加快对象检测的预测
Speed up predictions for Object Detection
我正在努力为我的预测获得良好的 FPS。我是 运行 我对 Tesla K80 的预测，我想将我的预测速度至少提高 20 倍。这是我的代码：
def load_detection_graph(PATH_TO_CKPT):
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
return detection_graph
def load_image_into_numpy_array(image):
'''
convert image to numpy arrays
'''
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape((im_height, im_width, 3)).astype(np.uint8)
def run_inference_for_single_image(image, graph, filename):
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[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['filename'] = filename
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 predict_image(TEST_IMAGE_PATHS, PATH_TO_CKPT, category_index, save_path):
detection_graph = load_detection_graph(PATH_TO_CKPT)
prediction_dict = defaultdict()
start_time = time.time()
for image_path in TEST_IMAGE_PATHS:
toc = time.time()
filename = image_path
image = Image.open(image_path)
# the array based representation of the image will be used later in order to prepare the
# result image with boxes and labels on it.
image_np = load_image_into_numpy_array(image)
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image_np, axis=0)
# Actual detection.
output_dict = run_inference_for_single_image(image_np, detection_graph, filename)
# Visualization of the results of a detection.
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
output_dict['detection_boxes'],
output_dict['detection_classes'],
output_dict['detection_scores'],
category_index,
instance_masks=output_dict.get('detection_masks'),
use_normalized_coordinates=True,
line_thickness=1)
prediction_dict[filename] = output_dict
plt.figure(figsize=(8,6), dpi=100)
plt.imshow(image_np)
plt.savefig(save_path+'{}'.format(filename))
tic = time.time()
print('{0} saved in {1:.2f}sec'.format(filename, tic-toc))
end_time = time.time()
print('{0:.2f}min to predict all images'.format((end_time-start_time)/60))
with open('../predictions/predictions.pickle', 'wb') as f:
pickle.dump(prediction_dict, f)
return prediction_dict
现在每次检测大约需要 1.8 秒。这包括保存图像和绘制边界框。我不需要保存图像或绘制边界框，我只需要 output_dict。关于如何加快速度的任何建议？
优化 GPU/CPU 分配似乎可以提高性能，如所讨论的 here。在 GPU 上使 CNN 相关节点 运行 和在 CPU 上使其余节点（post 处理）运行 似乎给出比报告速度更高的推理速度。
而不是 运行 单图像推理，您应该对一批图像进行对象检测。不过图片需要大小相同。
检查这个 -
我观察到使用 skimage.io.imread() 或 cv2.imread() 加载图像的速度相当快。这些函数直接将图像加载为 numpy 数组。所以你可以跳过"image = Image.open(image_path)"和"image_np = load_image_into_numpy_array(image)"。只需确保 sess.run 中的 "image_tensor" 获得正确的维度。
此外，skimage 或 opencv 在保存图像方面比 matplotlib 更快
创建session是开销最大的操作，不要每次都重新创建，尽量复用session对象
我正在努力为我的预测获得良好的 FPS。我是 运行 我对 Tesla K80 的预测，我想将我的预测速度至少提高 20 倍。这是我的代码：
def load_detection_graph(PATH_TO_CKPT):
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
return detection_graph
def load_image_into_numpy_array(image):
'''
convert image to numpy arrays
'''
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape((im_height, im_width, 3)).astype(np.uint8)
def run_inference_for_single_image(image, graph, filename):
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[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['filename'] = filename
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 predict_image(TEST_IMAGE_PATHS, PATH_TO_CKPT, category_index, save_path):
detection_graph = load_detection_graph(PATH_TO_CKPT)
prediction_dict = defaultdict()
start_time = time.time()
for image_path in TEST_IMAGE_PATHS:
toc = time.time()
filename = image_path
image = Image.open(image_path)
# the array based representation of the image will be used later in order to prepare the
# result image with boxes and labels on it.
image_np = load_image_into_numpy_array(image)
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image_np, axis=0)
# Actual detection.
output_dict = run_inference_for_single_image(image_np, detection_graph, filename)
# Visualization of the results of a detection.
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
output_dict['detection_boxes'],
output_dict['detection_classes'],
output_dict['detection_scores'],
category_index,
instance_masks=output_dict.get('detection_masks'),
use_normalized_coordinates=True,
line_thickness=1)
prediction_dict[filename] = output_dict
plt.figure(figsize=(8,6), dpi=100)
plt.imshow(image_np)
plt.savefig(save_path+'{}'.format(filename))
tic = time.time()
print('{0} saved in {1:.2f}sec'.format(filename, tic-toc))
end_time = time.time()
print('{0:.2f}min to predict all images'.format((end_time-start_time)/60))
with open('../predictions/predictions.pickle', 'wb') as f:
pickle.dump(prediction_dict, f)
return prediction_dict
现在每次检测大约需要 1.8 秒。这包括保存图像和绘制边界框。我不需要保存图像或绘制边界框，我只需要 output_dict。关于如何加快速度的任何建议？
优化 GPU/CPU 分配似乎可以提高性能，如所讨论的 here。在 GPU 上使 CNN 相关节点 运行 和在 CPU 上使其余节点（post 处理）运行 似乎给出比报告速度更高的推理速度。
而不是 运行 单图像推理，您应该对一批图像进行对象检测。不过图片需要大小相同。
检查这个 -
我观察到使用 skimage.io.imread() 或 cv2.imread() 加载图像的速度相当快。这些函数直接将图像加载为 numpy 数组。所以你可以跳过"image = Image.open(image_path)"和"image_np = load_image_into_numpy_array(image)"。只需确保 sess.run 中的 "image_tensor" 获得正确的维度。
此外，skimage 或 opencv 在保存图像方面比 matplotlib 更快
创建session是开销最大的操作，不要每次都重新创建，尽量复用session对象