Hello, I tried to load the pretrained checkpoints and faced a prblem of weights mismatch, code:
import os, torch
from collections import OrderedDict
import data
# change config file for ablation study...
from options.config_hifacegan import TestOptions
from models.pix2pix_model import Pix2PixModel
from util.visualizer import Visualizer
from util import html
import numpy as np
import cv2
from tqdm import tqdm
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
torch.backends.cudnn.benchmark = True
opt = TestOptions()
opt.name='4xsr'
# opt.checkpoints_dir='checkpoints/4xsr/'
# dataloader = data.create_dataloader(opt)
model = Pix2PixModel(opt)
### 20200218 Critical Bug
# When model is set to eval mode, the generated image
# is not enhanced whatsoever, with almost 0 residual
# when turned to training mode, it behaves as expected.
###
#model.eval()
#model.netG.eval()
model.netG.train()
error:
`
Network [HiFaceGANGenerator] was created. Total number of parameters: 130.6 million. To see the architecture, do print(network).
RuntimeError Traceback (most recent call last)
in
22 # dataloader = data.create_dataloader(opt)
23
---> 24 model = Pix2PixModel(opt)
25 ### 20200218 Critical Bug
26 # When model is set to eval mode, the generated image
~/git/Face-Renovation/models/pix2pix_model.py in init(self, opt)
24 else torch.ByteTensor
25
---> 26 self.netG, self.netD, self.netE = self.initialize_networks(opt)
27
28 # set loss functions
~/git/Face-Renovation/models/pix2pix_model.py in initialize_networks(self, opt)
186
187 if not opt.isTrain or opt.continue_train:
--> 188 netG = util.load_network(netG, 'G', opt.which_epoch, opt)
189 if opt.isTrain:
190 netD = util.load_network(netD, 'D', opt.which_epoch, opt)
~/git/Face-Renovation/util/util.py in load_network(net, label, epoch, opt)
207 save_path = os.path.join(save_dir, save_filename)
208 weights = torch.load(save_path)
--> 209 net.load_state_dict(weights)
210 print('Load checkpoint from path: ', save_path)
211 return net
~/.conda/envs/face-renovation/lib/python3.7/site-packages/torch/nn/modules/module.py in load_state_dict(self, state_dict, strict)
1043 0, 'Unexpected key(s) in state_dict: {}. '.format(
1044 ', '.join('"{}"'.format(k) for k in unexpected_keys)))
-> 1045 if len(missing_keys) > 0:
1046 error_msgs.insert(
1047 0, 'Missing key(s) in state_dict: {}. '.format(
RuntimeError: Error(s) in loading state_dict for HiFaceGANGenerator:
Missing key(s) in state_dict: "encoder.head.0.weight", "encoder.encoder_0.0.logit.0.weight", "encoder.encoder_0.0.logit.1.weight", "encoder.encoder_0.0.logit.1.bias", "encoder.encoder_0.1.weight", "encoder.encoder_0.1.bias", "encoder.encoder_1.0.logit.0.weight", "encoder.encoder_1.0.logit.1.weight", "encoder.encoder_1.0.logit.1.bias", "encoder.encoder_1.1.weight", "encoder.encoder_1.1.bias", "encoder.encoder_2.0.logit.0.weight", "encoder.encoder_2.0.logit.1.weight", "encoder.encoder_2.0.logit.1.bias", "encoder.encoder_2.1.weight", "encoder.encoder_2.1.bias", "encoder.encoder_3.0.logit.0.weight", "encoder.encoder_3.0.logit.1.weight", "encoder.encoder_3.0.logit.1.bias", "encoder.encoder_3.1.weight", "encoder.encoder_3.1.bias", "encoder.encoder_4.0.logit.0.weight", "encoder.encoder_4.0.logit.1.weight", "encoder.encoder_4.0.logit.1.bias", "encoder.encoder_4.1.weight", "encoder.encoder_4.1.bias".
size mismatch for fc.weight: copying a param with shape torch.Size([768, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 3, 3, 3]).
size mismatch for fc.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for head_0.conv_0.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for head_0.conv_0.weight_orig: copying a param with shape torch.Size([768, 768, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 1024, 3, 3]).
size mismatch for head_0.conv_0.weight_u: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for head_0.conv_0.weight_v: copying a param with shape torch.Size([6912]) from checkpoint, the shape in current model is torch.Size([9216]).
size mismatch for head_0.conv_1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for head_0.conv_1.weight_orig: copying a param with shape torch.Size([768, 768, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 1024, 3, 3]).
size mismatch for head_0.conv_1.weight_u: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for head_0.conv_1.weight_v: copying a param with shape torch.Size([6912]) from checkpoint, the shape in current model is torch.Size([9216]).
size mismatch for head_0.norm_0.param_free_norm.running_mean: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for head_0.norm_0.param_free_norm.running_var: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for head_0.norm_0.mlp_shared.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 1024, 3, 3]).
size mismatch for head_0.norm_0.mlp_gamma.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for head_0.norm_0.mlp_beta.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for head_0.norm_1.param_free_norm.running_mean: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for head_0.norm_1.param_free_norm.running_var: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for head_0.norm_1.mlp_shared.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 1024, 3, 3]).
size mismatch for head_0.norm_1.mlp_gamma.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for head_0.norm_1.mlp_beta.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for G_middle_0.conv_0.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_0.conv_0.weight_orig: copying a param with shape torch.Size([768, 768, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 1024, 3, 3]).
size mismatch for G_middle_0.conv_0.weight_u: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_0.conv_0.weight_v: copying a param with shape torch.Size([6912]) from checkpoint, the shape in current model is torch.Size([9216]).
size mismatch for G_middle_0.conv_1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_0.conv_1.weight_orig: copying a param with shape torch.Size([768, 768, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 1024, 3, 3]).
size mismatch for G_middle_0.conv_1.weight_u: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_0.conv_1.weight_v: copying a param with shape torch.Size([6912]) from checkpoint, the shape in current model is torch.Size([9216]).
size mismatch for G_middle_0.norm_0.param_free_norm.running_mean: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_0.norm_0.param_free_norm.running_var: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_0.norm_0.mlp_shared.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 1024, 3, 3]).
size mismatch for G_middle_0.norm_0.mlp_gamma.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for G_middle_0.norm_0.mlp_beta.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for G_middle_0.norm_1.param_free_norm.running_mean: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_0.norm_1.param_free_norm.running_var: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_0.norm_1.mlp_shared.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 1024, 3, 3]).
size mismatch for G_middle_0.norm_1.mlp_gamma.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for G_middle_0.norm_1.mlp_beta.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for G_middle_1.conv_0.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_1.conv_0.weight_orig: copying a param with shape torch.Size([768, 768, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 1024, 3, 3]).
size mismatch for G_middle_1.conv_0.weight_u: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_1.conv_0.weight_v: copying a param with shape torch.Size([6912]) from checkpoint, the shape in current model is torch.Size([9216]).
size mismatch for G_middle_1.conv_1.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_1.conv_1.weight_orig: copying a param with shape torch.Size([768, 768, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 1024, 3, 3]).
size mismatch for G_middle_1.conv_1.weight_u: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_1.conv_1.weight_v: copying a param with shape torch.Size([6912]) from checkpoint, the shape in current model is torch.Size([9216]).
size mismatch for G_middle_1.norm_0.param_free_norm.running_mean: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_1.norm_0.param_free_norm.running_var: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_1.norm_0.mlp_shared.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 1024, 3, 3]).
size mismatch for G_middle_1.norm_0.mlp_gamma.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for G_middle_1.norm_0.mlp_beta.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for G_middle_1.norm_1.param_free_norm.running_mean: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_1.norm_1.param_free_norm.running_var: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for G_middle_1.norm_1.mlp_shared.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 1024, 3, 3]).
size mismatch for G_middle_1.norm_1.mlp_gamma.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for G_middle_1.norm_1.mlp_beta.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for ups.0.conv_0.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for ups.0.conv_0.weight_orig: copying a param with shape torch.Size([384, 768, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 1024, 3, 3]).
size mismatch for ups.0.conv_0.weight_u: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for ups.0.conv_0.weight_v: copying a param with shape torch.Size([6912]) from checkpoint, the shape in current model is torch.Size([9216]).
size mismatch for ups.0.conv_1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for ups.0.conv_1.weight_orig: copying a param with shape torch.Size([384, 384, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 512, 3, 3]).
size mismatch for ups.0.conv_1.weight_u: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for ups.0.conv_1.weight_v: copying a param with shape torch.Size([3456]) from checkpoint, the shape in current model is torch.Size([4608]).
size mismatch for ups.0.conv_s.weight_orig: copying a param with shape torch.Size([384, 768, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 1024, 1, 1]).
size mismatch for ups.0.conv_s.weight_u: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for ups.0.conv_s.weight_v: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for ups.0.norm_0.param_free_norm.running_mean: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for ups.0.norm_0.param_free_norm.running_var: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for ups.0.norm_0.mlp_shared.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 512, 3, 3]).
size mismatch for ups.0.norm_0.mlp_gamma.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for ups.0.norm_0.mlp_beta.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for ups.0.norm_1.param_free_norm.running_mean: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for ups.0.norm_1.param_free_norm.running_var: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for ups.0.norm_1.mlp_shared.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 512, 3, 3]).
size mismatch for ups.0.norm_1.mlp_gamma.weight: copying a param with shape torch.Size([384, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 128, 3, 3]).
size mismatch for ups.0.norm_1.mlp_beta.weight: copying a param with shape torch.Size([384, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 128, 3, 3]).
size mismatch for ups.0.norm_s.param_free_norm.running_mean: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for ups.0.norm_s.param_free_norm.running_var: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for ups.0.norm_s.mlp_shared.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 512, 3, 3]).
size mismatch for ups.0.norm_s.mlp_gamma.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for ups.0.norm_s.mlp_beta.weight: copying a param with shape torch.Size([768, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([1024, 128, 3, 3]).
size mismatch for ups.1.conv_0.bias: copying a param with shape torch.Size([192]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ups.1.conv_0.weight_orig: copying a param with shape torch.Size([192, 384, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 512, 3, 3]).
size mismatch for ups.1.conv_0.weight_u: copying a param with shape torch.Size([192]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ups.1.conv_0.weight_v: copying a param with shape torch.Size([3456]) from checkpoint, the shape in current model is torch.Size([4608]).
size mismatch for ups.1.conv_1.bias: copying a param with shape torch.Size([192]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ups.1.conv_1.weight_orig: copying a param with shape torch.Size([192, 192, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 256, 3, 3]).
size mismatch for ups.1.conv_1.weight_u: copying a param with shape torch.Size([192]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ups.1.conv_1.weight_v: copying a param with shape torch.Size([1728]) from checkpoint, the shape in current model is torch.Size([2304]).
size mismatch for ups.1.conv_s.weight_orig: copying a param with shape torch.Size([192, 384, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 512, 1, 1]).
size mismatch for ups.1.conv_s.weight_u: copying a param with shape torch.Size([192]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ups.1.conv_s.weight_v: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for ups.1.norm_0.param_free_norm.running_mean: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for ups.1.norm_0.param_free_norm.running_var: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for ups.1.norm_0.mlp_shared.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 256, 3, 3]).
size mismatch for ups.1.norm_0.mlp_gamma.weight: copying a param with shape torch.Size([384, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 128, 3, 3]).
size mismatch for ups.1.norm_0.mlp_beta.weight: copying a param with shape torch.Size([384, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 128, 3, 3]).
size mismatch for ups.1.norm_1.param_free_norm.running_mean: copying a param with shape torch.Size([192]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ups.1.norm_1.param_free_norm.running_var: copying a param with shape torch.Size([192]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ups.1.norm_1.mlp_shared.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 256, 3, 3]).
size mismatch for ups.1.norm_1.mlp_gamma.weight: copying a param with shape torch.Size([192, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 128, 3, 3]).
size mismatch for ups.1.norm_1.mlp_beta.weight: copying a param with shape torch.Size([192, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 128, 3, 3]).
size mismatch for ups.1.norm_s.param_free_norm.running_mean: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for ups.1.norm_s.param_free_norm.running_var: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([512]).
size mismatch for ups.1.norm_s.mlp_shared.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 256, 3, 3]).
size mismatch for ups.1.norm_s.mlp_gamma.weight: copying a param with shape torch.Size([384, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 128, 3, 3]).
size mismatch for ups.1.norm_s.mlp_beta.weight: copying a param with shape torch.Size([384, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 128, 3, 3]).
size mismatch for ups.2.conv_0.bias: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.2.conv_0.weight_orig: copying a param with shape torch.Size([96, 192, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 256, 3, 3]).
size mismatch for ups.2.conv_0.weight_u: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.2.conv_0.weight_v: copying a param with shape torch.Size([1728]) from checkpoint, the shape in current model is torch.Size([2304]).
size mismatch for ups.2.conv_1.bias: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.2.conv_1.weight_orig: copying a param with shape torch.Size([96, 96, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
size mismatch for ups.2.conv_1.weight_u: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.2.conv_1.weight_v: copying a param with shape torch.Size([864]) from checkpoint, the shape in current model is torch.Size([1152]).
size mismatch for ups.2.conv_s.weight_orig: copying a param with shape torch.Size([96, 192, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 256, 1, 1]).
size mismatch for ups.2.conv_s.weight_u: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.2.conv_s.weight_v: copying a param with shape torch.Size([192]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ups.2.norm_0.param_free_norm.running_mean: copying a param with shape torch.Size([192]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ups.2.norm_0.param_free_norm.running_var: copying a param with shape torch.Size([192]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ups.2.norm_0.mlp_shared.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
size mismatch for ups.2.norm_0.mlp_gamma.weight: copying a param with shape torch.Size([192, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 128, 3, 3]).
size mismatch for ups.2.norm_0.mlp_beta.weight: copying a param with shape torch.Size([192, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 128, 3, 3]).
size mismatch for ups.2.norm_1.param_free_norm.running_mean: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.2.norm_1.param_free_norm.running_var: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.2.norm_1.mlp_shared.0.weight: copying a param with shape torch.Size([96, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
size mismatch for ups.2.norm_1.mlp_shared.0.bias: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.2.norm_1.mlp_gamma.weight: copying a param with shape torch.Size([96, 96, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
size mismatch for ups.2.norm_1.mlp_beta.weight: copying a param with shape torch.Size([96, 96, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
size mismatch for ups.2.norm_s.param_free_norm.running_mean: copying a param with shape torch.Size([192]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ups.2.norm_s.param_free_norm.running_var: copying a param with shape torch.Size([192]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ups.2.norm_s.mlp_shared.0.weight: copying a param with shape torch.Size([128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
size mismatch for ups.2.norm_s.mlp_gamma.weight: copying a param with shape torch.Size([192, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 128, 3, 3]).
size mismatch for ups.2.norm_s.mlp_beta.weight: copying a param with shape torch.Size([192, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 128, 3, 3]).
size mismatch for ups.3.conv_0.bias: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for ups.3.conv_0.weight_orig: copying a param with shape torch.Size([48, 96, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 128, 3, 3]).
size mismatch for ups.3.conv_0.weight_u: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for ups.3.conv_0.weight_v: copying a param with shape torch.Size([864]) from checkpoint, the shape in current model is torch.Size([1152]).
size mismatch for ups.3.conv_1.bias: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for ups.3.conv_1.weight_orig: copying a param with shape torch.Size([48, 48, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]).
size mismatch for ups.3.conv_1.weight_u: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for ups.3.conv_1.weight_v: copying a param with shape torch.Size([432]) from checkpoint, the shape in current model is torch.Size([576]).
size mismatch for ups.3.conv_s.weight_orig: copying a param with shape torch.Size([48, 96, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 128, 1, 1]).
size mismatch for ups.3.conv_s.weight_u: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for ups.3.conv_s.weight_v: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.3.norm_0.param_free_norm.running_mean: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.3.norm_0.param_free_norm.running_var: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.3.norm_0.mlp_shared.0.weight: copying a param with shape torch.Size([96, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 64, 3, 3]).
size mismatch for ups.3.norm_0.mlp_shared.0.bias: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.3.norm_0.mlp_gamma.weight: copying a param with shape torch.Size([96, 96, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
size mismatch for ups.3.norm_0.mlp_beta.weight: copying a param with shape torch.Size([96, 96, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
size mismatch for ups.3.norm_1.param_free_norm.running_mean: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for ups.3.norm_1.param_free_norm.running_var: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for ups.3.norm_1.mlp_shared.0.weight: copying a param with shape torch.Size([48, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]).
size mismatch for ups.3.norm_1.mlp_shared.0.bias: copying a param with shape torch.Size([48]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for ups.3.norm_1.mlp_gamma.weight: copying a param with shape torch.Size([48, 48, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]).
size mismatch for ups.3.norm_1.mlp_beta.weight: copying a param with shape torch.Size([48, 48, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 64, 3, 3]).
size mismatch for ups.3.norm_s.param_free_norm.running_mean: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.3.norm_s.param_free_norm.running_var: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.3.norm_s.mlp_shared.0.weight: copying a param with shape torch.Size([96, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 64, 3, 3]).
size mismatch for ups.3.norm_s.mlp_shared.0.bias: copying a param with shape torch.Size([96]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for ups.3.norm_s.mlp_gamma.weight: copying a param with shape torch.Size([96, 96, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
size mismatch for ups.3.norm_s.mlp_beta.weight: copying a param with shape torch.Size([96, 96, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 128, 3, 3]).
size mismatch for to_rgbs.0.weight: copying a param with shape torch.Size([3, 384, 3, 3]) from checkpoint, the shape in current model is torch.Size([3, 512, 3, 3]).
size mismatch for to_rgbs.1.weight: copying a param with shape torch.Size([3, 192, 3, 3]) from checkpoint, the shape in current model is torch.Size([3, 256, 3, 3]).
size mismatch for to_rgbs.2.weight: copying a param with shape torch.Size([3, 96, 3, 3]) from checkpoint, the shape in current model is torch.Size([3, 128, 3, 3]).
size mismatch for to_rgbs.3.weight: copying a param with shape torch.Size([3, 48, 3, 3]) from checkpoint, the shape in current model is torch.Size([3, 64, 3, 3]).
`
Tested with torch 1.8.1, 1.6, 1.5