HantingChen
HantingChen
We only release evaluation code here. You may refer to mindspore code for training (https://gitee.com/mindspore/mindspore/tree/master/model_zoo/research/cv/IPT )
See https://gitee.com/mindspore/models/tree/master/research/cv/IPT
What is the meaning of inputting large sequance for position encoding? As the position encoding is added to the input patches, their size should be exactly same as the patches...
1. rain100L数据集的命名应该是norain-001.png和rain-001.png这样的格式，由于rain100L数据集的版本不止一个，请确定下载了正确版本的rain100L，我们使用的是和对比论文里相同版本的数据集，可以参考：https://github.com/csdwren/PReNet. 测试时不需要用到RainTrainL这个数据集，相应代码已经修改。 2. 数据集具体路径可以参考： ### Evaluation Process > Inference example: > For SR x2,x3,x4: ```bash python main.py --dir_data $DATA_PATH --pretrain $MODEL_PATH --data_test Set5+Set14+B100+Urban100 --scale $SCALE ``` > Note: path...
The code only support evaluation with fixed test batch size=1.
We have not planed to release the model for now. The config for deblurring: python main.py --dir_data $DATA_PATH --pretrain $MODEL_PATH --data_test GoPro --scale 1 --deblur --n_feats 9 --patch_dim 8 --patch_size...
> 为什么调用过程中会出现PermissionError: [Errno 13] Permission denied: '/cache'错误，谢谢解答 你好，你的/cache目录没有权限访问，可以尝试将数据和模型放在其他位置。
Note: path of images should be like: $MODEL_PATH/benchmark/CBSD68/XXX.png
Maybe you should rename your dataset as CBSD68, since we do not write codes for dataset BW.
> I tried. I thought adding "BW" to this would work? Was in a different issue thread. > > `self.loader_test = [] for d in args.data_test: if d in ['Set5',...