Skip to content

F
Ffmpeg

小白菜888 / Ffmpeg

通知 3
Star 0
Fork 0
F
Ffmpeg

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

切换分支/标签
  1. 25 6月, 2020 5 次提交
    • T
      dnn_backend_native_layer_mathunary: add atan support · 13f5613e
      由 Ting Fu 提交于 
      It can be tested with the model generated with below python script:

import tensorflow as tf
import numpy as np
import imageio

in_img = imageio.imread('input.jpeg')
in_img = in_img.astype(np.float32)/255.0
in_data = in_img[np.newaxis, :]

x = tf.placeholder(tf.float32, shape=[1, None, None, 3], name='dnn_in')
x1 = tf.atan(x)
x2 = tf.divide(x1, 3.1416/4) # pi/4
y = tf.identity(x2, name='dnn_out')

sess=tf.Session()
sess.run(tf.global_variables_initializer())

graph_def = tf.graph_util.convert_variables_to_constants(sess, sess.graph_def, ['dnn_out'])
tf.train.write_graph(graph_def, '.', 'image_process.pb', as_text=False)

print("image_process.pb generated, please use \
path_to_ffmpeg/tools/python/convert.py to generate image_process.model\n")

output = sess.run(y, feed_dict={x: in_data})
imageio.imsave("out.jpg", np.squeeze(output))
Signed-off-by: NTing Fu <ting.fu@intel.com>
Signed-off-by: 郭叶军's avatarGuo Yejun <yejun.guo@intel.com>
      13f5613e
    • T
      dnn-layer-math-unary-test: add unit test for acos · 130c6001
      由 Ting Fu 提交于 
      Signed-off-by: NTing Fu <ting.fu@intel.com>
Signed-off-by: 郭叶军's avatarGuo Yejun <yejun.guo@intel.com>
      130c6001
    • T
      dnn_backend_native_layer_mathunary: add acos support · 461485fe
      由 Ting Fu 提交于 
      It can be tested with the model generated with below python script:

import tensorflow as tf
import numpy as np
import imageio

in_img = imageio.imread('input.jpeg')
in_img = in_img.astype(np.float32)/255.0
in_data = in_img[np.newaxis, :]

x = tf.placeholder(tf.float32, shape=[1, None, None, 3], name='dnn_in')
x1 = tf.acos(x)
x2 = tf.divide(x1, 3.1416/2) # pi/2
y = tf.identity(x2, name='dnn_out')

sess=tf.Session()
sess.run(tf.global_variables_initializer())

graph_def = tf.graph_util.convert_variables_to_constants(sess, sess.graph_def, ['dnn_out'])
tf.train.write_graph(graph_def, '.', 'image_process.pb', as_text=False)

print("image_process.pb generated, please use \
path_to_ffmpeg/tools/python/convert.py to generate image_process.model\n")

output = sess.run(y, feed_dict={x: in_data})
imageio.imsave("out.jpg", np.squeeze(output))
Signed-off-by: NTing Fu <ting.fu@intel.com>
Signed-off-by: 郭叶军's avatarGuo Yejun <yejun.guo@intel.com>
      461485fe
    • T
      dnn-layer-math-unary-test: add unit test for asin · 057f6ee7
      由 Ting Fu 提交于 
      Signed-off-by: NTing Fu <ting.fu@intel.com>
Signed-off-by: 郭叶军's avatarGuo Yejun <yejun.guo@intel.com>
      057f6ee7
    • T
      dnn_backend_native_layer_mathunary: add asin support · 486c0c41
      由 Ting Fu 提交于 
      It can be tested with the model generated with below python script:

import tensorflow as tf
import numpy as np
import imageio

in_img = imageio.imread('input.jpeg')
in_img = in_img.astype(np.float32)/255.0
in_data = in_img[np.newaxis, :]

x = tf.placeholder(tf.float32, shape=[1, None, None, 3], name='dnn_in')
x1 = tf.asin(x)
x2 = tf.divide(x1, 3.1416/2) # pi/2
y = tf.identity(x2, name='dnn_out')

sess=tf.Session()
sess.run(tf.global_variables_initializer())

graph_def = tf.graph_util.convert_variables_to_constants(sess, sess.graph_def, ['dnn_out'])
tf.train.write_graph(graph_def, '.', 'image_process.pb', as_text=False)

print("image_process.pb generated, please use \
path_to_ffmpeg/tools/python/convert.py to generate image_process.model\n")

output = sess.run(y, feed_dict={x: in_data})
imageio.imsave("out.jpg", np.squeeze(output))
Signed-off-by: NTing Fu <ting.fu@intel.com>
Signed-off-by: 郭叶军's avatarGuo Yejun <yejun.guo@intel.com>
      486c0c41
  3. 24 6月, 2020 7 次提交
  5. 23 6月, 2020 4 次提交
  7. 22 6月, 2020 20 次提交
  9. 21 6月, 2020 4 次提交