Issues with load_state_dict when putting Unet into production (model loading)

Andal · April 17, 2020, 8:05pm

I run a Unet model in cloab:

arch = models.resnet34
bs,size=32,128
wd = 1e-3
learn_gen = unet_learner(data, arch, wd=wd, loss_func=F.l1_loss, callback_fns=LossMetrics,
blur=True, norm_type=NormType.Weight)

I run that model and save a version of it on my machine in a folder: ‘/model’

from there I create a data path and a data file:

data_path = os.getcwd() + ‘/data’
data = (ImageImageList.from_folder(data_path).split_by_rand_pct(0.1, seed=42)
.label_from_func(lambda x: data_path/x)
.transform(get_transforms(), size=size, tfm_y=True)
.databunch(bs=1).normalize(imagenet_stats, do_y=True))
data.c = 3

I then want to load that model and make predictions on my machine:

#load the model path
model_path = os.getcwd() + ‘/model’
#load the model state
state= torch.load(model_path + ‘/Gen_Test.pth’, map_location=torch.device(‘cpu’))
#create an instance of the model
body = create_body(models.resnet34, True, None)
data_classes=data.c
nf = callbacks.hooks.num_features_model(body) * 2
head = create_head(nf, data_classes, None, ps=0.5, bn_final=False)
model = nn.Sequential(body, head)

#load the state of the model I saved earlier
model.load_state_dict(state)

This gives me the following error:

Unexpected key(s) in state_dict: “model”, “opt”.

Help is greatly appreciated - I really wasn’t lazy. I am out of options…

Andal · April 17, 2020, 8:36pm

Update: if I set state = state[‘model’], I don’t get the “Unexpected key(s) in state_dict: “model”, “opt”.” error anymore, but I get the following error:

RuntimeError: Error(s) in loading state_dict for Sequential:
Missing key(s) in state_dict: “0.0.weight”, “0.1.weight”, “0.1.bias”, “0.1.running_mean”, “0.1.running_var”, “0.4.0.conv1.weight”, “0.4.0.bn1.weight”, “0.4.0.bn1.bias”, “0.4.0.bn1.running_mean”, “0.4.0.bn1.running_var”, “0.4.0.conv2.weight”, “0.4.0.bn2.weight”, “0.4.0.bn2.bias”, “0.4.0.bn2.running_mean”, “0.4.0.bn2.running_var”, “0.4.1.conv1.weight”, “0.4.1.bn1.weight”, “0.4.1.bn1.bias”, “0.4.1.bn1.running_mean”, “0.4.1.bn1.running_var”, “0.4.1.conv2.weight”, “0.4.1.bn2.weight”, “0.4.1.bn2.bias”, “0.4.1.bn2.running_mean”, “0.4.1.bn2.running_var”, “0.4.2.conv1.weight”, “0.4.2.bn1.weight”, “0.4.2.bn1.bias”, “0.4.2.bn1.running_mean”, “0.4.2.bn1.running_var”, “0.4.2.conv2.weight”, “0.4.2.bn2.weight”, “0.4.2.bn2.bias”, “0.4.2.bn2.running_mean”, “0.4.2.bn2.running_var”, “0.5.0.conv1.weight”, “0.5.0.bn1.weight”, “0.5.0.bn1.bias”, “0.5.0.bn1.running_mean”, “0.5.0.bn1.running_var”, “0.5.0.conv2.weight”, “0.5.0.bn2.weight”, “0.5.0.bn2.bias”,

This list of missing weights goes on for a while

This is the output of print(learn_gen):

Test: None, model=DynamicUnet(
(layers): ModuleList(
(0): Sequential(
(0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(4): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(1): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(2): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(5): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(2): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(3): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(6): Sequential(
(0): BasicBlock(
(conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(2): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(3): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(4): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(5): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(7): Sequential(
(0): BasicBlock(
(conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(2): BasicBlock(
(conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU()
(3): Sequential(
(0): Sequential(
(0): Conv2d(512, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
)
(1): Sequential(
(0): Conv2d(1024, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
)
)
(4): UnetBlock(
(shuf): PixelShuffle_ICNR(
(conv): Sequential(
(0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1))
)
(shuf): PixelShuffle(upscale_factor=2)
(pad): ReplicationPad2d((1, 0, 1, 0))
(blur): AvgPool2d(kernel_size=2, stride=1, padding=0)
(relu): ReLU(inplace=True)
)
(bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv1): Sequential(
(0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
)
(relu): ReLU()
)
(5): UnetBlock(
(shuf): PixelShuffle_ICNR(
(conv): Sequential(
(0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1))
)
(shuf): PixelShuffle(upscale_factor=2)
(pad): ReplicationPad2d((1, 0, 1, 0))
(blur): AvgPool2d(kernel_size=2, stride=1, padding=0)
(relu): ReLU(inplace=True)
)
(bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv1): Sequential(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
)
(relu): ReLU()
)
(6): UnetBlock(
(shuf): PixelShuffle_ICNR(
(conv): Sequential(
(0): Conv2d(384, 768, kernel_size=(1, 1), stride=(1, 1))
)
(shuf): PixelShuffle(upscale_factor=2)
(pad): ReplicationPad2d((1, 0, 1, 0))
(blur): AvgPool2d(kernel_size=2, stride=1, padding=0)
(relu): ReLU(inplace=True)
)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv1): Sequential(
(0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
)
(relu): ReLU()
)
(7): UnetBlock(
(shuf): PixelShuffle_ICNR(
(conv): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1))
)
(shuf): PixelShuffle(upscale_factor=2)
(pad): ReplicationPad2d((1, 0, 1, 0))
(blur): AvgPool2d(kernel_size=2, stride=1, padding=0)
(relu): ReLU(inplace=True)
)
(bn): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(conv1): Sequential(
(0): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
)
(conv2): Sequential(
(0): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
)
(relu): ReLU()
)
(8): PixelShuffle_ICNR(
(conv): Sequential(
(0): Conv2d(96, 384, kernel_size=(1, 1), stride=(1, 1))
)
(shuf): PixelShuffle(upscale_factor=2)
(pad): ReplicationPad2d((1, 0, 1, 0))
(blur): AvgPool2d(kernel_size=2, stride=1, padding=0)
(relu): ReLU(inplace=True)
)
(9): MergeLayer()
(10): SequentialEx(
(layers): ModuleList(
(0): Sequential(
(0): Conv2d(99, 99, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
)
(1): Sequential(
(0): Conv2d(99, 99, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
)
(2): MergeLayer()
)
)
(11): Sequential(
(0): Conv2d(99, 3, kernel_size=(1, 1), stride=(1, 1))
)
)
), opt_func=functools.partial(<class ‘torch.optim.adam.Adam’>, betas=(0.9, 0.99)), loss_func=<function l1_loss at 0x131eb5730>, metrics=[], true_wd=True, bn_wd=True, wd=0.001, train_bn=True, path=PosixPath(’/Users/andresreibel/code/learn-code/gen_test/data’), model_dir=‘models’, callback_fns=[functools.partial(<class ‘fastai.basic_train.Recorder’>, add_time=True, silent=False), <class ‘fastai.callbacks.loss_metrics.LossMetrics’>], callbacks=[], layer_groups=[Sequential(
(0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(4): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(5): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(6): ReLU(inplace=True)
(7): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(8): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(9): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(10): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(11): ReLU(inplace=True)
(12): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(13): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(14): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(15): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(16): ReLU(inplace=True)
(17): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(18): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(19): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(20): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(21): ReLU(inplace=True)
(22): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(23): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(24): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
(25): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(26): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(27): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(28): ReLU(inplace=True)
(29): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(30): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(31): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(32): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(33): ReLU(inplace=True)
(34): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(35): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(36): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(37): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(38): ReLU(inplace=True)
(39): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(40): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
), Sequential(
(0): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
(6): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(7): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(8): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(9): ReLU(inplace=True)
(10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(11): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(13): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(14): ReLU(inplace=True)
(15): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(16): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(17): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(18): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(19): ReLU(inplace=True)
(20): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(21): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(22): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(23): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(24): ReLU(inplace=True)
(25): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(26): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(27): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(28): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(29): ReLU(inplace=True)
(30): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(31): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(32): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(33): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(34): ReLU(inplace=True)
(35): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(36): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(37): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(38): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(39): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(40): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(41): ReLU(inplace=True)
(42): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(43): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(44): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(45): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(46): ReLU(inplace=True)
(47): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(48): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
), Sequential(
(0): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(1): ReLU()
(2): Conv2d(512, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace=True)
(4): Conv2d(1024, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(5): ReLU(inplace=True)
(6): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1))
(7): PixelShuffle(upscale_factor=2)
(8): ReplicationPad2d((1, 0, 1, 0))
(9): AvgPool2d(kernel_size=2, stride=1, padding=0)
(10): ReLU(inplace=True)
(11): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(12): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU(inplace=True)
(14): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU(inplace=True)
(16): ReLU()
(17): Conv2d(512, 1024, kernel_size=(1, 1), stride=(1, 1))
(18): PixelShuffle(upscale_factor=2)
(19): ReplicationPad2d((1, 0, 1, 0))
(20): AvgPool2d(kernel_size=2, stride=1, padding=0)
(21): ReLU(inplace=True)
(22): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(23): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(24): ReLU(inplace=True)
(25): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(26): ReLU(inplace=True)
(27): ReLU()
(28): Conv2d(384, 768, kernel_size=(1, 1), stride=(1, 1))
(29): PixelShuffle(upscale_factor=2)
(30): ReplicationPad2d((1, 0, 1, 0))
(31): AvgPool2d(kernel_size=2, stride=1, padding=0)
(32): ReLU(inplace=True)
(33): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(34): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(35): ReLU(inplace=True)
(36): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(37): ReLU(inplace=True)
(38): ReLU()
(39): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1))
(40): PixelShuffle(upscale_factor=2)
(41): ReplicationPad2d((1, 0, 1, 0))
(42): AvgPool2d(kernel_size=2, stride=1, padding=0)
(43): ReLU(inplace=True)
(44): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(45): Conv2d(192, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(46): ReLU(inplace=True)
(47): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(48): ReLU(inplace=True)
(49): ReLU()
(50): Conv2d(96, 384, kernel_size=(1, 1), stride=(1, 1))
(51): PixelShuffle(upscale_factor=2)
(52): ReplicationPad2d((1, 0, 1, 0))
(53): AvgPool2d(kernel_size=2, stride=1, padding=0)
(54): ReLU(inplace=True)
(55): MergeLayer()
(56): Conv2d(99, 99, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(57): ReLU(inplace=True)
(58): Conv2d(99, 99, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(59): ReLU(inplace=True)
(60): MergeLayer()
(61): Conv2d(99, 3, kernel_size=(1, 1), stride=(1, 1))
)], add_time=True, silent=False)

This is the output of print(model) for model = nn.Sequenntial(body, head):

Sequential(
(0): Sequential(
(0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): ReLU(inplace=True)
(3): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(4): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(1): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(2): BasicBlock(
(conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(5): Sequential(
(0): BasicBlock(
(conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(2): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(3): BasicBlock(
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(6): Sequential(
(0): BasicBlock(
(conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(2): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(3): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(4): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(5): BasicBlock(
(conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(7): Sequential(
(0): BasicBlock(
(conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(downsample): Sequential(
(0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
(1): BasicBlock(
(conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(2): BasicBlock(
(conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
)
)
(1): Sequential(
(0): AdaptiveConcatPool2d(
(ap): AdaptiveAvgPool2d(output_size=1)
(mp): AdaptiveMaxPool2d(output_size=1)
)
(1): Flatten()
(2): BatchNorm1d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(3): Dropout(p=0.25, inplace=False)
(4): Linear(in_features=1024, out_features=512, bias=True)
(5): ReLU(inplace=True)
(6): BatchNorm1d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(7): Dropout(p=0.5, inplace=False)
(8): Linear(in_features=512, out_features=3, bias=True)
)
)

Andal · April 17, 2020, 8:41pm

Update: when I set model.load_state_dict(state, strict=False)

It solves the problem: but how can I be sure that I am now running the same model as I saved?