Move instruction

pull/16223/head
Liubov Batanina 5 years ago
parent 5790810c3a
commit 4a19ac5aca
  1. 4
      modules/dnn/include/opencv2/dnn/dnn.hpp
  2. 80
      samples/dnn/human_parsing.py

@ -47,9 +47,9 @@
#include "opencv2/core/async.hpp"
#if !defined CV_DOXYGEN && !defined CV_STATIC_ANALYSIS && !defined CV_DNN_DONT_ADD_EXPERIMENTAL_NS
#define CV__DNN_EXPERIMENTAL_NS_BEGIN namespace experimental_dnn_34_v15 {
#define CV__DNN_EXPERIMENTAL_NS_BEGIN namespace experimental_dnn_34_v16 {
#define CV__DNN_EXPERIMENTAL_NS_END }
namespace cv { namespace dnn { namespace experimental_dnn_34_v15 { } using namespace experimental_dnn_34_v15; }}
namespace cv { namespace dnn { namespace experimental_dnn_34_v16 { } using namespace experimental_dnn_34_v16; }}
#else
#define CV__DNN_EXPERIMENTAL_NS_BEGIN
#define CV__DNN_EXPERIMENTAL_NS_END

@ -1,6 +1,47 @@
#!/usr/bin/env python
'''
You can download the converted pb model from https://www.dropbox.com/s/qag9vzambhhkvxr/lip_jppnet_384.pb?dl=0
or convert the model yourself.
Follow these steps if you want to convert the original model yourself:
To get original .meta pre-trained model download https://drive.google.com/file/d/1BFVXgeln-bek8TCbRjN6utPAgRE0LJZg/view
For correct convert .meta to .pb model download original repository https://github.com/Engineering-Course/LIP_JPPNet
Change script evaluate_parsing_JPPNet-s2.py for human parsing
1. Remove preprocessing to create image_batch_origin:
with tf.name_scope("create_inputs"):
...
Add
image_batch_origin = tf.placeholder(tf.float32, shape=(2, None, None, 3), name='input')
2. Create input
image = cv2.imread(path/to/image)
image_rev = np.flip(image, axis=1)
input = np.stack([image, image_rev], axis=0)
3. Hardcode image_h and image_w shapes to determine output shapes.
We use default INPUT_SIZE = (384, 384) from evaluate_parsing_JPPNet-s2.py.
parsing_out1 = tf.reduce_mean(tf.stack([tf.image.resize_images(parsing_out1_100, INPUT_SIZE),
tf.image.resize_images(parsing_out1_075, INPUT_SIZE),
tf.image.resize_images(parsing_out1_125, INPUT_SIZE)]), axis=0)
Do similarly with parsing_out2, parsing_out3
4. Remove postprocessing. Last net operation:
raw_output = tf.reduce_mean(tf.stack([parsing_out1, parsing_out2, parsing_out3]), axis=0)
Change:
parsing_ = sess.run(raw_output, feed_dict={'input:0': input})
5. To save model after sess.run(...) add:
input_graph_def = tf.get_default_graph().as_graph_def()
output_node = "Mean_3"
output_graph_def = tf.graph_util.convert_variables_to_constants(sess, input_graph_def, output_node)
output_graph = "LIP_JPPNet.pb"
with tf.gfile.GFile(output_graph, "wb") as f:
f.write(output_graph_def.SerializeToString())'
'''
import argparse
import cv2 as cv
import numpy as np
import cv2 as cv
backends = (cv.dnn.DNN_BACKEND_DEFAULT, cv.dnn.DNN_BACKEND_INFERENCE_ENGINE, cv.dnn.DNN_BACKEND_OPENCV)
@ -116,7 +157,7 @@ if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Use this script to run human parsing using JPPNet',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--input', '-i', required=True, help='Path to input image.')
parser.add_argument('--model', '-m', required=True, help='Path to pb model(https://www.dropbox.com/s/qag9vzambhhkvxr/lip_jppnet_384.pb?dl=0).')
parser.add_argument('--model', '-m', required=True, help='Path to pb model.')
parser.add_argument('--backend', choices=backends, default=cv.dnn.DNN_BACKEND_DEFAULT, type=int,
help="Choose one of computation backends: "
"%d: automatically (by default), "
@ -135,38 +176,3 @@ if __name__ == '__main__':
cv.namedWindow(winName, cv.WINDOW_AUTOSIZE)
cv.imshow(winName, output)
cv.waitKey()
# To get original .meta pre-trained model download https://drive.google.com/file/d/1BFVXgeln-bek8TCbRjN6utPAgRE0LJZg/view
# For correct convert .meta to .pb model download original repository https://github.com/Engineering-Course/LIP_JPPNet
# Change script evaluate_parsing_JPPNet-s2.py for human parsing
# 1. Remove preprocessing to create image_batch_origin:
# - with tf.name_scope("create_inputs"):
# ...
# Add
# - image_batch_origin = tf.placeholder(tf.float32, shape=(2, None, None, 3), name='input')
#
# 2. Create input
# image = cv2.imread(path/to/image)
# image_rev = np.flip(image, axis=1)
# input = np.stack([image, image_rev], axis=0)
#
# 3. Hardcode image_h and image_w shapes to determine output shapes.
# We use default INPUT_SIZE = (384, 384) from evaluate_parsing_JPPNet-s2.py.
# - parsing_out1 = tf.reduce_mean(tf.stack([tf.image.resize_images(parsing_out1_100, INPUT_SIZE),
# tf.image.resize_images(parsing_out1_075, INPUT_SIZE),
# tf.image.resize_images(parsing_out1_125, INPUT_SIZE)]), axis=0)
# Do similarly with parsing_out2, parsing_out3
# 4. Remove postprocessing. Last net operation:
# raw_output = tf.reduce_mean(tf.stack([parsing_out1, parsing_out2, parsing_out3]), axis=0)
# Change:
# parsing_ = sess.run(raw_output, feed_dict={'input:0': input})
#
# 5. To save model after sess.run(...) add:
# input_graph_def = tf.get_default_graph().as_graph_def()
# output_node = "Mean_3"
# output_graph_def = tf.graph_util.convert_variables_to_constants(sess, input_graph_def, output_node)
#
# output_graph = "LIP_JPPNet.pb"
# with tf.gfile.GFile(output_graph, "wb") as f:
# f.write(output_graph_def.SerializeToString())

Loading…
Cancel
Save