def run_inference_for_single_image(model, image): image = np.asarray(image) input_tensor = tf.convert_to_tensor(image) input_tensor = input_tensor[tf.newaxis] output_dict = model(input_tensor) num_detections = int(output_dict.pop('num_detections')) output_dict = { key: value[0, :num_detections].numpy() for key, value in output_dict.items() } output_dict['num_detections'] = num_detections output_dict['detection_classes'] = output_dict['detection_classes'].astype( np.int64) if 'detection_masks' in output_dict: detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks( output_dict['detection_masks'], output_dict['detection_boxes'], image.shape[0], image.shape[1]) detection_masks_reframed = tf.cast(detection_masks_reframed > 0.5, tf.unit8) output_dict[ 'detection_masks_reframed'] = detection_masks_reframed.numpy() return output_dict
def run_inference_for_single_image(image, graph): if 'detection_masks' in tensor_dict: # The following processing is only for single image detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0]) detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0]) # Reframe is required to translate mask from box coordinates to image coordinates and fit the image size. real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32) detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1]) detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1]) detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks( detection_masks, detection_boxes, image.shape[0], image.shape[1]) detection_masks_reframed = tf.cast( tf.greater(detection_masks_reframed, 0.5), tf.uint8) # Follow the convention by adding back the batch dimension tensor_dict['detection_masks'] = tf.expand_dims( detection_masks_reframed, 0) image_tensor = tf.compat.v1.get_default_graph().get_tensor_by_name( 'image_tensor:0') # Run inference output_dict = sess.run(tensor_dict, feed_dict={image_tensor: np.expand_dims(image, 0)}) # all outputs are float32 numpy arrays, so convert types as appropriate output_dict['num_detections'] = int(output_dict['num_detections'][0]) output_dict['detection_classes'] = output_dict['detection_classes'][ 0].astype(np.uint8) output_dict['detection_boxes'] = output_dict['detection_boxes'][0] output_dict['detection_scores'] = output_dict['detection_scores'][0] if 'detection_masks' in output_dict: output_dict['detection_masks'] = output_dict['detection_masks'][0] return output_dict
def run_inference_for_single_image(model, image): image = np.asarray(image) # The input needs to be a tensor, convert it using `tf.convert_to_tensor`. input_tensor = tf.convert_to_tensor(image) # The model expects a batch of images, so add an axis with `tf.newaxis`. input_tensor = input_tensor[tf.newaxis, ...] # Run inference output_dict = model(input_tensor) # All outputs are batches tensors. # Convert to numpy arrays, and take index [0] to remove the batch dimension. # We're only interested in the first num_detections. num_detections = int(output_dict.pop('num_detections')) output_dict = {key: value[0, :num_detections].numpy() for key, value in output_dict.items()} output_dict['num_detections'] = num_detections # detection_classes should be ints. output_dict['detection_classes'] = output_dict['detection_classes'].astype(np.int64) # Handle models with masks: if 'detection_masks' in output_dict: # Reframe the the bbox mask to the image size. detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks( output_dict['detection_masks'], output_dict['detection_boxes'], image.shape[0], image.shape[1]) detection_masks_reframed = tf.cast(detection_masks_reframed > 0.5, tf.uint8) output_dict['detection_masks_reframed'] = detection_masks_reframed.numpy() return output_dict
def run_inference_for_single_image(image,sess): '''DOCTRING This predicts the bounding boxes and class type for an image. This is pretty much the same as the object_detection_tutorial.ipynb, but I moved the 2 opening with statements into above a for loop, s the graph isn't re-loaded everytime ------------- INPUT: image: the image you want to predict after it has been loaded into a numpy array and had it's dimensions expanded graph: the detection_graph you loaded from a checkpoint, after it has gone through the long function name above ------------- RETURNS: output_dict: 3 keys, detection_boxes, detection_scores, detection_classes ''' # Get handles to input and output tensors ops = tf.get_default_graph().get_operations() all_tensor_names = {output.name for op in ops for output in op.outputs} tensor_dict = {} for key in [ 'num_detections', 'detection_boxes', 'detection_scores', 'detection_classes', 'detection_masks' ]: tensor_name = key + ':0' if tensor_name in all_tensor_names: tensor_dict[key] = tf.get_default_graph().get_tensor_by_name( tensor_name) if 'detection_masks' in tensor_dict: # The following processing is only for single image detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0]) detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0]) # Reframe is required to translate mask from box coordinates to image coordinates and fit the image size. real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32) detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1]) detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1]) detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks( detection_masks, detection_boxes, image.shape[0], image.shape[1]) detection_masks_reframed = tf.cast( tf.greater(detection_masks_reframed, 0.5), tf.uint8) # Follow the convention by adding back the batch dimension tensor_dict['detection_masks'] = tf.expand_dims( detection_masks_reframed, 0) image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0') # Run inference output_dict = sess.run(tensor_dict, feed_dict={image_tensor: np.expand_dims(image, 0)}) # all outputs are float32 numpy arrays, so convert types as appropriate output_dict['num_detections'] = int(output_dict['num_detections'][0]) output_dict['detection_classes'] = output_dict[ 'detection_classes'][0].astype(np.uint8) output_dict['detection_boxes'] = output_dict['detection_boxes'][0] output_dict['detection_scores'] = output_dict['detection_scores'][0] if 'detection_masks' in output_dict: output_dict['detection_masks'] = output_dict['detection_masks'][0] return output_dict
def run_inference_for_single_image(image, graph): with graph.as_default(): with tf.Session() as sess: # Get handles to input and output tensors ops = tf.get_default_graph().get_operations() all_tensor_names = {output.name for op in ops for output in op.outputs} tensor_dict = {} for key in [ 'num_detections', 'detection_boxes', 'detection_scores', 'detection_classes', 'detection_masks' ]: tensor_name = key + ':0' if tensor_name in all_tensor_names: tensor_dict[key] = tf.get_default_graph().get_tensor_by_name( tensor_name) if 'detection_masks' in tensor_dict: # The following processing is only for single image detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0]) detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0]) # Reframe is required to translate mask from box coordinates to image coordinates and fit the image size. real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32) detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1]) detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1]) detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks( detection_masks, detection_boxes, image.shape[1], image.shape[2]) detection_masks_reframed = tf.cast( tf.greater(detection_masks_reframed, 0.5), tf.uint8) # Follow the convention by adding back the batch dimension tensor_dict['detection_masks'] = tf.expand_dims( detection_masks_reframed, 0) image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0') # Run inference output_dict = sess.run(tensor_dict, feed_dict={image_tensor: image}) # all outputs are float32 numpy arrays, so convert types as appropriate output_dict['num_detections'] = int(output_dict['num_detections'][0]) output_dict['detection_classes'] = output_dict[ 'detection_classes'][0].astype(np.int64) output_dict['detection_boxes'] = output_dict['detection_boxes'][0] output_dict['detection_scores'] = output_dict['detection_scores'][0] if 'detection_masks' in output_dict: output_dict['detection_masks'] = output_dict['detection_masks'][0] return output_dict
]: tensor_name = key + ':0' if tensor_name in all_tensor_names: tensor_dict[key] = tf.get_default_graph().get_tensor_by_name( tensor_name) if 'detection_masks' in tensor_dict: # The following processing is only for single image detection_boxes = tf.squeeze(tensor_dict['detection_boxes'], [0]) detection_masks = tf.squeeze(tensor_dict['detection_masks'], [0]) # Reframe is required to translate mask from box coordinates to image coordinates and fit the image size. real_num_detection = tf.cast(tensor_dict['num_detections'][0], tf.int32) detection_boxes = tf.slice(detection_boxes, [0, 0], [real_num_detection, -1]) detection_masks = tf.slice(detection_masks, [0, 0, 0], [real_num_detection, -1, -1]) detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks( detection_masks, detection_boxes, image.shape[1], image.shape[2]) detection_masks_reframed = tf.cast( tf.greater(detection_masks_reframed, 0.5), tf.uint8) # Follow the convention by adding back the batch dimension tensor_dict['detection_masks'] = tf.expand_dims(detection_masks_reframed, 0) image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0') def gen(): myrtmp_addr = "rtmp://localhost/live/indycar live=1" cap = cv2.VideoCapture(myrtmp_addr) while True: ret, frame = cap.read()