Fictionarry / ER-NeRF

[ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis
https://fictionarry.github.io/ER-NeRF/
MIT License
894 stars 124 forks source link

训练的时候报错,这是为什么 #144

Closed superwhys closed 1 month ago

superwhys commented 2 months ago

执行训练脚本报错 python main.py data/obama/ --workspace trial_obama/ -O --iters 100000

这是我的环境 image

报错内容如下

/root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/modules/conv.h: In instantiation of ‘const torch::ExpandingArray<D>& torch::nn::ConvTransposeNdImpl<D, Derived>::padding() const [with long unsigned int D = 1; Derived = torch::nn::ConvTranspose1dImpl]’:
/root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/modules/conv.h:288:23:   required from ‘void torch::nn::ConvTransposeNdImpl<D, Derived>::pretty_print(std::ostream&) const [with long unsigned int D = 1; Derived = torch::nn::ConvTranspose1dImpl; std::ostream = std::basic_ostream<char>]’
/root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/modules/conv.h:282:8:   required from here
/root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/modules/conv.h:313:39: error: no matching function for call to ‘torch::nn::detail::ConvNdOptions<1>::padding() const’
  313 |     return std::get<ExpandingArray<D>>(this->options.padding());
      |            ~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~
In file included from /root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:3,
                 from /root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                 from /root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:4,
                 from /root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                 from /root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                 from /root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/all.h:9,
                 from /root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/extension.h:5,
                 from /home/hoven/ER-NeRF/raymarching/src/bindings.cpp:1:
/root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/options/conv.h:61:3: note: candidate: ‘decltype (*(torch::nn::detail::ConvNdOptions<D>*)this) torch::nn::detail::ConvNdOptions<D>::padding(const int&) [with long unsigned int D = 1; decltype (*(torch::nn::detail::ConvNdOptions<D>*)this) = torch::nn::detail::ConvNdOptions<1>&]’
   61 |   TORCH_ARG(padding_t, padding) = 0;
      |   ^~~~~~~~~
/root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/options/conv.h:61:3: note:   candidate expects 1 argument, 0 provided
/root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/options/conv.h:61:3: note: candidate: ‘decltype (*(torch::nn::detail::ConvNdOptions<D>*)this) torch::nn::detail::ConvNdOptions<D>::padding(int&&) [with long unsigned int D = 1; decltype (*(torch::nn::detail::ConvNdOptions<D>*)this) = torch::nn::detail::ConvNdOptions<1>&]’
   61 |   TORCH_ARG(padding_t, padding) = 0;
      |   ^~~~~~~~~
/root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/options/conv.h:61:3: note:   candidate expects 1 argument, 0 provided
In file included from /root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/functional/conv.h:3,
                 from /root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/functional.h:4,
                 from /root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn.h:4,
                 from /root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/all.h:16,
                 from /root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/extension.h:5,
                 from /home/hoven/ER-NeRF/raymarching/src/bindings.cpp:1:
/root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/options/conv.h:64:18: note: candidate: ‘decltype(auto) torch::nn::detail::ConvNdOptions<D>::padding(std::initializer_list<long int>) [with long unsigned int D = 1]’
   64 |   decltype(auto) padding(std::initializer_list<int64_t> il) {
      |                  ^~~~~~~
/root/anaconda3/envs/ernerf/lib/python3.10/site-packages/torch/include/torch/csrc/api/include/torch/nn/options/conv.h:64:18: note:   candidate expects 1 argument, 0 provided
ninja: build stopped: subcommand failed.
superwhys commented 2 months ago

这是为什么报错,研究了很久没搞明白

G-force78 commented 1 month ago

something to do with this I think https://stackoverflow.com/questions/50689784/in-google-collab-i-get-iopub-data-rate-exceeded not too sure how to change it