From 4b351120222f5fde688f37a465c78e9ef6668787 Mon Sep 17 00:00:00 2001
From: Liubov Batanina <piccione-mail@yandex.ru>
Date: Fri, 24 Jan 2020 16:30:10 +0300
Subject: [PATCH] Update sample

---
 samples/dnn/human_parsing.py | 76 ++++++++++++++++++------------------
 1 file changed, 39 insertions(+), 37 deletions(-)

diff --git a/samples/dnn/human_parsing.py b/samples/dnn/human_parsing.py
index 4a51c35af7..5bfe19aee7 100644
--- a/samples/dnn/human_parsing.py
+++ b/samples/dnn/human_parsing.py
@@ -1,45 +1,11 @@
+import argparse
 import cv2 as cv
 import numpy as np
-import argparse
 
 
 backends = (cv.dnn.DNN_BACKEND_DEFAULT, cv.dnn.DNN_BACKEND_INFERENCE_ENGINE, cv.dnn.DNN_BACKEND_OPENCV)
 targets = (cv.dnn.DNN_TARGET_CPU, cv.dnn.DNN_TARGET_OPENCL, cv.dnn.DNN_TARGET_OPENCL_FP16, cv.dnn.DNN_TARGET_MYRIAD)
 
-# To get 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())
-
 
 def preprocess(image_path):
     """
@@ -149,8 +115,9 @@ def parse_human(image_path, model_path, backend=cv.dnn.DNN_BACKEND_OPENCV, targe
 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', help='Path to input image. Skip this argument to capture frames from a camera.')
-    parser.add_argument('--model', '-m', required=True, help='Path to pb model.')
+    parser.add_argument('--input', '-i', help='Path to input image.')
+    parser.add_argument('--model', '-m', required=True, help='Path to pb model
+                        (https://drive.google.com/open?id=1XHvo111Gj1ZGoNUJt4Y4OsShrt_eUT34).')
     parser.add_argument('--backend', choices=backends, default=cv.dnn.DNN_BACKEND_DEFAULT, type=int,
                         help="Choose one of computation backends: "
                              "%d: automatically (by default), "
@@ -169,3 +136,38 @@ 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())