ffmpeg/tools
Ting Fu c0cdeea0ee dnn_backend_native_layer_mathunary: add atanh support
It can be tested with the model generated with below python script:

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')

please uncomment the part you want to test

x_sinh_1 = tf.sinh(x)
x_out = tf.divide(x_sinh_1, 1.176) # sinh(1.0)

x_cosh_1 = tf.cosh(x)
x_out = tf.divide(x_cosh_1, 1.55) # cosh(1.0)

x_tanh_1 = tf.tanh(x)
x__out = tf.divide(x_tanh_1, 0.77) # tanh(1.0)

x_asinh_1 = tf.asinh(x)
x_out = tf.divide(x_asinh_1, 0.89) # asinh(1.0/1.1)

x_acosh_1 = tf.add(x, 1.1)
x_acosh_2 = tf.acosh(x_acosh_1) # accept (1, inf)
x_out = tf.divide(x_acosh_2, 1.4) # acosh(2.1)

x_atanh_1 = tf.divide(x, 1.1)
x_atanh_2 = tf.atanh(x_atanh_1) # accept (-1, 1)
x_out = tf.divide(x_atanh_2, 1.55) # atanhh(1.0/1.1)

y = tf.identity(x_out, name='dnn_out') #please only preserve the x_out you want to test

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>
2020-07-06 12:45:14 +08:00
..
python dnn_backend_native_layer_mathunary: add atanh support 2020-07-06 12:45:14 +08:00
.gitignore
aviocat.c
bisect-create
bookmarklets.html
cl2c
clean-diff
coverity.c
crypto_bench.c
cws2fws.c
dvd2concat
enum_options.c tools: stop using deprecated av_codec_next() 2020-04-20 15:08:20 +00:00
ffescape.c
ffeval.c
ffhash.c
fourcc2pixfmt.c
gen-rc
graph2dot.c
ismindex.c
libav-merge-next-commit
loudnorm.rb
make_chlayout_test
Makefile tools: add a fuzzer tool for bitstream filters 2019-12-05 20:49:15 -03:00
missing_codec_desc
murge
normalize.py
patcheck tools/patcheck: remove gcc-2.95 compat check 2019-09-21 12:57:04 -07:00
pktdumper.c
plotframes
probetest.c tools: fix const specifier for AVInputFormat 2020-04-30 10:25:32 +01:00
qt-faststart.c
seek_print.c
sidxindex.c
sofa2wavs.c
target_bsf_fuzzer.c lavc: rename bsf.h to bsf_internal.h 2020-05-22 14:38:57 +02:00
target_dec_fate.list
target_dec_fate.sh
target_dec_fuzzer.c tools/target_dec_fuzzer: Adjust threshold for lagarith 2020-06-11 14:59:04 +02:00
target_dem_fuzzer.c tools/target_dem_fuzzer: Use file extensions listed in input formats 2020-06-11 13:49:54 +02:00
trasher.c
uncoded_frame.c
unwrap-diff
venc_data_dump.c fate: add tests for h264 and vp9 video enc parameters export 2020-05-25 11:59:45 +02:00
yuvcmp.c
zmqsend.c
zmqshell.py