Tenghanggoi
Tenghanggoi
we could calculate cosine similarity with following succinct code: cosine_similarity = F.cosine_similarity(support_image, target_set) where F is imported as torch.nn.functional
I can't find optim.zero_grad() after loss.backward(), have you cleaned the grad after backpropagation?
I fix this issue on BerriAI/litellm#4752
I faced the same problem. yeah, I fixed the metainfo.classes in config file, which I take a spelling error. this classes name must be match to datasets' categories name, then...
下载这个仓库[https://github.com/shivammehta25/Matcha-TTS],把里面的model文件夹复制到cosyvoice项目的根目录