[FFmpeg-devel] [PATCH 5/6] avfilter/dnn/dnn_backend_tf: simplify the code with ff_hex_to_data

[lance.lmwang at gmail.com]

On Tue, Apr 27, 2021 at 04:09:18AM +0000, Guo, Yejun wrote:
> 
> 
> > -----Original Message-----
> > From: ffmpeg-devel <ffmpeg-devel-bounces at ffmpeg.org> On Behalf Of
> > lance.lmwang at gmail.com
> > Sent: 2021年4月26日 18:49
> > To: ffmpeg-devel at ffmpeg.org
> > Cc: Limin Wang <lance.lmwang at gmail.com>
> > Subject: [FFmpeg-devel] [PATCH 5/6] avfilter/dnn/dnn_backend_tf: simplify
> > the code with ff_hex_to_data
> > 
> > From: Limin Wang <lance.lmwang at gmail.com>
> > 
> > please use tools/python/tf_sess_config.py to get the sess_config after that.
> > note the byte order of session config is the normal order.
> > 
> > Signed-off-by: Limin Wang <lance.lmwang at gmail.com>
> > ---
> >  libavfilter/dnn/dnn_backend_tf.c | 34 ++++++----------------------------
> >  1 file changed, 6 insertions(+), 28 deletions(-)
> > 
> > diff --git a/libavfilter/dnn/dnn_backend_tf.c
> > b/libavfilter/dnn/dnn_backend_tf.c
> > index fb799d2..0084157 100644
> > --- a/libavfilter/dnn/dnn_backend_tf.c
> > +++ b/libavfilter/dnn/dnn_backend_tf.c
> > @@ -28,6 +28,7 @@
> >  #include "dnn_backend_native_layer_conv2d.h"
> >  #include "dnn_backend_native_layer_depth2space.h"
> >  #include "libavformat/avio.h"
> > +#include "libavformat/internal.h"
> >  #include "libavutil/avassert.h"
> >  #include "../internal.h"
> >  #include "dnn_backend_native_layer_pad.h"
> > @@ -202,35 +203,21 @@ static DNNReturnType load_tf_model(TFModel
> > *tf_model, const char *model_filename
> >      TF_SessionOptions *sess_opts;
> >      const TF_Operation *init_op;
> >      uint8_t *sess_config = NULL;
> > -    int sess_config_length = 0;
> > +    int sess_config_length = ff_hex_to_data(NULL,
> > tf_model->ctx.options.sess_config + 2);
> > 
> >      // prepare the sess config data
> >      if (tf_model->ctx.options.sess_config != NULL) {
> >          /*
> >          tf_model->ctx.options.sess_config is hex to present the
> > serialized proto
> >          required by TF_SetConfig below, so we need to first generate
> > the serialized
> > -        proto in a python script, the following is a script example to
> > generate
> > -        serialized proto which specifies one GPU, we can change the
> > script to add
> > -        more options.
> > -
> > -        import tensorflow as tf
> > -        gpu_options = tf.GPUOptions(visible_device_list='0')
> > -        config = tf.ConfigProto(gpu_options=gpu_options)
> > -        s = config.SerializeToString()
> > -        b = ''.join("%02x" % int(ord(b)) for b in s[::-1])
> > -        print('0x%s' % b)
> > -
> > -        the script output looks like: 0xab...cd, and then pass 0xab...cd to
> > sess_config.
> > +        proto in a python script, tools/python/tf_sess_config.py is a
> > script example
> > +        to generate the configs of sess_config.
> >          */
> > -        char tmp[3];
> > -        tmp[2] = '\0';
> > -
> >          if (strncmp(tf_model->ctx.options.sess_config, "0x", 2) != 0) {
> >              av_log(ctx, AV_LOG_ERROR, "sess_config should start with
> > '0x'\n");
> >              return DNN_ERROR;
> >          }
> 
> there are two '+2' to skip "0x" in the code, we'd better to unify here after
> "0x" checking like:
> 
> // skip "0x"
> const char *config = tf_model->ctx.options.sess_config + 2;
> sess_config_length = ff_hex_to_data(NULL, config);
> ...
> 

I'm OK with it.

> > 
> > -        sess_config_length = strlen(tf_model->ctx.options.sess_config);
> >          if (sess_config_length % 2 != 0) {
> >              av_log(ctx, AV_LOG_ERROR, "the length of sess_config is
> > not even (%s), "
> >                                        "please re-generate the
> > config.\n",
> > @@ -238,21 +225,12 @@ static DNNReturnType load_tf_model(TFModel
> > *tf_model, const char *model_filename
> >              return DNN_ERROR;
> >          }
> > 
> > -        sess_config_length -= 2; //ignore the first '0x'
> > -        sess_config_length /= 2; //get the data length in byte
> > -
> > -        sess_config = av_malloc(sess_config_length);
> > +        sess_config = av_mallocz(sess_config_length +
> > AV_INPUT_BUFFER_PADDING_SIZE);
> >          if (!sess_config) {
> >              av_log(ctx, AV_LOG_ERROR, "failed to allocate memory\n");
> >              return DNN_ERROR;
> >          }
> > -
> > -        for (int i = 0; i < sess_config_length; i++) {
> > -            int index = 2 + (sess_config_length - 1 - i) * 2;
> > -            tmp[0] = tf_model->ctx.options.sess_config[index];
> > -            tmp[1] = tf_model->ctx.options.sess_config[index + 1];
> > -            sess_config[i] = strtol(tmp, NULL, 16);
> > -        }
> > +        ff_hex_to_data(sess_config, tf_model->ctx.options.sess_config +
> > 2);
> >      }
> > 
> >      graph_def = read_graph(model_filename);
> > --
> > 1.8.3.1
> > 
> > _______________________________________________
> > ffmpeg-devel mailing list
> > ffmpeg-devel at ffmpeg.org
> > https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
> > 
> > To unsubscribe, visit link above, or email
> > ffmpeg-devel-request at ffmpeg.org with subject "unsubscribe".
> _______________________________________________
> ffmpeg-devel mailing list
> ffmpeg-devel at ffmpeg.org
> https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
> 
> To unsubscribe, visit link above, or email
> ffmpeg-devel-request at ffmpeg.org with subject "unsubscribe".

-- 
Thanks,
Limin Wang