Sample-design-alt
Sample-design-alt
yes, I have the same issue for this problem.
> I use Ubantu system, the error as follows: ERROR: Command errored out with exit status 1: command: /usr/local/bin/python -c 'import io, os, sys, setuptools, tokenize; sys.argv[0] = '"'"'/data/chenrj/SimTSC-main/pydtw/setup.py'"'"'; __file__='"'"'/data/chenrj/SimTSC-main/pydtw/setup.py'"'"';f...
I have the same question with you. The paper refers to 'It excels in zero-shot forecasting for out-of-domain data'. But how can the model get the 'prompt token'? The prompt...
I have the same problem with you.
LLM的backbone是冻结的，其余都是trainable，我采用GPT2、BERT、都会有一样的结果。
效果提升了一些，但仍然和其他方法相比仍然有差距，我发现如果patch_num 如果mean之后，再做分类，效果很差。所以最后一层的nn.linear(D*patch_num, num_classes)这样会好一些。你的输出层是怎么设计的？
可以，你也可以直接issue交流，更方便讨论
你是在哪儿数据集测试，datsets descrption？模型forward是怎么写的