kylin9511 / acrnet Goto Github PK
View Code? Open in Web Editor NEWThis is an implementation of ACRNet for results reproduction on COST2100
License: MIT License
This is an implementation of ACRNet for results reproduction on COST2100
License: MIT License
I was working on the algorithm, running all the parameters as required. This is the output shown. Can you please help with it?
C:\Users\User\Desktop\Home>python C:\Users\User\Desktop\Home>python C:\Users\User\Desktop\Home\ACRNet\main.py --data-dir C:\Users\User\Desktop\Home\COST2100 --reduction 4 --expansion 1 --batch-size 200 --scenario in --workers 0
I 09.13/12:19 C:\Users\User\Desktop\Home\ACRNet\main.py:35 ] => PyTorch Version: 1.9.0+cpu
I 09.13/12:19 C:\Users\User\Desktop\Home\ACRNet\main.py:14 ] Running on CPU
I 09.13/12:20 C:\Users\User\Desktop\Home\ACRNet\model\acrnet.py:117 ] => Model ACRNet with reduction=4, expansion=1
I 09.13/12:20 C:\Users\User\Desktop\Home\ACRNet\main.py:24 ] => Model Name: ACRNet
I 09.13/12:20 C:\Users\User\Desktop\Home\ACRNet\main.py:24 ] => Model Config: compression ratio=1/4; expansion=1
I 09.13/12:20 C:\Users\User\Desktop\Home\ACRNet\main.py:24 ]
ACRNet(
(encoder_feature): Sequential(
(conv5x5_bn): ConvBN(
(conv): Conv2d(2, 2, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)
(bn): BatchNorm2d(2, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(prelu): PReLU(num_parameters=2)
(ACREncoderBlock1): ACREncoderBlock(
(conv_bn1): ConvBN(
(conv): Conv2d(2, 2, kernel_size=(1, 9), stride=(1, 1), padding=(0, 4), bias=False)
(bn): BatchNorm2d(2, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(prelu1): PReLU(num_parameters=2)
(conv_bn2): ConvBN(
(conv): Conv2d(2, 2, kernel_size=(9, 1), stride=(1, 1), padding=(4, 0), bias=False)
(bn): BatchNorm2d(2, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(prelu2): PReLU(num_parameters=2)
(identity): Identity()
)
(ACREncoderBlock2): ACREncoderBlock(
(conv_bn1): ConvBN(
(conv): Conv2d(2, 2, kernel_size=(1, 9), stride=(1, 1), padding=(0, 4), bias=False)
(bn): BatchNorm2d(2, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(prelu1): PReLU(num_parameters=2)
(conv_bn2): ConvBN(
(conv): Conv2d(2, 2, kernel_size=(9, 1), stride=(1, 1), padding=(4, 0), bias=False)
(bn): BatchNorm2d(2, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(prelu2): PReLU(num_parameters=2)
(identity): Identity()
)
)
(encoder_fc): Linear(in_features=2048, out_features=512, bias=True)
(decoder_fc): Linear(in_features=512, out_features=2048, bias=True)
(decoder_feature): Sequential(
(conv5x5_bn): ConvBN(
(conv): Conv2d(2, 2, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), bias=False)
(bn): BatchNorm2d(2, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(prelu): PReLU(num_parameters=2)
(ACRDecoderBlock1): ACRDecoderBlock(
(conv1_bn): ConvBN(
(conv): Conv2d(2, 8, kernel_size=(1, 9), stride=(1, 1), padding=(0, 4), bias=False)
(bn): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(prelu1): PReLU(num_parameters=8)
(conv2_bn): ConvBN(
(conv): Conv2d(8, 8, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=4, bias=False)
(bn): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(prelu2): PReLU(num_parameters=8)
(conv3_bn): ConvBN(
(conv): Conv2d(8, 2, kernel_size=(9, 1), stride=(1, 1), padding=(4, 0), bias=False)
(bn): BatchNorm2d(2, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(prelu3): PReLU(num_parameters=2)
(identity): Identity()
)
(ACRDecoderBlock2): ACRDecoderBlock(
(conv1_bn): ConvBN(
(conv): Conv2d(2, 8, kernel_size=(1, 9), stride=(1, 1), padding=(0, 4), bias=False)
(bn): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(prelu1): PReLU(num_parameters=8)
(conv2_bn): ConvBN(
(conv): Conv2d(8, 8, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=4, bias=False)
(bn): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(prelu2): PReLU(num_parameters=8)
(conv3_bn): ConvBN(
(conv): Conv2d(8, 2, kernel_size=(9, 1), stride=(1, 1), padding=(4, 0), bias=False)
(bn): BatchNorm2d(2, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)
(prelu3): PReLU(num_parameters=2)
(identity): Identity()
)
(sigmoid): Sigmoid()
)
)
Traceback (most recent call last):
File "C:\Users\User\Desktop\Home\ACRNet\main.py", line 35, in
main()
File "C:\Users\User\Desktop\Home\ACRNet\main.py", line 31, in main
Tester(model, device, criterion, print_freq=20)(test_loader)
File "C:\Users\User\Desktop\Home\ACRNet\utils\solver.py", line 35, in call
loss, rho, nmse = self._iteration(test_data)
File "C:\Users\User\Desktop\Home\ACRNet\utils\solver.py", line 56, in _iteration
rho, nmse = evaluator(sparse_pred, sparse_gt, raw_gt)
File "C:\Users\User\Desktop\Home\ACRNet\utils\statics.py", line 60, in evaluator
raw_pred = torch.fft(sparse_pred, signal_ndim=1)[:, :, :125, :]
TypeError: 'module' object is not callable
Does this set of code not include the code of quantization part and the code of full connection layer binarization?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.