mirror of https://git.ffmpeg.org/ffmpeg.git
f4b3c0e55c
to support dnn networks more general, we need to know the input info of the dnn model. background: The data type of dnn model's input could be float32, uint8 or fp16, etc. And the w/h of input image could be fixed or variable. Signed-off-by: Guo, Yejun <yejun.guo@intel.com> Signed-off-by: Pedro Arthur <bygrandao@gmail.com> |
||
---|---|---|
.. | ||
Makefile | ||
dnn_backend_native.c | ||
dnn_backend_native.h | ||
dnn_backend_native_layer_conv2d.c | ||
dnn_backend_native_layer_conv2d.h | ||
dnn_backend_native_layer_depth2space.c | ||
dnn_backend_native_layer_depth2space.h | ||
dnn_backend_native_layer_maximum.c | ||
dnn_backend_native_layer_maximum.h | ||
dnn_backend_native_layer_pad.c | ||
dnn_backend_native_layer_pad.h | ||
dnn_backend_native_layers.c | ||
dnn_backend_native_layers.h | ||
dnn_backend_tf.c | ||
dnn_backend_tf.h | ||
dnn_interface.c |