chenjingcheng
chenjingcheng
i meet similar question: the image which copycrop return is blank.
我碰到你一样的，要修改加载数据的方式，我修改的代码： class FewShotDataset(Dataset): def __init__(self, path, processor, tokenizer, args): # max_seq_length = args.max_source_length + args.max_target_length with open(path, 'r', encoding='utf-8') as f: data = json.load(f) self.images = [] self.input_ids = []...
> 是不是没解压？ 您好，我也碰到这样问题，是在清华云下载的，内如下： total 17G -rw-rw-r-- 1 aifont aifont 2.1K Oct 13 13:51 config.json -rw-r--r-- 1 aifont aifont 4.4K Oct 13 14:04 configuration_chatglm.py -rw-r--r-- 1 aifont aifont 2.6M Oct 13...
哎，都做到这个，结果连个推理的脚本都没有。我也没有找到，看到说要放到webui上，为什么不能做个简单的推理脚本。
> @yeungchenwa Thanks for your reply. I tried to locate the code that needs to be modified, as you mentioned below, but I actually don't know how to modify it....
I meet the same problem.
I test it,it is very slow: Running on cpu Time: 0.005s Output: torch.Size([1, 8, 128, 128]) Running on mps Time: 0.292s Output: torch.Size([1, 8, 128, 128]) I built it from...