n\n# !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 512 --batch 16 --epochs 60 --data /kaggle/working/vinbigdata.yaml --weights yolov5l.pt  --cache\n\nplt.figure(figsize = (20,20))\nplt.axis('off')\nplt.imshow(plt.imread('runs/train/exp/labels_correlogram.jpg'));\n\n\nplt.figure(figsize = (20,20))\nplt.axis('off')\nplt.imshow(plt.imread('runs/train/exp/labels.jpg'));\n\nimport 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'))\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\nplt.figure(figsize=(30,15))\nplt.axis('off')\nplt.imshow(plt.imread('runs/train/exp/results.png'));\n\nplt.figure(figsize=(30,15))\nplt.axis('off')\nplt.imshow(plt.imread('runs/train/exp/confusion_matrix.png'));\n\n!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\n\nimport 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()\n\nshutil.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)\n\n","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}