hanbumko / dncnn-jpeg Goto Github PK
View Code? Open in Web Editor NEWA tensorflow implementation of 'Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising' only for JPEG deblokcing
A tensorflow implementation of 'Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising' only for JPEG deblokcing
Can you publish the trained model?
When I go to train it (python main.py), this error appears...
.../home/rahid/anaconda3/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
GPU
2018-11-20 13:39:06.545468: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:898] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-11-20 13:39:06.547196: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1356] Found device 0 with properties:
name: GeForce GTX 1060 6GB major: 6 minor: 1 memoryClockRate(GHz): 1.759
pciBusID: 0000:1f:00.0
totalMemory: 5.93GiB freeMemory: 5.71GiB
2018-11-20 13:39:06.547218: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1435] Adding visible gpu devices: 0
2018-11-20 13:39:06.776509: I tensorflow/core/common_runtime/gpu/gpu_device.cc:923] Device interconnect StreamExecutor with strength 1 edge matrix:
2018-11-20 13:39:06.776549: I tensorflow/core/common_runtime/gpu/gpu_device.cc:929] 0
2018-11-20 13:39:06.776555: I tensorflow/core/common_runtime/gpu/gpu_device.cc:942] 0: N
2018-11-20 13:39:06.776800: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1053] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 5463 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1060 6GB, pci bus id: 0000:1f:00.0, compute capability: 6.1)
[*] Initialize model successfully...
[*] Loading data...
[*] Load successfully...
[*] Reading checkpoint...
[*] Not find pretrained model!
[*] Start training, with start epoch 0 start iter 0 :
[*] Evaluating...
In __exit__()
Traceback (most recent call last):
File "main.py", line 82, in <module>
tf.app.run()
File "/home/rahid/.local/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 126, in run
_sys.exit(main(argv))
File "main.py", line 62, in main
denoiser_train(model, lr=lr)
File "main.py", line 35, in denoiser_train
sample_dir=args.sample_dir)
File "/home/rahid/DnCNN-JPEG/model.py", line 111, in train
summary_writer=writer) # eval_data value range is 0-255
File "/home/rahid/DnCNN-JPEG/model.py", line 57, in evaluate
noisy_image.save('./asdf/tmp2.jpg', quality=10)
File "/home/rahid/.local/lib/python3.6/site-packages/PIL/Image.py", line 1947, in save
fp = builtins.open(filename, "w+b")
FileNotFoundError: [Errno 2] No such file or directory: './asdf/tmp2.jpg'
Line 55 in model.py
noisy_image = np.squeeze(noisy_image, 2)
--> noisy_image = np.squeeze(noisy_image, 3) ??
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.