PMPBinZhang
PMPBinZhang
您好，我训练的时候train_batch_size给2，就报错(NotFound) Operator softmax does not have kernel for {data_type[int64_t]; data_layout[Undefined(AnyLayout)]; place[Place(cpu)]; library_type[PLAIN]}. [Hint: Expected kernel_iter != kernels.end(), but received kernel_iter == kernels.end().] (at ..\paddle\fluid\imperative\prepared_operator.cc:419) [operator < softmax > error]，给4就没有这种情况，这是什么原因呢 |...
> Hi, thanks for your interest in our project. > > Sure! Our method is basically a 3D GAN inversion method, any 3D GAN (trained on real or anime images)...
can i get a 3D model like the input image，what does the second image in mid data mean, how to get this result.
哦哦哦，那有好的方法处理这种情况吗？可以成段生成，然后进行切割吗？
当使用 funasr 推理时，不想推理出情绪，但是ban_emo_unk参数不好用。
您好，这个问题解决了吗？我也经常碰见这个问题。