ClipCap-Chinese
ClipCap-Chinese copied to clipboard
yangjianxin1
基于ClipCap的看图说话Image Caption模型
raceback (most recent call last): File "ClipCap-Chinese-master/models/model.py", line 75, in __init__ self.gpt2 = GPT2LMHeadModel.from_pretrained(gpt2_path) File "/root/miniconda3/lib/python3.8/site-packages/transformers/modeling_utils.py", line 1222, in from_pretrained raise EnvironmentError( OSError: Error no file named ['pytorch_model.bin', 'tf_model.h5', 'model.ckpt.index',...
Traceback (most recent call last): File "predict.py", line 227, in main(args) File "predict.py", line 152, in main captions = generate(model, clip_embeds, tokenizer, args) File "predict.py", line 88, in generate next_token_ids...
https://github.com/yangjianxin1/ClipCap-Chinese/blob/fd109453a69a92cfd917a4a62fa97be046d15e91/models/model.py#L84C44-L84C44
Traceback (most recent call last): File "/home/ai/wzy/Code/ClipCap-Chinese-master/predict.py", line 190, in main(args) File "/home/ai/wzy/Code/ClipCap-Chinese-master/predict.py", line 148, in main clip_embeds = clip_model.encode_image(images) File "/home/ai/wzy/Hugging_face/CLIP-main/clip/model.py", line 341, in encode_image return self.visual(image.type(self.dtype)) File "/home/ai/anaconda3/envs/pyTorch/lib/python3.10/site-packages/torch/nn/modules/module.py",...
感谢您的工作！在实验过程中，我发现了以下问题： 1. model.py中gpt2的加载报错 ` try: self.gpt2 = GPT2LMHeadModel.from_pretrained(gpt2_path) logger.info('succeed to load pretrain gpt2 model') except: config = GPT2Config.from_pretrained(gpt2_path) self.gpt2 = GPT2LMHeadModel.from_config(config) logger.info('random initialize gpt2 model')` line178: AttributeError: type object 'GPT2LMHeadModel'...
Hi yang, Thanks for sharing the code and this is quite valuable work. I would like to know the performance of the CLIP in Chinese recently. Could you please release...
