xiaoBIGfeng

> 你好，我在做推理的时候，显示在 preset/models/seesr路径下 缺少 diffusion_pytorch_model.bin 文件。但是作者给的预训练下载文件中，并没有这个文件。请问你遇到过同样的问题吗？ 这个报错是因为seesr/unet中没有diffusion_pytorch_model.bin文件，你是用作者提供的google云盘下载的吧，随着压缩包下载的还有一个diffusion_pytorch_model-001.safetensors，把-001删掉之后放到seesr/unet/里就可以了

It should be a problem with the file structure. The file storage structure for HR should be $DATA-PATH/benchmark/HR, while the storage structure for LR should be $DATA-PATH/benchmark/LR-bicubic/X2 The relevant code...

Note: path of paired images should be like: $DATA-PATH/benchmark/Set5/HR/baby.png and $DATA-PATH/benchmark/Set5/LR_bicubic/X2/babyx2.png

Thanks for your great work on VLMEvalKit and the powerful InternVL models. I've been trying to evaluate the InternVL3_5-38B model on the MMMU_DEV_VAL benchmark. I've been following the discussions in...