The prefix for symbols not exported from the library and not
local to one translation unit is ff_ (or FF for types).
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
'void *' is too flexible, since we can derive info from
AVFilterContext*, so we just unify the interface with this data
structure.
Signed-off-by: Xie, Lin <lin.xie@intel.com>
Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
function fill_model_input_ov and infer_completion_callback are
extracted, it will help the async execution for reuse.
Signed-off-by: Xie, Lin <lin.xie@intel.com>
Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
TensorFlow C library accepts config for session options to
set different parameters for the inference. This patch exports
this interface.
The config is a serialized tensorflow.ConfigProto proto, so we need
two steps to use it:
1. generate the serialized proto with python (see script example below)
the output looks like: 0xab...cd
where 0xcd is the least significant byte and 0xab is the most significant byte.
2. pass the python script output into ffmpeg with
dnn_processing=options=sess_config=0xab...cd
The following script is an example to specify one GPU. If the system contains
3 GPU cards, the visible_device_list could be '0', '1', '2', '0,1' etc.
'0' does not mean physical GPU card 0, we need to try and see.
And we can also add more opitions here to generate more serialized proto.
script example to generate serialized proto which specifies one GPU:
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)
for some cases (for example, super resolution), the DNN model changes
the frame size which impacts the filter behavior, so the filter needs
to know the out frame size at very beginning.
Currently, the filter reuses DNNModule.execute_model to query the
out frame size, it is not clear from interface perspective, so add
a new explict interface DNNModel.get_output for such query.
suppose we have a detect and classify filter in the future, the
detect filter generates some bounding boxes (BBox) as AVFrame sidedata,
and the classify filter executes DNN model for each BBox. For each
BBox, we need to crop the AVFrame, copy data to DNN model input and do
the model execution. So we have to save the in_frame at DNNModel.set_input
and use it at DNNModule.execute_model, such saving is not feasible
when we support async execute_model.
This patch sets the in_frame as execution_model parameter, and so
all the information are put together within the same function for
each inference. It also makes easy to support BBox async inference.
Currently, every filter needs to provide code to transfer data from
AVFrame* to model input (DNNData*), and also from model output
(DNNData*) to AVFrame*. Actually, such transfer can be implemented
within DNN module, and so filter can focus on its own business logic.
DNN module also exports the function pointer pre_proc and post_proc
in struct DNNModel, just in case that a filter has its special logic
to transfer data between AVFrame* and DNNData*. The default implementation
within DNN module is used if the filter does not set pre/post_proc.
Before patch, fate test for dnn may fail in some Windows environment
while succeed in my Linux. The bug was caused by a wrong loop boundary.
After patch, fate test succeed in my windows mingw 64-bit.
Signed-off-by: Xu Jun <xujunzz@sjtu.edu.cn>
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Before patch, memory was allocated in each thread functions,
which may cause more than one time of memory allocation and
cause crash.
After patch, memory is allocated in the main thread once,
an index was parsed into thread functions. Bug fixed.
Signed-off-by: Xu Jun <xujunzz@sjtu.edu.cn>
show all input/output names when the input or output name not correct
Signed-off-by: Ting Fu <ting.fu@intel.com>
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Found via ASAN with the dnn-layer-conv2d FATE-test.
Reviewed-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
Use pthread to multithread dnn_execute_layer_conv2d.
Can be tested with command "./ffmpeg_g -i input.png -vf \
format=yuvj420p,dnn_processing=dnn_backend=native:model= \
espcn.model:input=x:output=y:options=conv2d_threads=23 \
-y sr_native.jpg -benchmark"
before patch: utime=11.238s stime=0.005s rtime=11.248s
after patch: utime=20.817s stime=0.047s rtime=1.051s
on my 3900X 12c24t @4.2GHz
About the increase of utime, it's because that CPU HyperThreading
technology makes logical cores twice of physical cores while cpu's
counting performance improves less than double. And utime sums
all cpu's logical cores' runtime. As a result, using threads num
near cpu's logical core's number will double utime, while reduce
rtime less than half for HyperThreading CPUs.
Signed-off-by: Xu Jun <xujunzz@sjtu.edu.cn>
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Unify all error return as DNN_ERROR, in order to cease model executing
when return error in ff_dnn_execute_model_native layer_func.pf_exec
Signed-off-by: Ting Fu <ting.fu@intel.com>
currently, output is set both at DNNModel.set_input_output and
DNNModule.execute_model, it makes sense that the output name is
provided at model inference time so all the output info is set
at a single place.
and so DNNModel.set_input_output is renamed to DNNModel.set_input
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
dnn_execute_layer_avg_pool() contains the following line:
assert(avgpool_params->padding_method = VALID);
This statement contains an assignment where obviously a comparison was
intended. Furthermore, *avgpool_params is const, so that the attempted
assignment leads to a compilation failure if asserts are enabled
(i.e. if DEBUG is defined which leads libavutil/internal.h to not define
NDEBUG). Moreover, the enumeration constant VALID actually has the value 0,
so that the assert would be triggered if a compiler compiles this with
asserts enabled. Finally, the statement uses assert() directly instead
of av_assert*().
All these errors have been fixed.
Thanks to ubitux for providing a FATE-box [1] where DEBUG is defined.
[1]: http://fate.ffmpeg.org/history.cgi?slot=x86_64-archlinux-gcc-ddebug
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
Reviewed-by: Guo, Yejun <yejun.guo@intel.com>
different backend might need different options for a better performance,
so, add the parameter into dnn interface, as a preparation.
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
We should not silently allocate an incorrect sized buffer.
Fixes trac issue #8718.
Signed-off-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de>
Reviewed-by: Michael Niedermayer <michael@niedermayer.cc>
Reviewed-by: Guo, Yejun <yejun.guo@intel.com>
OpenVINO is a Deep Learning Deployment Toolkit at
https://github.com/openvinotoolkit/openvino, it supports CPU, GPU
and heterogeneous plugins to accelerate deep learning inferencing.
Please refer to https://github.com/openvinotoolkit/openvino/blob/master/build-instruction.md
to build openvino (c library is built at the same time). Please add
option -DENABLE_MKL_DNN=ON for cmake to enable CPU path. The header
files and libraries are installed to /usr/local/deployment_tools/inference_engine/
with default options on my system.
To build FFmpeg with openvion, take my system as an example, run with:
$ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/deployment_tools/inference_engine/lib/intel64/:/usr/local/deployment_tools/inference_engine/external/tbb/lib/
$ ../ffmpeg/configure --enable-libopenvino --extra-cflags=-I/usr/local/deployment_tools/inference_engine/include/ --extra-ldflags=-L/usr/local/deployment_tools/inference_engine/lib/intel64
$ make
Here are the features provided by OpenVINO inference engine:
- support more DNN model formats
It supports TensorFlow, Caffe, ONNX, MXNet and Kaldi by converting them
into OpenVINO format with a python script. And torth model
can be first converted into ONNX and then to OpenVINO format.
see the script at https://github.com/openvinotoolkit/openvino/tree/master/model-optimizer/mo.py
which also does some optimization at model level.
- optimize at inference stage
It optimizes for X86 CPUs with SSE, AVX etc.
It also optimizes based on OpenCL for Intel GPUs.
(only Intel GPU supported becuase Intel OpenCL extension is used for optimization)
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
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: Ting Fu <ting.fu@intel.com>
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
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>
so, we can make a filter more general to accept different network
models, by adding a data type convertion after getting data from network.
After we add dt field into struct DNNData, it becomes the same as
DNNInputData, so merge them with one struct: DNNData.
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
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>
and also change CONV to DLT_CONV2D for better description
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
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>
the logic is that one layer in one separated source file to make
the source files simple for maintaining.
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
the logic is that one layer in one separated source file to make
the source files simple for maintaining.
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
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>
the info can be saved in dnn operand object without regenerating again and again,
and it is also needed for layer split/merge, and for memory reuse.
to make things step by step, this patch just focuses on c code,
the change within python script will be added later.
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
if it is initialized randomly, the tensorflow lib will report
error message such as:
Attempt to add output -7920 of depth_to_space4 not in range [0, 1) to node with type Identity
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
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>
the reason to add this layer first is that vf_sr uses it in its
tensorflow model, and the next plan is to update the python script
to convert tf.pad into native model.
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
it is expected that there will be more files to support native mode,
so put all the dnn codes under libavfilter/dnn
The main change of this patch is to move the file location, see below:
modified: libavfilter/Makefile
new file: libavfilter/dnn/Makefile
renamed: libavfilter/dnn_backend_native.c -> libavfilter/dnn/dnn_backend_native.c
renamed: libavfilter/dnn_backend_native.h -> libavfilter/dnn/dnn_backend_native.h
renamed: libavfilter/dnn_backend_tf.c -> libavfilter/dnn/dnn_backend_tf.c
renamed: libavfilter/dnn_backend_tf.h -> libavfilter/dnn/dnn_backend_tf.h
renamed: libavfilter/dnn_interface.c -> libavfilter/dnn/dnn_interface.c
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
Guo, Yejun
Xie, Lin
Ting Fu
Jun Zhao
Chris Miceli
Mingyu Yin
Xu Jun
Andreas Rheinhardt
Reimar Döffinger
Wu Zhiwen
Carl Eugen Hoyos
Marton Balint