- 13 Dec, 2019 1 commit
-
-
Guo, Yejun authored
convert_from_tensorflow.py: add support when kernel size is 1*1 with one input/output channel (gray image) Signed-off-by:
Guo, Yejun <yejun.guo@intel.com> Signed-off-by:
Pedro Arthur <bygrandao@gmail.com>
-
- 30 Oct, 2019 1 commit
-
-
Guo, Yejun authored
Unlike other tf.*.conv2d layers, tf.nn.conv2d does not create many nodes (within a scope) in the graph, it just acts like other layers. tf.nn.conv2d only creates one node in the graph, and no internal nodes such as 'kernel' are created. The format of native model file is also changed, a flag named has_bias is added, so change the version number. Signed-off-by:
Guo, Yejun <yejun.guo@intel.com> Signed-off-by:
Pedro Arthur <bygrandao@gmail.com>
-
- 20 Sep, 2019 1 commit
-
-
Guo, Yejun authored
The reason to add this layer is that it is used by srcnn in vf_sr. This layer is currently ignored in native mode. After this patch, we can add multiple outputs support for native mode. Signed-off-by:
Guo, Yejun <yejun.guo@intel.com> Signed-off-by:
Pedro Arthur <bygrandao@gmail.com>
-
- 04 Sep, 2019 1 commit
-
-
Guo, Yejun authored
Signed-off-by:
Guo, Yejun <yejun.guo@intel.com> Signed-off-by:
Pedro Arthur <bygrandao@gmail.com>
-
- 30 Aug, 2019 2 commits
-
-
Guo, Yejun authored
Signed-off-by:
Guo, Yejun <yejun.guo@intel.com> Signed-off-by:
Pedro Arthur <bygrandao@gmail.com>
-
Guo, Yejun authored
currently, the layer number is at the beginning of the .model file, so we have to scan twice in python script, the first scan to get the layer number. Only one scan needed after put the layer number at the end of .model file. Signed-off-by:
Guo, Yejun <yejun.guo@intel.com> Signed-off-by:
Pedro Arthur <bygrandao@gmail.com>
-
- 15 Aug, 2019 2 commits
-
-
Guo, Yejun authored
conv2d with dilation > 1 generates tens of nodes in graph, it is not easy to parse each node one by one, so we do special tricks to parse the conv2d layer. Signed-off-by:
Guo, Yejun <yejun.guo@intel.com> Signed-off-by:
Pedro Arthur <bygrandao@gmail.com>
-
Guo, Yejun authored
Signed-off-by:
Guo, Yejun <yejun.guo@intel.com> Signed-off-by:
Pedro Arthur <bygrandao@gmail.com>
-
- 29 Jul, 2019 1 commit
-
-
Guo, Yejun authored
since tf.pad is enabled, the conv2d(valid) changes back to its original behavior. Signed-off-by:
Guo, Yejun <yejun.guo@intel.com> Signed-off-by:
Pedro Arthur <bygrandao@gmail.com>
-
- 01 Jul, 2019 1 commit
-
-
Guo, Yejun authored
For example, given TensorFlow model file espcn.pb, to generate native model file espcn.model, just run: python convert.py espcn.pb In current implementation, the native model file is generated for specific dnn network with hard-code python scripts maintained out of ffmpeg. For example, srcnn network used by vf_sr is generated with https://github.com/HighVoltageRocknRoll/sr/blob/master/generate_header_and_model.py#L85 In this patch, the script is designed as a general solution which converts general TensorFlow model .pb file into .model file. The script now has some tricky to be compatible with current implemention, will be refined step by step. The script is also added into ffmpeg source tree. It is expected there will be many more patches and community needs the ownership of it. Another technical direction is to do the conversion in c/c++ code within ffmpeg source tree. While .pb file is organized with protocol buffers, it is not easy to do such work with tiny c/c++ code, see more discussion at http://ffmpeg.org/pipermail/ffmpeg-devel/2019-May/244496.html. So, choose the python script. Signed-off-by:
Guo, Yejun <yejun.guo@intel.com>
-