保存模型出现错误 Save the latest model calculate_psnr() missing 1 required positional argument: 'img'

[xsmbb]

我在训练完成 保存模型时出现了一点问题 有没有大哥救救我 2021-11-16 06:22:08,277 INFO: Save the latest model. 0%| | 0/1 [00:00<?, ?image/s]Traceback (most recent call last): File "gfpgan/train.py", line 11, in train_pipeline(root_path) File "/root/miniconda3/envs/myconda/lib/python3.8/site-packages/basicsr/train.py", line 208, in train_pipeline model.validation(val_loader, current_iter, tb_logger, opt['val']['save_img']) File "/root/miniconda3/envs/myconda/lib/python3.8/site-packages/basicsr/models/base_model.py", line 46, in validation self.dist_validation(dataloader, current_iter, tb_logger, save_img) File "/root/miniconda3/envs/myconda/lib/python3.8/site-packages/gfpgan/models/gfpgan_model.py", line 483, in dist_validation self.nondist_validation(dataloader, current_iter, tb_logger, save_img) File "/root/miniconda3/envs/myconda/lib/python3.8/site-packages/gfpgan/models/gfpgan_model.py", line 526, in nondist_validation self.metric_results[name] += calculate_metric(metric_data, opt_) File "/root/miniconda3/envs/myconda/lib/python3.8/site-packages/basicsr/metrics/init.py", line 19, in calculate_metric metric = METRIC_REGISTRY.get(metric_type)(**data, **opt)

TypeError: calculate_psnr() missing 1 required positional argument: 'img' 0%| | 0/1 [00:00<?, ?image/s] ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 473) of binary: /root/miniconda3/envs/myconda/bin/python

[chenloveheimei]

我在训练完成 保存模型时出现了一点问题 有没有大哥救救我 2021-11-16 06:22:08,277 INFO: Save the latest model. 0%| | 0/1 [00:00<?, ?image/s]Traceback (most recent call last): File "gfpgan/train.py", line 11, in train_pipeline(root_path) File "/root/miniconda3/envs/myconda/lib/python3.8/site-packages/basicsr/train.py", line 208, in train_pipeline model.validation(val_loader, current_iter, tb_logger, opt['val']['save_img']) File "/root/miniconda3/envs/myconda/lib/python3.8/site-packages/basicsr/models/base_model.py", line 46, in validation self.dist_validation(dataloader, current_iter, tb_logger, save_img) File "/root/miniconda3/envs/myconda/lib/python3.8/site-packages/gfpgan/models/gfpgan_model.py", line 483, in dist_validation self.nondist_validation(dataloader, current_iter, tb_logger, save_img) File "/root/miniconda3/envs/myconda/lib/python3.8/site-packages/gfpgan/models/gfpgan_model.py", line 526, in nondist_validation self.metric_results[name] += calculate_metric(metric_data, opt_) File "/root/miniconda3/envs/myconda/lib/python3.8/site-packages/basicsr/metrics/init.py", line 19, in calculate_metric metric = METRIC_REGISTRY.get(metric_type)(**data, **opt)

TypeError: calculate_psnr() missing 1 required positional argument: 'img' 0%| | 0/1 [00:00<?, ?image/s] ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 473) of binary: /root/miniconda3/envs/myconda/bin/python

你问题解决了吗？我也遇到这个问题了

[Zhaiyan1996]

这两位小哥可以分享一下你们train的过程吗？或者给我指导一下，我现在的问题是这样的： File "train.py", line 10, in train_pipeline(root_path) File "/home/yanglin/anaconda3/envs/zhaiyan3.8/lib/python3.8/site-packages/basicsr/train.py", line 169, in train_pipeline model.optimize_parameters(current_iter) File "/home/yanglin/zhaiyan/GFPGAN/gfpgan/models/gfpgan_model.py", line 308, in optimize_parameters self.output, out_rgbs = self.net_g(self.lq, return_rgb=True) File "/home/yanglin/anaconda3/envs/zhaiyan3.8/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yanglin/anaconda3/envs/zhaiyan3.8/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 619, in forward output = self.module(*inputs[0], **kwargs[0]) File "/home/yanglin/anaconda3/envs/zhaiyan3.8/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yanglin/zhaiyan/GFPGAN/gfpgan/archs/gfpganv1_arch.py", line 353, in forward feat = self.conv_body_downi File "/home/yanglin/anaconda3/envs/zhaiyan3.8/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yanglin/anaconda3/envs/zhaiyan3.8/lib/python3.8/site-packages/basicsr/archs/stylegan2_arch.py", line 726, in forward out = self.conv2(out) File "/home/yanglin/anaconda3/envs/zhaiyan3.8/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yanglin/anaconda3/envs/zhaiyan3.8/lib/python3.8/site-packages/torch/nn/modules/container.py", line 117, in forward input = module(input) File "/home/yanglin/anaconda3/envs/zhaiyan3.8/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/yanglin/anaconda3/envs/zhaiyan3.8/lib/python3.8/site-packages/basicsr/archs/stylegan2_arch.py", line 635, in forward out = F.conv2d( TypeError: conv2d(): argument 'input' (position 1) must be Tensor, not NoneType Traceback (most recent call last): File "/home/yanglin/anaconda3/envs/zhaiyan3.8/lib/python3.8/runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None, File "/home/yanglin/anaconda3/envs/zhaiyan3.8/lib/python3.8/runpy.py", line 87, in _run_code exec(code, run_globals) 盼回复~