fupiao1998 / transformersod Goto Github PK
View Code? Open in Web Editor NEWA unified framework for Transformer supervised/weakly supervised SOD, RGBD SOD, COD
A unified framework for Transformer supervised/weakly supervised SOD, RGBD SOD, COD
Hello, thank you for sharing your excellent work.
I am facing this error when running your code in a custom dataset. This error occur specifically when using --backbone dpt
. When using --backbone R50
works properly.
Could you please help me?
$ python train.py --task lesions --uncer_method basic --backbone dpt --use_22k
[INFO] Experiments saved in: lesions_2.5e-05_dpt_basic_cat_basic_REMOVE
[INFO]: Model based on [dpt_basic_cat_basic] have 108.2544Mb paramerters in total
dataset_size 27508
Learning Rate: 2.50e-05
Epoch[001/050]: 0%| | 0/2299 [00:00<?, ?it/s]/home/viplabgpu/anaconda3/envs/gpu/lib/python3.9/site-packages/torch/nn/functional.py:3609: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
warnings.warn(
Epoch[001/050]: 0%| | 0/2299 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/home/TrasformerSOD/train.py", line 43, in <module>
model_dict, loss_record = train_one_epoch(epoch, model_list, optimizer_list, train_loader, dataset_size, loss_fun)
File "/home/TrasformerSOD/trainer/trainer_basic.py", line 43, in train_one_epoch
pred = generator(img=images, depth=depth)
File "/home/viplabgpu/anaconda3/envs/gpu/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/TrasformerSOD/model/saliency_detector.py", line 34, in forward
backbone_features = self.backbone(img)
File "/home/viplabgpu/anaconda3/envs/gpu/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/TrasformerSOD/model/backbone/DPT.py", line 83, in forward
layer_1, layer_2, layer_3, layer_4 = forward_vit(self.pretrained, x)
File "/home/TrasformerSOD/model/backbone/DPT_blocks/vit.py", line 107, in forward_vit
glob = pretrained.model.forward_flex(x)
File "/home/TrasformerSOD/model/backbone/DPT_blocks/vit.py", line 185, in forward_flex
dist_token = self.dist_token.expand(B, -1, -1)
AttributeError: 'NoneType' object has no attribute 'expand'
Should i assign "iters" variable in test.py=10 ?. like 10 times sample form h? or h on test phase via Gauss distribution, therefore iters=1?
the link there is not a valid clickable link to access your predicted saliency map.
please release the map for comparison.
thanks
如题,感谢
hello, thanks for your great work.
Would you mind providing your saliency map and your pre-trained model of your code?
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.