hc/JSCC
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
ZHENG Chunhang 2024-01-16 22:54:43 +08:00 committed by GitHub
parent 824265511c
commit 2064fd28aa
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@ -1,5 +1,5 @@
# Deep JSCC
This implements training of deep JSCC models for wireless image transmission as described in the paper [Deep Joint Source-Channel Coding for Wireless Image Transmission](https://ieeexplore.ieee.org/abstract/document/8723589) by PyTorch. And there has been a [Tensorflow and keras implementations ](https://github.com/irdanish11/DJSCC-for-Wireless-Image-Transmission).
This implements training of deep JSCC models for wireless image transmission as described in the paper [Deep Joint Source-Channel Coding for Wireless Image Transmission](https://ieeexplore.ieee.org/abstract/document/8723589) by Pytorch. And there has been a [Tensorflow and keras implementations ](https://github.com/irdanish11/DJSCC-for-Wireless-Image-Transmission).
This is my first time to use PyTorch and git to reproduce a paper, so there may be some mistakes. If you find any, please let me know. Thanks!
## Architecture
@ -25,6 +25,12 @@ pip install requirements.txt
```
## Usage
### Prepare Dataset
The cifar10 dataset can be downloaded automatically by torchvision. But the imagenet dataset should be downloaded manually and put in the right place, refer to [dataset.py](https://github.com/chunbaobao/Deep-JSCC-PyTorch/blob/main/dataset.py#L28). And run:
```
python dataset.py
```
### Training Model
Run(example presented in paper) on cifar10