{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 5GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import os\nimport pandas as pd\nimport tensorflow as tf\nimport tensorflow_hub as hub\nimport matplotlib.pyplot as plt\nfrom six import BytesIO\nimport numpy as np\nimport xml.etree.ElementTree as et\nimport ast\nimport tqdm\nfrom itertools import chain\nfrom xml.dom import minidom\nfrom PIL import Image\nfrom PIL import ImageColor\nfrom PIL import ImageDraw\nfrom PIL import ImageFont\nfrom PIL import ImageOps\nimport cv2\nimport glob\nimport time","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"path1='/kaggle/input/open-images-object-detection-rvc-2020/test/'\nsample = pd.read_csv(\"/kaggle/input/open-images-object-detection-rvc-2020/sample_submission.csv\")\nsample.head()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ids = []\nfor i in range(len(sample)):\n    ids.append(sample['ImageId'][i])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#ids[0:5","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_data=[]\nfor i in range(len(sample)):\n    img_data.append(glob.glob('/kaggle/input/open-images-object-detection-rvc-2020/test/{0}.jpg'.format(ids[i])))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_data[0:5]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_prediction_string(result):\n    with tf.device('/device:GPU:0'):\n        df = pd.DataFrame(columns=['Ymin','Xmin','Ymax', 'Xmax','Score','Label','Class_label','Class_name'])\n        min_score=0.01\n        for i in range(result['detection_boxes'].shape[0]):\n           if (result[\"detection_scores\"][i]) >= min_score:\n              df.loc[i]= tuple(result['detection_boxes'][i])+(result[\"detection_scores\"][i],)+(result[\"detection_class_labels\"][i],)+(result[\"detection_class_names\"][i],)+(result[\"detection_class_entities\"][i],)\n        return df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow.compat.v1 as tf\ntf.disable_v2_behavior()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"module_handle = \"https://tfhub.dev/google/faster_rcnn/openimages_v4/inception_resnet_v2/1\"\nwith tf.device('/device:GPU:0'):\n    with tf.Graph().as_default():\n        detector = hub.Module(module_handle)\n        image_string_placeholder = tf.placeholder(tf.string)\n        decoded_image = tf.image.decode_jpeg(image_string_placeholder)\n        decoded_image_float = tf.image.convert_image_dtype(\n            image=decoded_image, dtype=tf.float32)\n        module_input = tf.expand_dims(decoded_image_float, 0)\n        result = detector(module_input, as_dict=True)\n        init_ops = [tf.global_variables_initializer(), tf.tables_initializer()]\n\n        session = tf.Session()\n        session.run(init_ops)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def nms(dets, thresh):\n    x1 = dets[:, 0]\n    y1 = dets[:, 1]\n    x2 = dets[:, 2]\n    y2 = dets[:, 3]\n    scores = dets[:, 4]\n\n    areas = (x2 - x1 + 1) * (y2 - y1 + 1)\n    order = scores.argsort()[::-1]\n\n    keep = []\n    while order.size > 0:\n        i = order[0]\n        keep.append(i)\n        xx1 = np.maximum(x1[i], x1[order[1:]])\n        yy1 = np.maximum(y1[i], y1[order[1:]])\n        xx2 = np.minimum(x2[i], x2[order[1:]])\n        yy2 = np.minimum(y2[i], y2[order[1:]])\n\n        w = np.maximum(0.0, xx2 - xx1 + 1)\n        h = np.maximum(0.0, yy2 - yy1 + 1)\n        inter = w * h\n        ovr = inter / (areas[i] + areas[order[1:]] - inter)\n\n        inds = np.where(ovr <= thresh)[0]\n        order = order[inds + 1]\n\n    return keep","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"image_paths = img_data[0:10]\nimages = []\nfor f in image_paths:\n    images.append(np.asarray(Image.open(f[0])))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!mkdir detect","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"image_id = sample['ImageId']\ndef format_prediction_string(image_id, result):\n    prediction_strings = []\n    \n    for i in range(len(result['Score'])):\n        class_name = result['Class_label'][i].decode(\"utf-8\")\n        YMin,XMin,YMax,XMax = result['Ymin'][i],result['Xmin'][i],result['Ymax'][i],result['Xmax'][i]\n        score = result['Score'][i]\n        \n        prediction_strings.append(\n            f\"{class_name} {score} {XMin} {YMin} {XMax} {YMax}\"\n        )\n        \n    prediction_string = \" \".join(prediction_strings)\n\n    return {\n        \"PredictionString\": prediction_string\n    }","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"k =-1\npredictions = []\nwith tf.device('/device:GPU:0'):\n    for image_path in image_paths:\n        k=k+1\n        img_path = img_data[k]\n        img = cv2.imread(img_path[0])\n        with tf.io.gfile.GFile(image_path[0], \"rb\") as binfile:\n            image_string = binfile.read()\n\n        inference_start_time = time.time()\n        result_out, image_out = session.run(\n            [result, decoded_image],\n            feed_dict={image_string_placeholder: image_string})\n        df1=get_prediction_string(result_out)\n        z1=nms(df1.values,0.68)\n        z=df1.iloc[z1]\n        z=z.reset_index()\n        predictions.append(format_prediction_string(image_id, z))\n        data1=z\n        COLORS = np.random.uniform(0, 255, size=(len(z['Class_name']), 3))\n        for m in range(len(data1)):\n            if data1['Score'][m] >=0.01:\n                img_class=data1.iloc[m].Class_name\n                img_xmax, img_ymax =images[k].shape[1],images[k].shape[0]\n                bbox_x_max, bbox_x_min = data1.Xmax[m] * img_xmax, data1.Xmin[m] * img_xmax\n                bbox_y_max ,bbox_y_min = data1.Ymax[m] * img_ymax, data1.Ymin[m] * img_ymax\n                xmin = int(bbox_x_min)\n                ymin = int(bbox_y_min)\n                xmax = int(bbox_x_max)\n                ymax = int(bbox_y_max)\n                width = xmax - xmin\n                height = ymax - ymin\n                label = str(data1['Class_name'][m])\n                color = COLORS[m]\n                cv2.rectangle(img, (xmin, ymax), (xmax, ymin), color, 2)\n                path1 = '/kaggle/working/detect/'+str(k)+'.jpg'\n                cv2.imwrite(path1, img)\n                cv2.putText(img, label, (xmax,ymin), cv2.FONT_HERSHEY_SIMPLEX, 0.9,color, 2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def load_images(folder):\n    images = []\n    for filename in os.listdir(folder):\n        img = Image.open(os.path.join(folder, filename))\n        if img is not None:\n            images.append(img)\n    return images","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"z = load_images(\"/kaggle/working/detect\")\nz[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"z[1]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"z[3]","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}