Mingyu Yin
fab00b0ae0
dnn_backend_native_layer_mathunary: add floor support
...
It can be tested with the model generated with below python script:
import tensorflow as tf
import os
import numpy as np
import imageio
from tensorflow.python.framework import graph_util
name = 'floor'
pb_file_path = os.getcwd()
if not os.path.exists(pb_file_path+'/{}_savemodel/'.format(name)):
os.mkdir(pb_file_path+'/{}_savemodel/'.format(name))
with tf.Session(graph=tf.Graph()) as sess:
in_img = imageio.imread('detection.jpg')
in_img = in_img.astype(np.float32)
in_data = in_img[np.newaxis, :]
input_x = tf.placeholder(tf.float32, shape=[1, None, None, 3], name='dnn_in')
y_ = tf.math.floor(input_x*255)/255
y = tf.identity(y_, name='dnn_out')
sess.run(tf.global_variables_initializer())
constant_graph = graph_util.convert_variables_to_constants(sess, sess.graph_def, ['dnn_out'])
with tf.gfile.FastGFile(pb_file_path+'/{}_savemodel/model.pb'.format(name), mode='wb') as f:
f.write(constant_graph.SerializeToString())
print("model.pb generated, please in ffmpeg path use\n \n \
python tools/python/convert.py {}_savemodel/model.pb --outdir={}_savemodel/ \n \nto generate model.model\n".format(name,name))
output = sess.run(y, feed_dict={ input_x: in_data})
imageio.imsave("out.jpg", np.squeeze(output))
print("To verify, please ffmpeg path use\n \n \
./ffmpeg -i detection.jpg -vf format=rgb24,dnn_processing=model={}_savemodel/model.pb:input=dnn_in:output=dnn_out:dnn_backend=tensorflow -f framemd5 {}_savemodel/tensorflow_out.md5\n \
or\n \
./ffmpeg -i detection.jpg -vf format=rgb24,dnn_processing=model={}_savemodel/model.pb:input=dnn_in:output=dnn_out:dnn_backend=tensorflow {}_savemodel/out_tensorflow.jpg\n \nto generate output result of tensorflow model\n".format(name, name, name, name))
print("To verify, please ffmpeg path use\n \n \
./ffmpeg -i detection.jpg -vf format=rgb24,dnn_processing=model={}_savemodel/model.model:input=dnn_in:output=dnn_out:dnn_backend=native -f framemd5 {}_savemodel/native_out.md5\n \
or \n \
./ffmpeg -i detection.jpg -vf format=rgb24,dnn_processing=model={}_savemodel/model.model:input=dnn_in:output=dnn_out:dnn_backend=native {}_savemodel/out_native.jpg\n \nto generate output result of native model\n".format(name, name, name, name))
Signed-off-by: Mingyu Yin <mingyu.yin@intel.com>
2020-08-07 10:34:22 +08:00
Mingyu Yin
9fbdd5454b
dnn_backend_native_layer_mathunary: add ceil support
...
It can be tested with the model generated with below python script:
import tensorflow as tf
import os
import numpy as np
import imageio
from tensorflow.python.framework import graph_util
name = 'ceil'
pb_file_path = os.getcwd()
if not os.path.exists(pb_file_path+'/{}_savemodel/'.format(name)):
os.mkdir(pb_file_path+'/{}_savemodel/'.format(name))
with tf.Session(graph=tf.Graph()) as sess:
in_img = imageio.imread('detection.jpg')
in_img = in_img.astype(np.float32)
in_data = in_img[np.newaxis, :]
input_x = tf.placeholder(tf.float32, shape=[1, None, None, 3], name='dnn_in')
y = tf.math.ceil( input_x, name='dnn_out')
sess.run(tf.global_variables_initializer())
constant_graph = graph_util.convert_variables_to_constants(sess, sess.graph_def, ['dnn_out'])
with tf.gfile.FastGFile(pb_file_path+'/{}_savemodel/model.pb'.format(name), mode='wb') as f:
f.write(constant_graph.SerializeToString())
print("model.pb generated, please in ffmpeg path use\n \n \
python tools/python/convert.py ceil_savemodel/model.pb --outdir=ceil_savemodel/ \n \n \
to generate model.model\n")
output = sess.run(y, feed_dict={ input_x: in_data})
imageio.imsave("out.jpg", np.squeeze(output))
print("To verify, please ffmpeg path use\n \n \
./ffmpeg -i detection.jpg -vf format=rgb24,dnn_processing=model=ceil_savemodel/model.pb:input=dnn_in:output=dnn_out:dnn_backend=tensorflow -f framemd5 ceil_savemodel/tensorflow_out.md5\n \n \
to generate output result of tensorflow model\n")
print("To verify, please ffmpeg path use\n \n \
./ffmpeg -i detection.jpg -vf format=rgb24,dnn_processing=model=ceil_savemodel/model.model:input=dnn_in:output=dnn_out:dnn_backend=native -f framemd5 ceil_savemodel/native_out.md5\n \n \
to generate output result of native model\n")
Signed-off-by: Mingyu Yin <mingyu.yin@intel.com>
Reviewed-by: Guo, Yejun <yejun.guo@intel.com>
2020-08-04 19:56:54 +08:00
Ting Fu
dbf66b9e0e
tests/dnn/mathunary: fix the issue of NAN
...
When one of output[i] & expected_output is NAN, the unit test will always pass.
Signed-off-by: Ting Fu <ting.fu@intel.com>
Reviewed-by: Guo, Yejun <yejun.guo@intel.com>
2020-07-09 09:34:44 +08:00
Ting Fu
57ea0483af
dnn-layer-math-unary-test: add unit test for atanh
...
Signed-off-by: Ting Fu <ting.fu@intel.com>
2020-07-06 12:45:14 +08:00
Ting Fu
52d2e16665
dnn-layer-math-unary-test: add unit test for acosh
...
Signed-off-by: Ting Fu <ting.fu@intel.com>
2020-07-06 12:45:14 +08:00
Ting Fu
33374bdbd8
dnn-layer-math-unary-test: add unit test for asinh
...
Signed-off-by: Ting Fu <ting.fu@intel.com>
2020-07-06 12:45:14 +08:00
Ting Fu
0de5043060
dnn-layer-math-unary-test: add unit test for tanh
...
Signed-off-by: Ting Fu <ting.fu@intel.com>
2020-07-06 12:45:14 +08:00
Ting Fu
c5de77e33c
dnn-layer-math-unary-test: add unit test for cosh
...
Signed-off-by: Ting Fu <ting.fu@intel.com>
2020-07-06 12:45:14 +08:00
Ting Fu
85c0608c6b
dnn-layer-math-unary-test: add unit test for sinh
...
Signed-off-by: Ting Fu <ting.fu@intel.com>
2020-07-06 12:45:14 +08:00
Ting Fu
24d1781cbd
dnn-layer-math-unary-test: add unit test for atan
...
Signed-off-by: Ting Fu <ting.fu@intel.com>
Signed-off-by: Guo Yejun <yejun.guo@intel.com>
2020-06-25 08:41:50 +08:00
Ting Fu
130c600144
dnn-layer-math-unary-test: add unit test for acos
...
Signed-off-by: Ting Fu <ting.fu@intel.com>
Signed-off-by: Guo Yejun <yejun.guo@intel.com>
2020-06-25 08:41:50 +08:00
Ting Fu
057f6ee7f4
dnn-layer-math-unary-test: add unit test for asin
...
Signed-off-by: Ting Fu <ting.fu@intel.com>
Signed-off-by: Guo Yejun <yejun.guo@intel.com>
2020-06-25 08:41:50 +08:00
Ting Fu
3ac2f7ccd7
dnn-layer-mathunary-test: add unit test for tan
...
Signed-off-by: Ting Fu <ting.fu@intel.com>
Signed-off-by: Guo Yejun <yejun.guo@intel.com>
2020-06-11 11:10:51 +08:00
Ting Fu
dd3fe3e77c
dnn-layer-mathunary-test: add unit test for cos
...
Signed-off-by: Ting Fu <ting.fu@intel.com>
Signed-off-by: Guo Yejun <yejun.guo@intel.com>
2020-06-11 11:10:51 +08:00
Ting Fu
3f7c5a375b
dnn-layer-mathunary-test: add unit test for sin
...
Signed-off-by: Ting Fu <ting.fu@intel.com>
Signed-off-by: Guo Yejun <yejun.guo@intel.com>
2020-06-11 11:10:51 +08:00
Ting Fu
c51b46e5dd
dnn-layer-mathunary-test: add unit test for abs
...
Signed-off-by: Ting Fu <ting.fu@intel.com>
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
2020-05-28 11:04:21 +08:00
Guo, Yejun
6fd61234d5
dnn-layer-mathbinary-test: add unit test for minimum
...
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
2020-05-08 15:22:44 +08:00
Martin Storsjö
f4d8fad802
dnn-layer-mathbinary-test: Fix tests for cases with extra intermediate precision
...
This fixes tests on 32 bit x86 mingw with clang, which uses x87
fpu by default.
In this setup, while the get_expected function is declared to
return float, the compiler is (especially given the optimization
flags set) free to keep the intermediate values (in this case,
the return value from the inlined function) in higher precision.
This results in the situation where 7.28 (which actually, as
a float, ends up as 7.2800002098), multiplied by 100, is
728.000000 when really forced into a 32 bit float, but 728.000021
when kept with higher intermediate precision.
For the multiplication case, a more suitable epsilon would e.g.
be 2*FLT_EPSILON*fabs(expected_output), but just increase the
current hardcoded threshold for now.
Signed-off-by: Martin Storsjö <martin@martin.st>
2020-04-24 14:41:06 +03:00
Guo, Yejun
2e38c63630
dnn-layer-mathbinary-test: add unit test for divide
...
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
2020-04-22 13:15:09 +08:00
Guo, Yejun
265b5bd324
dnn-layer-mathbinary-test: add unit test for 'mul'
...
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
2020-04-22 13:14:55 +08:00
Guo, Yejun
17006196a6
dnn-layer-mathbinary-test: add unit test for add
...
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
2020-04-22 13:14:39 +08:00
Guo, Yejun
bbc64799dc
dnn-layer-mathbinary-test: add unit test for subtraction
...
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
2020-04-07 11:04:40 +08:00
Guo, Yejun
dff39ea9f0
dnn: add tf.nn.conv2d support for native model
...
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>
2019-10-30 10:31:55 -03:00
Zhao Zhili
11cfff04ed
FATE/dnn: add .gitignore
...
Reviewed-by: Guo, Yejun <yejun.guo@intel.com>
2019-10-23 09:58:17 -03:00
Guo, Yejun
3fd5ac7e92
avfilter/dnn: unify the layer execution function in native mode
...
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
2019-10-15 18:56:25 -03:00
Zhao Zhili
7c145b6441
FATE/dnn: fix stack buffer overflow
...
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
2019-10-04 09:58:22 -03:00
Guo, Yejun
9ae42c130c
FATE/dnn: add unit test for layer maximum
...
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
2019-09-20 10:57:23 -03:00
Guo, Yejun
b766a13dba
FATE/dnn: add unit test for dnn depth_to_space layer
...
'make fate-dnn-layer-depth2space' to run the test
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
2019-09-19 11:29:57 -03:00
Guo, Yejun
24f507301b
FATE/dnn: add unit test for dnn conv2d layer
...
'make fate-dnn-layer-conv2d' to run the test
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
2019-09-19 11:21:38 -03:00
Guo, Yejun
09a455a246
dnn: introduce dnn operand (in c code) to hold operand infos within network
...
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>
2019-08-30 11:41:30 -03:00
Guo, Yejun
d0fa1a58da
FATE/dnn: let fate/dnn tests depend on ffmpeg static libraries
...
background:
DNN (deep neural network) is a sub module of libavfilter, and FATE/dnn
is unit test for the DNN module, one unit test for one dnn layer.
The unit tests are not based on the APIs exported by libavfilter,
they just directly call into the functions within DNN submodule.
There is an issue when run the following command:
build$ ../ffmpeg/configure --disable-static --enable-shared
make
make fate-dnn-layer-pad
And part of error message:
tests/dnn/dnn-layer-pad-test.o: In function `test_with_mode_symmetric':
/work/media/ffmpeg/build/src/tests/dnn/dnn-layer-pad-test.c:73: undefined reference to `dnn_execute_layer_pad'
The root cause is that function dnn_execute_layer_pad is a LOCAL symbol
in libavfilter.so, and so the linker could not find it when build dnn-layer-pad-test.
To check it, just run: readelf -s libavfilter/libavfilter.so | grep dnn
So, add dependency in fate/dnn Makefile with ffmpeg static libraries.
This is the same method used in fate/checkasm
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
2019-08-19 11:37:16 -03:00
Guo, Yejun
3805aae479
fate: add unit test for dnn-layer-pad
...
'make fate-dnn-layer-pad' to run the test
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>
2019-07-29 12:34:19 -03:00