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

tiny spell-fix

Browse Source
This commit is contained in:
chun 2024-06-09 01:48:54 +08:00
parent 8796899e49
commit dce3f80d36
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -6,7 +6,7 @@ This is my first time to use PyTorch and git to reproduce a paper, so there may
## Update-2024.06.04 ## Update-2024.06.04
- modify the `train.py` to omit most of the args in command line, you can just us `python train.py --dataset ${dataset_name}` to train the model. - modify the `train.py` to omit most of the args in command line, you can just use `python train.py --dataset ${dataset_name}` to train the model.
- add tensorboard to record the results in exp. - add tensorboard to record the results in exp.
- add the `visualization/` file to visualize the result. - add the `visualization/` file to visualize the result.
- add bash file to run the code in parallel. - add bash file to run the code in parallel.
@ -22,7 +22,7 @@ This is my first time to use PyTorch and git to reproduce a paper, so there may
## Demo ## Demo
The model trained on cifar10 which is 32\*32 but test on kodim which is 768\*512 (left); and the model trained on imagenet which is resized to 128\*128 but test on kodim which is 768\*512 (right). The model trained on cifar10 which is 32\*32 but test on kodim which is 768\*512 (top); and the model trained on imagenet which is resized to 128\*128 but test on kodim which is 768\*512 (bottom).
<div style="display: flex;"> <div style="display: flex;">
<img src="./demo/cifar10_kodim08.png" alt="Image 1" style="flex: 1; max-width: 48%; height: auto;"> <img src="./demo/cifar10_kodim08.png" alt="Image 1" style="flex: 1; max-width: 48%; height: auto;">
<div style="width: 5px;"></div> <div style="width: 5px;"></div>