Question about testing

[purple7seven]

Thanks your project. I trained the model by my dataset. But when i test the model, i got the error.

Network structure: [DataParallel - SRFBN], with parameters: [3,631,478]

===> Loading model from [./experiments/SRFBN_in3f32_x4/epochs/best_ckp.pth]...
Traceback (most recent call last):
File "test.py", line 106, in
main()
File "test.py", line 35, in main
solver = create_solver(opt)
File "/home/xuhuali/projects/SRFBN_CVPR19/solvers/init.py", line 5, in create_solver
solver = SRSolver(opt)
File "/home/xuhuali/projects/SRFBN_CVPR19/solvers/SRSolver.py", line 70, in init
self.load()
File "/home/xuhuali/projects/SRFBN_CVPR19/solvers/SRSolver.py", line 309, in load
load_func(checkpoint)
File "/home/xuhuali/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 777, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for DataParallel:
Missing key(s) in state_dict: "module.block.upBlocks.3.0.weight", "module.block.upBlocks.3.0.bias", "module.block.upBlocks.3.1.weight", "module.block.upBlocks.4.0.weight", "module.block.upBlocks.4.0.bias", "module.block.upBlocks.4.1.weight", "module.block.upBlocks.5.0.weight", "module.block.upBlocks.5.0.bias", "module.block.upBlocks.5.1.weight", "module.block.downBlocks.3.0.weight", "module.block.downBlocks.3.0.bias", "module.block.downBlocks.3.1.weight", "module.block.downBlocks.4.0.weight", "module.block.downBlocks.4.0.bias", "module.block.downBlocks.4.1.weight", "module.block.downBlocks.5.0.weight", "module.block.downBlocks.5.0.bias", "module.block.downBlocks.5.1.weight", "module.block.uptranBlocks.2.0.weight", "module.block.uptranBlocks.2.0.bias", "module.block.uptranBlocks.2.1.weight", "module.block.uptranBlocks.3.0.weight", "module.block.uptranBlocks.3.0.bias", "module.block.uptranBlocks.3.1.weight", "module.block.uptranBlocks.4.0.weight", "module.block.uptranBlocks.4.0.bias", "module.block.uptranBlocks.4.1.weight", "module.block.downtranBlocks.2.0.weight", "module.block.downtranBlocks.2.0.bias", "module.block.downtranBlocks.2.1.weight", "module.block.downtranBlocks.3.0.weight", "module.block.downtranBlocks.3.0.bias", "module.block.downtranBlocks.3.1.weight", "module.block.downtranBlocks.4.0.weight", "module.block.downtranBlocks.4.0.bias", "module.block.downtranBlocks.4.1.weight".
size mismatch for module.conv_in.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 3, 3, 3]).
size mismatch for module.conv_in.0.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for module.feat_in.0.weight: copying a param with shape torch.Size([32, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]).
size mismatch for module.feat_in.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for module.block.compress_in.0.weight: copying a param with shape torch.Size([32, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 128, 1, 1]).
size mismatch for module.block.compress_in.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for module.block.upBlocks.0.0.weight: copying a param with shape torch.Size([32, 32, 8, 8]) from checkpoint, the shape in current model is torch.Size([64, 64, 8, 8]).
size mismatch for module.block.upBlocks.0.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for module.block.upBlocks.1.0.weight: copying a param with shape torch.Size([32, 32, 8, 8]) from checkpoint, the shape in current model is torch.Size([64, 64, 8, 8]).
size mismatch for module.block.upBlocks.1.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for module.block.upBlocks.2.0.weight: copying a param with shape torch.Size([32, 32, 8, 8]) from checkpoint, the shape in current model is torch.Size([64, 64, 8, 8]).
size mismatch for module.block.upBlocks.2.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for module.block.downBlocks.0.0.weight: copying a param with shape torch.Size([32, 32, 8, 8]) from checkpoint, the shape in current model is torch.Size([64, 64, 8, 8]).
size mismatch for module.block.downBlocks.0.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for module.block.downBlocks.1.0.weight: copying a param with shape torch.Size([32, 32, 8, 8]) from checkpoint, the shape in current model is torch.Size([64, 64, 8, 8]).
size mismatch for module.block.downBlocks.1.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for module.block.downBlocks.2.0.weight: copying a param with shape torch.Size([32, 32, 8, 8]) from checkpoint, the shape in current model is torch.Size([64, 64, 8, 8]).
size mismatch for module.block.downBlocks.2.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for module.block.uptranBlocks.0.0.weight: copying a param with shape torch.Size([32, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 128, 1, 1]).
size mismatch for module.block.uptranBlocks.0.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for module.block.uptranBlocks.1.0.weight: copying a param with shape torch.Size([32, 96, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 192, 1, 1]).
size mismatch for module.block.uptranBlocks.1.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for module.block.downtranBlocks.0.0.weight: copying a param with shape torch.Size([32, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 128, 1, 1]).
size mismatch for module.block.downtranBlocks.0.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for module.block.downtranBlocks.1.0.weight: copying a param with shape torch.Size([32, 96, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 192, 1, 1]).
size mismatch for module.block.downtranBlocks.1.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for module.block.compress_out.0.weight: copying a param with shape torch.Size([32, 96, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 384, 1, 1]).
size mismatch for module.block.compress_out.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for module.out.0.weight: copying a param with shape torch.Size([32, 32, 8, 8]) from checkpoint, the shape in current model is torch.Size([64, 64, 8, 8]).
size mismatch for module.out.0.bias: copying a param with shape torch.Size([32]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for module.conv_out.0.weight: copying a param with shape torch.Size([3, 32, 3, 3]) from checkpoint, the shape in current model is torch.Size([3, 64, 3, 3]).

Is my data wrong?or the pytorch version wrong?

[Paper99]

Maybe you need to modify your network options in test_*.json according to your training configures (network options in train_*.json).