[GPU] VINBIGDATA EFFICIENTDET TRAINING USING TF OBJECT DETECTION API
\n"},{"metadata":{},"cell_type":"markdown","source":"Overview
\n\nTensorFlow 2 Object Detection API is a framework built on top of TF2, which makes it easy to construct, train and deploy, robust and high performance Object Detection Models. This notebook presents the process of TFrecord Data Preparation, loading Pre-trained models, Transfer Learning, Tuning and Inference of state-of-the-art models such as EfficientDet.
\n\nServeral models from the TensorFlow Model Zoo can be trained with just 1-2 lines of code change.
\n\n![](\"https://i.ibb.co/V9wc85F/tboard1.gif\")
\n\nPlease do check out the dataset used for training and the notebook for fusing bounding boxes with Weighted Boxes Fusion.
\n\nVinBigData COCO Dataset 3x Downsampled\n\nDATASET LINK - https://www.kaggle.com/sreevishnudamodaran/vinbigdata-coco-dataset-with-wbf-3x-downscaled\n\nVinBigData - Fusing Bboxes + Coco Dataset Creation Notebook\n\nNOTEBOOK LINK - https://www.kaggle.com/sreevishnudamodaran/vinbigdata-fusing-bboxes-coco-dataset\n\n"},{"metadata":{},"cell_type":"markdown","source":"## Load the Latest Checkpoint"},{"metadata":{"trusted":true},"cell_type":"code","source":"last_ckpt = Path(sorted(glob.glob(os.path.join(model_dir,'ckpt-*')))[-1]).stem\nlast_ckpt","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"configs = config_util.get_configs_from_pipeline_file(pipeline_file)\nmodel_config = configs['model']\ndetection_model = model_builder.build(model_config=model_config, is_training=False)\n\n## Restore checkpoint\nckpt = tf.compat.v2.train.Checkpoint(model=detection_model)\nckpt.restore(os.path.join(model_dir, last_ckpt))\n\ndef get_model_detection_function(model):\n \"\"\"Get a tf.function for detection.\"\"\"\n @tf.function\n def detect_fn(image):\n \"\"\"Detect objects in image.\"\"\"\n image, shapes = model.preprocess(image)\n prediction_dict = model.predict(image, shapes)\n detections = model.postprocess(prediction_dict, shapes)\n return detections, prediction_dict, tf.reshape(shapes, [-1])\n return detect_fn\n\ndetect_fn = get_model_detection_function(detection_model)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Load Label Map File For Scoring & Visualization"},{"metadata":{"trusted":true},"cell_type":"code","source":"## Map labels for Inference\nlabel_map_path = configs['eval_input_config'].label_map_path\nlabel_map = label_map_util.load_labelmap(label_map_path)\ncategories = label_map_util.convert_label_map_to_categories(\n label_map,\n max_num_classes=label_map_util.get_max_label_map_index(label_map),\n use_display_name=True)\ncategory_index = label_map_util.create_category_index(categories)\nlabel_map_dict = label_map_util.get_label_map_dict(label_map, use_display_name=True)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Score on Sample Images\n\n### Helper Functions for Visualization"},{"metadata":{"trusted":true},"cell_type":"code","source":"def plot_imgs(imgs, cols=2, size=10, is_rgb=True, title=\"\", cmap='gray', img_size=None):\n rows = len(imgs)//cols + 1\n fig = plt.figure(figsize=(round(cols*size*0.7), rows*size))\n for i, img in enumerate(imgs):\n if img_size is not None:\n img = cv2.resize(img, img_size)\n fig.add_subplot(rows, cols, i+1)\n plt.imshow(img, cmap=cmap)\n plt.suptitle(title) \n \ndef draw_bbox(image, box, label, color): \n alpha = 0.1\n alpha_box = 0.4\n overlay_bbox = image.copy()\n overlay_text = image.copy()\n output = image.copy()\n output = cv2.rectangle(output, (box[0], box[1]), (box[2], box[3]),\n color, 2)\n\n text_width, text_height = cv2.getTextSize(label.upper(), cv2.FONT_HERSHEY_SIMPLEX, 0.6, 1)[0]\n cv2.rectangle(overlay_bbox, (box[0], box[1]), (box[2], box[3]),\n color, -1)\n cv2.addWeighted(overlay_bbox, alpha, output, 1 - alpha, 0, output)\n \n cv2.rectangle(overlay_text, (box[0], box[1]-7-text_height),\n (box[0]+text_width+2, box[1]), (0, 0, 0), -1)\n \n cv2.addWeighted(overlay_text, alpha_box, output, 1 - alpha_box, 0, output)\n cv2.putText(output, label.upper(), (box[0], box[1]-5),\n cv2.FONT_HERSHEY_SIMPLEX, 0.6, (255, 255, 255), 2, cv2.LINE_AA)\n return output","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"val_images = glob.glob('../input/vinbigdata-coco-dataset-with-wbf-3x-downscaled/vinbigdata-coco-dataset-with-wbf-3x-downscaled/val_images/*.jpg')\n\nviz_images = []\nfor img_path in val_images[:4]:\n image_np = cv2.imread(img_path)\n input_tensor = tf.convert_to_tensor(np.expand_dims(image_np, 0),\n dtype=tf.float32)\n detections, predictions_dict, shapes = detect_fn(input_tensor)\n label_id_offset = 1\n image_np_with_detections = image_np.copy()\n\n label2color = [[59, 238, 119], [222, 21, 229], [94, 49, 164], [206, 221, 133], [117, 75, 3],\n [210, 224, 119], [211, 176, 166], [63, 7, 197], [102, 65, 77], [194, 134, 175],\n [209, 219, 50], [255, 44, 47], [89, 125, 149], [110, 27, 100]]\n \n min_score_thresh = 0.4\n width, height, _ = image_np.shape\n boxes = detections['detection_boxes'][0].numpy()\n boxes = boxes[:,[1, 0, 3, 2]]*np.array([height, width, height, width])\n \n for box, label_id, score in zip(boxes,\n (detections['detection_classes'][0].numpy() + label_id_offset).astype(int),\n detections['detection_scores'][0].numpy()):\n if (score > min_score_thresh):\n image_np_with_detections = draw_bbox(image_np_with_detections, list(np.int_(box)),\n category_index[label_id]['name']+'_'+str(round(score*100,1))+'%',\n label2color[label_id-1])\n \n viz_images.append(image_np_with_detections)\n\nplot_imgs(viz_images, cols=2, size=10, cmap=None)\nplt.savefig('inference_sample.png')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"# !rm -r ./models\n# !rm -r ./efficientdet_d1_coco17_tpu-32","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"THANK YOU! PLEASE UPVOTE
\n\nHOPE IT WAS USEFUL
\n\nTuning & updation in progress.
"}],"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}