Facial_Details_Synthesis
Facial_Details_Synthesis copied to clipboard
about textureRender.exe, and hmrenderer.exe warning of result.mtl, --emotion
thank your sharing your wonderful job, and i still got some questions,any help will be great appreciated,
when run:
python facialDetails.py -i samples\details\013578.jpg -o samples\out_details
there will a window pop-up and shut down(i don't know what it's, textureRender.exe?), then hmrender.exe will pop-up with warning.
but i got files like yours‘ and the warning
LOG (WARN: Material file [ result.mtl ] not found. WARN: Failed to load material file(s). Use default material. ) ~In file (e:\face2face\code\release_v1\src\face_rendering\src\includes\ind\loaders.cc) , line (81)
(https://github.com/apchenstu/Facial_Details_Synthesis/issues/10), and those files can open with paint 3D with testure(very slowly),
in meshlab(i don't how to cover texture ,but open files quickly),https://github.com/apchenstu/Facial_Details_Synthesis/issues/12
does the warning matter?and i change the PIL libs to PIL 6.0.0,the warning still there,and result.mtl is there with .obj
only run textureRender.exe not working in conda prompt(just break down with error: "textureRender.exe stop working"):
in folder released_v0.1 run:
textureRender\textureRender.exe samples\out_details\000008\result.obj samples\out_details\000008\result.isomap.png 0 samples\proxy\000008.jpg samples\out_details\000008\result.affine_from_ortho.txt textureRender\shaders
or in folder released_v0.1\textureRender run:
textureRender.exe ..\samples\out_details\000008\result.obj ..\samples\out_details\000008\result.isomap.png 0 ..\samples\proxy\000008.jpg ..\samples\out_details\000008\result.affine_from_ortho.txt shaders
only run hmrenderer.exe in conda prompt is same waring:
faceRender\hmrenderer.exe samples\out_details\000008\result.obj samples\out_details\000008\result.normalmap.png faceRender\shaders
when run:
python proxyPredictor.py -i samples\proxy -o samples\out_proxy+emotion --emotion 1
break down with error: "python stop working"(like textureRender.exe)
python version is 3.6.9, because i can't install eos-py==0.16.1 with pyhton3.7.3(https://github.com/apchenstu/Facial_Details_Synthesis/issues/5)
output in conda prompt:
Using TensorFlow backend.
WARNING: Logging before flag parsing goes to stderr.
W0915 12:09:47.706274 14808 deprecation_wrapper.py:119] From d:\Miniconda3\envs\python36\lib\site-packages\keras\backend\tensorflow_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.
W0915 12:09:47.985552 14808 deprecation_wrapper.py:119] From d:\Miniconda3\envs\python36\lib\site-packages\keras\backend\tensorflow_backend.py:4138: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.
W0915 12:09:48.102215 14808 deprecation_wrapper.py:119] From d:\Miniconda3\envs\python36\lib\site-packages\keras\backend\tensorflow_backend.py:245: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.
W0915 12:09:48.105208 14808 deprecation_wrapper.py:119] From d:\Miniconda3\envs\python36\lib\site-packages\keras\backend\tensorflow_backend.py:174: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead.
W0915 12:09:48.107202 14808 deprecation_wrapper.py:119] From d:\Miniconda3\envs\python36\lib\site-packages\keras\backend\tensorflow_backend.py:181: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.
2019-09-15 12:09:48.211278: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
2019-09-15 12:09:48.231910: I tensorflow/stream_executor/platform/default/dso_loader.cc:42] Successfully opened dynamic library nvcuda.dll
2019-09-15 12:09:48.648618: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1640] Found device 0 with properties:
name: GeForce GTX 1070 with Max-Q Design major: 6 minor: 1 memoryClockRate(GHz): 1.2655
pciBusID: 0000:01:00.0
2019-09-15 12:09:48.659840: I tensorflow/stream_executor/platform/default/dlopen_checker_stub.cc:25] GPU libraries are statically linked, skip dlopen check.
2019-09-15 12:09:48.677600: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1763] Adding visible gpu devices: 0
2019-09-15 12:09:53.927988: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1181] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-09-15 12:09:53.935198: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1187] 0
2019-09-15 12:09:53.939248: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1200] 0: N
2019-09-15 12:09:53.959566: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1326] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 6376 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1070 with Max-Q Design, pci bus id: 0000:01:00.0, compute capability: 6.1)
W0915 12:09:54.951899 14808 deprecation_wrapper.py:119] From d:\Miniconda3\envs\python36\lib\site-packages\keras\backend\tensorflow_backend.py:1834: The name tf.nn.fused_batch_norm is deprecated. Please use tf.compat.v1.nn.fused_batch_norm instead.
W0915 12:09:55.019749 14808 deprecation_wrapper.py:119] From d:\Miniconda3\envs\python36\lib\site-packages\keras\backend\tensorflow_backend.py:3976: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead.
W0915 12:09:55.026697 14808 deprecation.py:506] From d:\Miniconda3\envs\python36\lib\site-packages\keras\backend\tensorflow_backend.py:3445: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.
Instructions for updating:
Please use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.
Hey there, don't worry about the Window as textureRender.exe is an opengl program for facial texture rendering, it would open a Window and automatic close it. For the hnrender warming, please ignore it as we don't use material in our details render. The model already link to it's texture, and meshlab should correctly open it, could you show me your output files list? Thanks.
thank you for your reply,my output files,
my meshlab open it,two files can be recognated
Oh, result.obj
is linked to result.mtl and result.isomap.png, you may need to put them in a same folder.
For the break down issue, I also don't know what's wrong with it, as the code is divided into a few individual parts, we may need to figure out which part causes the program break down. A simple way to this is to comment out some of the code in this main function
in fact ,those files all in the same folder as the first picture; the second picture was a screenshot when open meshlab with the folder as a project,only two files showed(in fact all files in the folder); as to the break down issue, maybe it's my problem and i'll figure it out. thank you. and expecting your proxy job