Add files via upload

notebook for training, testing added. Config file added

Author: vijendra1125

mask_rcnn_eval.ipynb

@@ -0,0 +1 @@
+{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"mask_rcnn_eval.ipynb","version":"0.3.2","provenance":[],"private_outputs":true,"collapsed_sections":[]},"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"accelerator":"GPU"},"cells":[{"metadata":{"id":"V8-yl-s-WKMG","colab_type":"text"},"cell_type":"markdown","source":["# UE ROLL Blue speaker detection\n","A model trained to detect Blue UE roll blutooth speaker.\n","Only 16 images has been used for current training. Performace could be increased using more images."]},{"metadata":{"id":"1Z_8-XxaPLNX","colab_type":"text"},"cell_type":"markdown","source":["#Environment Setup"]},{"metadata":{"id":"ZT31NO9WGpRD","colab_type":"code","colab":{}},"cell_type":"code","source":["!apt-get install protobuf-compiler python-pil python-lxml python-tk\n","!pip install Cython\n","!pip install jupyter\n","!pip install matplotlib\n","\n","!git clone https://github.com/tensorflow/models.git\n","\n","%cd /content/models/research\n","\n","!protoc object_detection/protos/*.proto --python_out=.\n","\n","%set_env PYTHONPATH=/content/models/research:/content/models/research/slim\n","\n","!python object_detection/builders/model_builder_test.py"],"execution_count":0,"outputs":[]},{"metadata":{"id":"kFSqkTCdWKMI","colab_type":"text"},"cell_type":"markdown","source":["# Imports"]},{"metadata":{"id":"hV4P5gyTWKMI","colab_type":"code","colab":{}},"cell_type":"code","source":["import numpy as np\n","import os\n","import six.moves.urllib as urllib\n","import sys\n","import tarfile\n","import tensorflow as tf\n","import zipfile\n","\n","from collections import defaultdict\n","from io import StringIO\n","from matplotlib import pyplot as plt\n","from PIL import Image\n","\n","# This is needed since the notebook is stored in the object_detection folder.\n","sys.path.append(\"..\")\n","from object_detection.utils import ops as utils_ops\n","from object_detection.utils import label_map_util\n","from object_detection.utils import visualization_utils as vis_util\n","\n","# This is needed to display the images.\n","%matplotlib inline\n"],"execution_count":0,"outputs":[]},{"metadata":{"id":"cfn_tRFOWKMO","colab_type":"text"},"cell_type":"markdown","source":["# Model preparation "]},{"metadata":{"id":"X_sEBLpVWKMQ","colab_type":"text"},"cell_type":"markdown","source":["## Variables\n","\n","Any model exported using the `export_inference_graph.py` tool can be loaded here simply by changing `PATH_TO_FROZEN_GRAPH` to point to a new .pb file.  \n","\n","By default we use an \"SSD with Mobilenet\" model here. See the [detection model zoo](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md) for a list of other models that can be run out-of-the-box with varying speeds and accuracies."]},{"metadata":{"id":"VyPz_t8WWKMQ","colab_type":"code","colab":{}},"cell_type":"code","source":["\n","\n","# Path to frozen detection graph. This is the actual model that is used for the object detection.\n","PATH_TO_FROZEN_GRAPH = '/content/drive/learning/DL/projects/object_detection/multiple_object_mask/IG/frozen_inference_graph.pb'\n","\n","# List of the strings that is used to add correct label for each box.\n","PATH_TO_LABELS = '/content/drive/learning/DL/projects/object_detection/multiple_object_mask/dataset/label.pbtxt'\n","\n","#Number of classes\n","NUM_CLASSES = 2"],"execution_count":0,"outputs":[]},{"metadata":{"id":"YBcB9QHLWKMU","colab_type":"text"},"cell_type":"markdown","source":["## Load a (frozen) Tensorflow model into memory."]},{"metadata":{"id":"KezjCRVvWKMV","colab_type":"code","colab":{}},"cell_type":"code","source":["detection_graph = tf.Graph()\n","with detection_graph.as_default():\n","  od_graph_def = tf.GraphDef()\n","  with tf.gfile.GFile(PATH_TO_FROZEN_GRAPH, 'rb') as fid:\n","    serialized_graph = fid.read()\n","    od_graph_def.ParseFromString(serialized_graph)\n","    tf.import_graph_def(od_graph_def, name='')"],"execution_count":0,"outputs":[]},{"metadata":{"id":"_1MVVTcLWKMW","colab_type":"text"},"cell_type":"markdown","source":["## Loading label map\n","Label maps map indices to category names, so that when our convolution network predicts `5`, we know that this corresponds to `airplane`.  Here we use internal utility functions, but anything that returns a dictionary mapping integers to appropriate string labels would be fine"]},{"metadata":{"id":"hDbpHkiWWKMX","colab_type":"code","colab":{}},"cell_type":"code","source":["label_map = label_map_util.load_labelmap(PATH_TO_LABELS)\n","categories = label_map_util.convert_label_map_to_categories(label_map, max_num_classes=NUM_CLASSES, use_display_name=True)\n","category_index = label_map_util.create_category_index(categories)"],"execution_count":0,"outputs":[]},{"metadata":{"id":"EFsoUHvbWKMZ","colab_type":"text"},"cell_type":"markdown","source":["## Helper code"]},{"metadata":{"id":"aSlYc3JkWKMa","colab_type":"code","colab":{}},"cell_type":"code","source":["def load_image_into_numpy_array(image):\n","  (im_width, im_height) = image.size\n","  return np.array(image.getdata()).reshape(\n","      (im_height, im_width, 3)).astype(np.uint8)"],"execution_count":0,"outputs":[]},{"metadata":{"id":"H0_1AGhrWKMc","colab_type":"text"},"cell_type":"markdown","source":["# Detection"]},{"metadata":{"id":"jG-zn5ykWKMd","colab_type":"code","colab":{}},"cell_type":"code","source":["# If you want to test the code with your images, just add path to the images to the TEST_IMAGE_PATHS.\n","PATH_TO_TEST_IMAGES_DIR = '/content/drive/learning/DL/projects/object_detection/multiple_object_mask/dataset/testImages'\n","TEST_IMAGE_PATHS = [ os.path.join(PATH_TO_TEST_IMAGES_DIR, 'image{}.jpg'.format(i)) for i in range(1, 7) ]\n","\n","# Size, in inches, of the output images.\n","IMAGE_SIZE = (12, 8)"],"execution_count":0,"outputs":[]},{"metadata":{"id":"92BHxzcNWKMf","colab_type":"code","colab":{}},"cell_type":"code","source":["def run_inference_for_single_image(image, graph):\n","  with graph.as_default():\n","    with tf.Session() as sess:\n","      # Get handles to input and output tensors\n","      ops = tf.get_default_graph().get_operations()\n","      all_tensor_names = {output.name for op in ops for output in op.outputs}\n","      tensor_dict = {}\n","      for key in [\n","          'num_detections', 'detection_boxes', 'detection_scores',\n","          'detection_classes', 'detection_masks'\n","      ]:\n","        tensor_name = key + ':0'\n","        if tensor_name in all_tensor_names:\n","          tensor_dict[key] = tf.get_default_graph().get_tensor_by_name(\n","              tensor_name)\n","      if 'detection_masks' in tensor_dict:\n","        # The following processing is only for single image\n","        detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0])\n","        detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0])\n","        # Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.\n","        real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32)\n","        detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1])\n","        detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1])\n","        detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(\n","            detection_masks, detection_boxes, image.shape[0], image.shape[1])\n","        detection_masks_reframed = tf.cast(\n","            tf.greater(detection_masks_reframed, 0.5), tf.uint8)\n","        # Follow the convention by adding back the batch dimension\n","        tensor_dict['detection_masks'] = tf.expand_dims(\n","            detection_masks_reframed, 0)\n","      image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0')\n","\n","      # Run inference\n","      output_dict = sess.run(tensor_dict,\n","                             feed_dict={image_tensor: np.expand_dims(image, 0)})\n","\n","      # all outputs are float32 numpy arrays, so convert types as appropriate\n","      output_dict['num_detections'] = int(output_dict['num_detections'][0])\n","      output_dict['detection_classes'] = output_dict[\n","          'detection_classes'][0].astype(np.uint8)\n","      output_dict['detection_boxes'] = output_dict['detection_boxes'][0]\n","      output_dict['detection_scores'] = output_dict['detection_scores'][0]\n","      if 'detection_masks' in output_dict:\n","        output_dict['detection_masks'] = output_dict['detection_masks'][0]\n","  return output_dict"],"execution_count":0,"outputs":[]},{"metadata":{"id":"3a5wMHN8WKMh","colab_type":"code","colab":{}},"cell_type":"code","source":["for image_path in TEST_IMAGE_PATHS:\n","  image = Image.open(image_path)\n","  # the array based representation of the image will be used later in order to prepare the\n","  # result image with boxes and labels on it.\n","  image_np = load_image_into_numpy_array(image)\n","  # Expand dimensions since the model expects images to have shape: [1, None, None, 3]\n","  image_np_expanded = np.expand_dims(image_np, axis=0)\n","  # Actual detection.\n","  output_dict = run_inference_for_single_image(image_np, detection_graph)\n","  # Visualization of the results of a detection.\n","  vis_util.visualize_boxes_and_labels_on_image_array(\n","      image_np,\n","      output_dict['detection_boxes'],\n","      output_dict['detection_classes'],\n","      output_dict['detection_scores'],\n","      category_index,\n","      instance_masks=output_dict.get('detection_masks'),\n","      use_normalized_coordinates=True,\n","      line_thickness=8)\n","  fig = plt.figure(figsize=IMAGE_SIZE)\n","  ax = fig.gca()\n","  ax.grid(False)\n","  plt.imshow(image_np)"],"execution_count":0,"outputs":[]},{"metadata":{"id":"HycEbEKkztwM","colab_type":"code","colab":{}},"cell_type":"code","source":[""],"execution_count":0,"outputs":[]}]}

mask_rcnn_inception_v2_coco.config

@@ -0,0 +1,165 @@
+# Mask R-CNN with Inception V2
+# Configured for MSCOCO Dataset.
+# Users should configure the fine_tune_checkpoint field in the train config as
+# well as the label_map_path and input_path fields in the train_input_reader and
+# eval_input_reader. Search for "PATH_TO_BE_CONFIGURED" to find the fields that
+# should be configured.
+
+model {
+  faster_rcnn {
+    num_classes: 90
+    image_resizer {
+      keep_aspect_ratio_resizer {
+        min_dimension: 800
+        max_dimension: 1365
+      }
+    }
+    number_of_stages: 3
+    feature_extractor {
+      type: 'faster_rcnn_inception_v2'
+      first_stage_features_stride: 16
+    }
+    first_stage_anchor_generator {
+      grid_anchor_generator {
+        scales: [0.25, 0.5, 1.0, 2.0]
+        aspect_ratios: [0.5, 1.0, 2.0]
+        height_stride: 16
+        width_stride: 16
+      }
+    }
+    first_stage_box_predictor_conv_hyperparams {
+      op: CONV
+      regularizer {
+        l2_regularizer {
+          weight: 0.0
+        }
+      }
+      initializer {
+        truncated_normal_initializer {
+          stddev: 0.01
+        }
+      }
+    }
+    first_stage_nms_score_threshold: 0.0
+    first_stage_nms_iou_threshold: 0.7
+    first_stage_max_proposals: 300
+    first_stage_localization_loss_weight: 2.0
+    first_stage_objectness_loss_weight: 1.0
+    initial_crop_size: 14
+    maxpool_kernel_size: 2
+    maxpool_stride: 2
+    second_stage_box_predictor {
+      mask_rcnn_box_predictor {
+        use_dropout: false
+        dropout_keep_probability: 1.0
+        predict_instance_masks: true
+        mask_height: 15
+        mask_width: 15
+        mask_prediction_conv_depth: 0
+        mask_prediction_num_conv_layers: 2
+        fc_hyperparams {
+          op: FC
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            variance_scaling_initializer {
+              factor: 1.0
+              uniform: true
+              mode: FAN_AVG
+            }
+          }
+        }
+        conv_hyperparams {
+          op: CONV
+          regularizer {
+            l2_regularizer {
+              weight: 0.0
+            }
+          }
+          initializer {
+            truncated_normal_initializer {
+              stddev: 0.01
+            }
+          }
+        }
+      }
+    }
+    second_stage_post_processing {
+      batch_non_max_suppression {
+        score_threshold: 0.0
+        iou_threshold: 0.6
+        max_detections_per_class: 100
+        max_total_detections: 300
+      }
+      score_converter: SOFTMAX
+    }
+    second_stage_localization_loss_weight: 2.0
+    second_stage_classification_loss_weight: 1.0
+    second_stage_mask_prediction_loss_weight: 4.0
+  }
+}
+
+train_config: {
+  batch_size: 1
+  optimizer {
+    momentum_optimizer: {
+      learning_rate: {
+        manual_step_learning_rate {
+          initial_learning_rate: 0.0002
+          schedule {
+            step: 900000
+            learning_rate: .00002
+          }
+          schedule {
+            step: 1200000
+            learning_rate: .000002
+          }
+        }
+      }
+      momentum_optimizer_value: 0.9
+    }
+    use_moving_average: false
+  }
+  gradient_clipping_by_norm: 10.0
+  fine_tune_checkpoint: '/content/drive/learning/DL/pre_trained_models/mask_rcnn_inception_v2_coco/model.ckpt'
+  from_detection_checkpoint: true
+  # Note: The below line limits the training process to 200K steps, which we
+  # empirically found to be sufficient enough to train the pets dataset. This
+  # effectively bypasses the learning rate schedule (the learning rate will
+  # never decay). Remove the below line to train indefinitely.
+  num_steps: 2000
+  data_augmentation_options {
+    random_horizontal_flip {
+    }
+  }
+}
+
+train_input_reader: {
+  tf_record_input_reader {
+    input_path: '/content/drive/learning/DL/projects/object_detection/multiple_object_mask/dataset/train.record'
+  }
+  label_map_path: '/content/drive/learning/DL/projects/object_detection/multiple_object_mask/dataset/label.pbtxt'
+  load_instance_masks: true
+  mask_type: PNG_MASKS
+}
+
+eval_config: {
+  num_examples: 8000
+  # Note: The below line limits the evaluation process to 10 evaluations.
+  # Remove the below line to evaluate indefinitely.
+  max_evals: 10
+}
+
+eval_input_reader: {
+  tf_record_input_reader {
+    input_path: '/content/drive/learning/DL/projects/object_detection/multiple_object_mask/dataset/train.record'
+  }
+  label_map_path: '/content/drive/learning/DL/projects/object_detection/multiple_object_mask/dataset/label.pbtxt'
+  load_instance_masks: true
+  mask_type: PNG_MASKS
+  shuffle: false
+  num_readers: 1
+}

mask_rcnn_train.ipynb

@@ -0,0 +1 @@
+{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"mask_rcnn_train.ipynb","version":"0.3.2","provenance":[],"private_outputs":true,"collapsed_sections":[]},"kernelspec":{"name":"python3","display_name":"Python 3"},"accelerator":"GPU"},"cells":[{"metadata":{"id":"kBwSn8yCQeOt","colab_type":"text"},"cell_type":"markdown","source":["#Environment Setup"]},{"metadata":{"id":"9vV5WmzT2Aey","colab_type":"code","colab":{}},"cell_type":"code","source":["!apt-get install protobuf-compiler python-pil python-lxml python-tk\n","!pip install Cython\n","!pip install jupyter\n","!pip install matplotlib\n","\n","!git clone https://github.com/tensorflow/models.git\n","\n","%cd /content/models/research\n","\n","!protoc object_detection/protos/*.proto --python_out=.\n","\n","%set_env PYTHONPATH=/content/models/research:/content/models/research/slim\n","\n","!python object_detection/builders/model_builder_test.py"],"execution_count":0,"outputs":[]},{"metadata":{"id":"7T3RDLqtU6IT","colab_type":"text"},"cell_type":"markdown","source":["#Train Model"]},{"metadata":{"id":"tDKvkhu32k1I","colab_type":"code","colab":{}},"cell_type":"code","source":["!python object_detection/legacy/train.py \\\n","--train_dir=/content/drive/learning/DL/projects/object_detection/multiple_object_mask/CP \\\n","--pipeline_config_path=/content/drive/learning/DL/projects/object_detection/multiple_object_mask/mask_rcnn_inception_v2_coco.config"],"execution_count":0,"outputs":[]},{"metadata":{"id":"dEiNEqC5U-mP","colab_type":"text"},"cell_type":"markdown","source":["#Save inference graph"]},{"metadata":{"id":"u_ixlaX62mMF","colab_type":"code","colab":{}},"cell_type":"code","source":["!python object_detection/export_inference_graph.py \\\n","--input_type=image_tensor \\\n","--pipeline_config_path=/content/drive/learning/DL/projects/object_detection/speaker_detection_mask/mask_rcnn_inception_v2_coco.config \\\n","--trained_checkpoint_prefix=/content/drive/learning/DL/projects/object_detection/multiple_object_mask/CP/model.ckpt-2000 \\\n","--output_directory=/content/drive/learning/DL/projects/object_detection/multiple_object_mask/IG"],"execution_count":0,"outputs":[]},{"metadata":{"id":"oiSnn-DhMDFK","colab_type":"code","colab":{}},"cell_type":"code","source":[""],"execution_count":0,"outputs":[]}]}