When I run the code, I got 'RuntimeWarning: invalid value encountered in scalar divide', and all score (avg PSNR, SSIM, MS-SSIM .etc) is NAN. Is there anything I missed ?
!!!!!!!!!!inference on 256*256
Initializing with device: cuda
scene_fold: []
Generating Floating EV stack1
Dataset info preparation!!
exp_result folder: ./train_strategy/experiment/CEVR_NormNoAffine_Maps_GN_Dmodel/exp_result_VDS_epochbest/ existed!
normal model
!!!! net_name = CEVR_NormNoAffine_Maps !!!!
CEVR(Maps) Normalization layer affine: False
/home/xxx/anaconda3/envs/xxx/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
warnings.warn(
/home/xxx/anaconda3/envs/xxxlib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=VGG16_BN_Weights.IMAGENET1K_V1. You can also use weights=VGG16_BN_Weights.DEFAULT to get the most up-to-date weights.
warnings.warn(msg)
BottleNeck normlization don't use affine(Learnable parameter)
#############################self.norm_type in bottleneck: GroupNorm ####################
Decoder normlization don't use affine(Learnable parameter)
#############################self.norm_type in DecoderBlock(Maps): GroupNorm ####################
Resize_conv upsample mode: bicubic
Decoder normlization don't use affine(Learnable parameter)
#############################self.norm_type in DecoderBlock(Maps): GroupNorm ####################
Resize_conv upsample mode: bicubic
Decoder normlization don't use affine(Learnable parameter)
#############################self.norm_type in DecoderBlock(Maps): GroupNorm ####################
Resize_conv upsample mode: bicubic
model_name: CEVR_NormNoAffine_Maps pretrain: vgg mlp_num: 3 decoder: mult_resizeUp_map activation: leaky_relu
!!!! net_name = CEVR_NormNoAffine_Maps !!!!
CEVR(Maps) Normalization layer affine: False
BottleNeck normlization don't use affine(Learnable parameter)
#############################self.norm_type in bottleneck: GroupNorm ####################
Decoder normlization don't use affine(Learnable parameter)
#############################self.norm_type in DecoderBlock(Maps): GroupNorm ####################
Resize_conv upsample mode: bicubic
Decoder normlization don't use affine(Learnable parameter)
#############################self.norm_type in DecoderBlock(Maps): GroupNorm ####################
Resize_conv upsample mode: bicubic
Decoder normlization don't use affine(Learnable parameter)
#############################self.norm_type in DecoderBlock(Maps): GroupNorm ####################
Resize_conv upsample mode: bicubic
model_name: CEVR_NormNoAffine_Maps pretrain: vgg mlp_num: 3 decoder: mult_resizeUp_map activation: leaky_relu
Model build up and load weight successfully!! Weight name: model_best.pth
/home/xxx/anaconda3/envs/xxx/lib/python3.9/site-packages/numpy/core/_methods.py:206: RuntimeWarning: Degrees of freedom <= 0 for slice
ret = _var(a, axis=axis, dtype=dtype, out=out, ddof=ddof,
/home/xxx/anaconda3/envs/xxx/lib/python3.9/site-packages/numpy/core/_methods.py:163: RuntimeWarning: invalid value encountered in divide
arrmean = um.true_divide(arrmean, div, out=arrmean,
/home/xxx/anaconda3/envs/xxx/lib/python3.9/site-packages/numpy/core/_methods.py:198: RuntimeWarning: invalid value encountered in scalar divide
ret = ret.dtype.type(ret / rcount)
/home/xxx/anaconda3/envs/xxx/lib/python3.9/site-packages/numpy/core/fromnumeric.py:3504: RuntimeWarning: Mean of empty slice.
return _methods._mean(a, axis=axis, dtype=dtype,
/home/xxx/anaconda3/envs/xxx/lib/python3.9/site-packages/numpy/core/_methods.py:129: RuntimeWarning: invalid value encountered in scalar divide
ret = ret.dtype.type(ret / rcount)
EV -3 avg PSNR: 0 , std: nan , avg SSIM: nan , std: nan svg MS-SSIM: nan , std: nan
EV -2 avg PSNR: 0 , std: nan , avg SSIM: nan , std: nan svg MS-SSIM: nan , std: nan
EV -1 avg PSNR: 0 , std: nan , avg SSIM: nan , std: nan svg MS-SSIM: nan , std: nan
EV 1 avg PSNR: 0 , std: nan , avg SSIM: nan , std: nan svg MS-SSIM: nan , std: nan
EV 2 avg PSNR: 0 , std: nan , avg SSIM: nan , std: nan svg MS-SSIM: nan , std: nan
EV 3 avg PSNR: 0 , std: nan , avg SSIM: nan , std: nan svg MS-SSIM: nan , std: nan
Note: The pth file in 'train_strategy/experiment/CEVR_NormNoAffine_Maps_GN_Bmodel/inc' should be model_best.pth, not 'final_model.pth'
!!!!!!!!!!inference on 256*256
Initializing with device: cuda
scene_fold: []
Generating Floating EV stack1
Dataset info preparation!!
exp_result folder: ./train_strategy/experiment/CEVR_NormNoAffine_Maps_GN_Dmodel/exp_result_VDS_epochbest/ existed!
normal model
!!!! net_name = CEVR_NormNoAffine_Maps !!!!
CEVR(Maps) Normalization layer affine: False
/home/xxx/anaconda3/envs/xxx/lib/python3.9/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
warnings.warn(
/home/xxx/anaconda3/envs/xxx/lib/python3.9/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior
is equivalent to passing weights=VGG16_BN_Weights.IMAGENET1K_V1. You can also use weights=VGG16_BN_Weights.DEFAULT to get the most up-to-date weights.
warnings.warn(msg)
BottleNeck normlization don't use affine(Learnable parameter)
#############################self.norm_type in bottleneck: GroupNorm ####################
Decoder normlization don't use affine(Learnable parameter)
#############################self.norm_type in DecoderBlock(Maps): GroupNorm ####################
Resize_conv upsample mode: bicubic
Decoder normlization don't use affine(Learnable parameter)
#############################self.norm_type in DecoderBlock(Maps): GroupNorm ####################
Resize_conv upsample mode: bicubic
Decoder normlization don't use affine(Learnable parameter)
#############################self.norm_type in DecoderBlock(Maps): GroupNorm ####################
Resize_conv upsample mode: bicubic
model_name: CEVR_NormNoAffine_Maps pretrain: vgg mlp_num: 3 decoder: mult_resizeUp_map activation: leaky_relu
!!!! net_name = CEVR_NormNoAffine_Maps !!!!
CEVR(Maps) Normalization layer affine: False
BottleNeck normlization don't use affine(Learnable parameter)
#############################self.norm_type in bottleneck: GroupNorm ####################
Decoder normlization don't use affine(Learnable parameter)
#############################self.norm_type in DecoderBlock(Maps): GroupNorm ####################
Resize_conv upsample mode: bicubic
Decoder normlization don't use affine(Learnable parameter)
#############################self.norm_type in DecoderBlock(Maps): GroupNorm ####################
Resize_conv upsample mode: bicubic
Decoder normlization don't use affine(Learnable parameter)
#############################self.norm_type in DecoderBlock(Maps): GroupNorm ####################
Resize_conv upsample mode: bicubic
model_name: CEVR_NormNoAffine_Maps pretrain: vgg mlp_num: 3 decoder: mult_resizeUp_map activation: leaky_relu
Traceback (most recent call last):
File "/home/xxx/2023_CEVR/demo_VDS.py", line 154, in
model_inc.load_state_dict(torch.load(B_path + 'inc/' + weight_name))
File "/home/xxx/anaconda3/envs/xxx/lib/python3.9/site-packages/torch/serialization.py", line 771, in load
with _open_file_like(f, 'rb') as opened_file:
File "/home/zwhong/anaconda3/envs/xxx/lib/python3.9/site-packages/torch/serialization.py", line 270, in _open_file_like
return _open_file(name_or_buffer, mode)
File "/home/xxx/anaconda3/envs/xxx/lib/python3.9/site-packages/torch/serialization.py", line 251, in init
super(_open_file, self).init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: './train_strategy/experiment/CEVR_NormNoAffine_Maps_GN_Bmodel/inc/model_best.pth'
When I run the code, I got 'RuntimeWarning: invalid value encountered in scalar divide', and all score (avg PSNR, SSIM, MS-SSIM .etc) is NAN. Is there anything I missed ?
Note: The pth file in 'train_strategy/experiment/CEVR_NormNoAffine_Maps_GN_Bmodel/inc' should be model_best.pth, not 'final_model.pth'