| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | dnn_backend_native_layer_mathbinary: add sub support | Guo, Yejun | 2020-04-07 | 1 | -1/+1 |
| | | | | | | | more math binary operations will be added here Signed-off-by: Guo, Yejun <[email protected]> | ||||
| * | dnn: add tf.nn.conv2d support for native model | Guo, Yejun | 2019-10-30 | 1 | -2/+2 |
| | | | | | | | | | | | | | | 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 <[email protected]> Signed-off-by: Pedro Arthur <[email protected]> | ||||
| * | libavfilter/dnn: add layer maximum for native mode. | Guo, Yejun | 2019-09-20 | 1 | -1/+1 |
| | | | | | | | | | | 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 <[email protected]> Signed-off-by: Pedro Arthur <[email protected]> | ||||
| * | libavfilter/dnn: add header into native model file | Guo, Yejun | 2019-09-04 | 1 | -0/+26 |
| Signed-off-by: Guo, Yejun <[email protected]> Signed-off-by: Pedro Arthur <[email protected]> | |||||
 |
index : ffmpeg | |
| Mirror of FFmpeg git repo |
| summaryrefslogtreecommitdiffstats |