1. 06 Jul, 2020 1 commit
  2. 02 Jul, 2020 2 commits
  3. 08 Jun, 2020 1 commit
  4. 07 Jun, 2020 2 commits
  5. 06 Jun, 2020 2 commits
  6. 03 Jun, 2020 1 commit
  7. 01 Jun, 2020 1 commit
  8. 30 May, 2020 11 commits
  9. 29 May, 2020 1 commit
    • Lynne's avatar
      lavfi/vulkan: use av_get_random_seed instead of rand · 83fa39eb
      Lynne authored
      We need at least a few bits of entropy to determine the start index of each
      queue, in order to let filters run in parallel as much as possible, and
      rand() is not thread safe and disrupts any external API's usage of rand,
      so instead replace it with av_get_random_seed.
      While it has more overhead than rand, we only run it once per filter upon init.
      83fa39eb
  10. 28 May, 2020 1 commit
    • Ting Fu's avatar
      dnn_backend_native_layer_mathunary: add abs support · f73cc61b
      Ting Fu authored
      more math unary operations will be added here
      
      It can be tested with the model file generated with below python scripy:
      
      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.subtract(x, 0.5)
      x2 = tf.abs(x1)
      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: 's avatarTing Fu <ting.fu@intel.com>
      Signed-off-by: 's avatarGuo, Yejun <yejun.guo@intel.com>
      f73cc61b
  11. 26 May, 2020 3 commits
  12. 23 May, 2020 8 commits
  13. 22 May, 2020 6 commits