a-little-bit-more's People
a-little-bit-more's Issues
About train
Hello, I'd like to train with my own dataset, but after just one epoch, I encountered the following results. I'm not sure why. Could you help me understand? Thank you.
loss: 0.0063 - binary_accuracy: 0.9994 - val_loss: 1.6513e-05 - val_binary_accuracy: 1.0000
Testing code does not work well
Hi! I'm interested in this work, but I find the testing code does not work well. The output images are totally dark. Just like this:
I create a new conda environment following the README.
Here is the output of command line. Would you mind having a look at it and pointing out the problem? Thanks!
$ python test.py --set_names Kodak --type_8_or_16 0 --quant 3 --quant_end 8 --dep 16 --save_result 1
Using TensorFlow backend.
2022-02-28 19:25:15.720844: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 AVX512F FMA
2022-02-28 19:25:15.924086: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1432] Found device 0 with properties:
name: GeForce RTX 3090 major: 8 minor: 6 memoryClockRate(GHz): 1.695
pciBusID: 0000:1a:00.0
totalMemory: 23.70GiB freeMemory: 23.44GiB
2022-02-28 19:25:16.048250: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1432] Found device 1 with properties:
name: GeForce RTX 3090 major: 8 minor: 6 memoryClockRate(GHz): 1.695
pciBusID: 0000:3d:00.0
totalMemory: 23.70GiB freeMemory: 23.44GiB
2022-02-28 19:25:16.153546: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1432] Found device 2 with properties:
name: GeForce RTX 3090 major: 8 minor: 6 memoryClockRate(GHz): 1.695
pciBusID: 0000:89:00.0
totalMemory: 23.70GiB freeMemory: 23.44GiB
2022-02-28 19:25:16.275457: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1432] Found device 3 with properties:
name: GeForce RTX 3090 major: 8 minor: 6 memoryClockRate(GHz): 1.695
pciBusID: 0000:b1:00.0
totalMemory: 23.70GiB freeMemory: 23.44GiB
2022-02-28 19:25:16.391234: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1432] Found device 4 with properties:
name: GeForce RTX 3090 major: 8 minor: 6 memoryClockRate(GHz): 1.695
pciBusID: 0000:b2:00.0
totalMemory: 23.70GiB freeMemory: 23.44GiB
2022-02-28 19:25:16.391292: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1511] Adding visible gpu devices: 0, 1, 2, 3, 4
2022-02-28 19:28:48.279998: I tensorflow/core/common_runtime/gpu/gpu_device.cc:982] Device interconnect StreamExecutor with strength 1 edge matrix:
2022-02-28 19:28:48.280047: I tensorflow/core/common_runtime/gpu/gpu_device.cc:988] 0 1 2 3 4
2022-02-28 19:28:48.280054: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1001] 0: N N N N N
2022-02-28 19:28:48.280058: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1001] 1: N N N N N
2022-02-28 19:28:48.280062: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1001] 2: N N N N N
2022-02-28 19:28:48.280066: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1001] 3: N N N N N
2022-02-28 19:28:48.280069: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1001] 4: N N N N N
2022-02-28 19:28:48.280303: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 22726 MB memory) -> physical GPU (device: 0, name: GeForce RTX 3090, pci bus id: 0000:1a:00.0, compute capability: 8.6)
2022-02-28 19:28:48.280689: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:1 with 14885 MB memory) -> physical GPU (device: 1, name: GeForce RTX 3090, pci bus id: 0000:3d:00.0, compute capability: 8.6)
2022-02-28 19:28:48.280933: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:2 with 19706 MB memory) -> physical GPU (device: 2, name: GeForce RTX 3090, pci bus id: 0000:89:00.0, compute capability: 8.6)
2022-02-28 19:28:48.281121: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:3 with 19706 MB memory) -> physical GPU (device: 3, name: GeForce RTX 3090, pci bus id: 0000:b1:00.0, compute capability: 8.6)
2022-02-28 19:28:48.281313: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:4 with 19706 MB memory) -> physical GPU (device: 4, name: GeForce RTX 3090, pci bus id: 0000:b2:00.0, compute capability: 8.6)
2022-02-28 19:28:52: load trained model - 4 - 030
2022-02-28 19:28:57: load trained model - 5 - 030
2022-02-28 19:29:01: load trained model - 6 - 030
2022-02-28 19:29:07: load trained model - 7 - 030
2022-02-28 19:29:13: load trained model - 8 - 030
Kodak : kodim04.png : 1055.9769 second
Kodak : kodim01.png : 0.5756 second
Kodak : kodim20.png : 0.5917 second
Kodak : kodim21.png : 0.5345 second
Kodak : kodim10.png : 0.5409 second
Kodak : kodim08.png : 0.5639 second
Kodak : kodim14.png : 0.5364 second
Kodak : kodim23.png : 0.5551 second
Kodak : kodim16.png : 0.5398 second
Kodak : kodim19.png : 0.5437 second
Kodak : kodim07.png : 0.5365 second
Kodak : kodim15.png : 0.5465 second
Kodak : kodim11.png : 0.5364 second
Kodak : kodim17.png : 0.5362 second
Kodak : kodim02.png : 0.5558 second
Kodak : kodim24.png : 0.5336 second
Kodak : kodim13.png : 0.5503 second
Kodak : kodim03.png : 0.5627 second
Kodak : kodim18.png : 0.5432 second
Kodak : kodim06.png : 0.5517 second
Kodak : kodim22.png : 0.5383 second
Kodak : kodim12.png : 0.5451 second
Kodak : kodim05.png : 0.5566 second
Kodak : kodim09.png : 0.5336 second
2022-02-28 19:47:29: Dataset: Kodak
PSNR = 8.4058dB, SSIM = 0.0673
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.