sftwre / imagecompressionnn Goto Github PK
View Code? Open in Web Editor NEWImplementation of: Real-Time Adaptive Image Compression by Oren Rippel and Lubomir Bourdev
Implementation of: Real-Time Adaptive Image Compression by Oren Rippel and Lubomir Bourdev
Hello, I find that your code seems to have no parts about bitplane decomposition, AAC and ACR. Have you realized them after this code? I am studying this paper and have some questions about these three parts, so I want to refer to your code to understand this process. Hope your reply, thanks!
In the paper:
Our pyramidal decomposition architecture is illustrated in Figure 3. In practice, we extract across a total of 6 scales. The feature extractors for the individual scales are composed of a sequence of convolutions with kernels or and ReLUs with a leak of 0.2. We learn all downsamplers as convolutions with a stride of 2.
But from the code, i found the kernel size of downsample is 3
When I execute the training command, there is an error of feature dimension. Displays dimensional errors in feature alignment.
Traceback (most recent call last):
File "project/train.py", line 114, in
main()
File "project/train.py", line 107, in main
train(dataloader, i)
File "project/train.py", line 46, in train
doc = net(img)
File "/media/yangxilab/DiskA/anaconda3/envs/yuyi/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/media/yangxilab/DiskB/zjn/yuyi/ImageCompressionNN/project/models.py", line 19, in forward
return self.encoder(img)
File "/media/yangxilab/DiskA/anaconda3/envs/yuyi/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "/media/yangxilab/DiskB/zjn/yuyi/ImageCompressionNN/project/models.py", line 139, in forward
y = self.align()
File "/media/yangxilab/DiskB/zjn/yuyi/ImageCompressionNN/project/models.py", line 116, in align
y += conv(coef)
RuntimeError: The size of tensor a (64) must match the size of tensor b (1019) at non-singleton dimension 3
The relevant information is printed as follows:
y torch.Size([32, 32, 64])
coef torch.Size([8, 64, 256, 256])
conv ConvTranspose2d(64, 64, kernel_size=(3, 3), stride=(4, 4), padding=(1, 1))
conv(coef) torch.Size([8, 64, 1021, 1021])
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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. 📊📈🎉
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 ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.