ducminhkhoi / feature-weighting-and-boosting Goto Github PK
View Code? Open in Web Editor NEWThis is the unofficially official implementation of the paper "Feature Weighting and Boosting for Few-Shot Segmentation"
License: Other
This is the unofficially official implementation of the paper "Feature Weighting and Boosting for Few-Shot Segmentation"
License: Other
Hello, when I use your repo with this command to train the model,
CUDA_VISIBLE_DEVICES=0 python main_official.py --train --exp few_shot_official_sub --dataset pascal --backbone vgg16 --model 5 --group 1 --iteration 10000 --base_lr 0.007 --num_folds 4 --crop_size 512 --batch_size 4 --val_interval 100
the training stops when the validation happens, and throws
Traceback (most recent call last):
File "/home/alisachen/文件/Programs/Feature-Weighting-and-Boosting/main_official.py", line 468, in
main()
File "/home/alisachen/文件/Programs/Feature-Weighting-and-Boosting/main_official.py", line 324, in main
loss = criterion(output, query_label)
File "/home/alisachen/miniconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/alisachen/miniconda3/lib/python3.9/site-packages/torch/nn/modules/loss.py", line 1120, in forward
return F.cross_entropy(input, target, weight=self.weight,
File "/home/alisachen/miniconda3/lib/python3.9/site-packages/torch/nn/functional.py", line 2824, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
RuntimeError: Expected target size [1, 500], got [1, 375, 500]
Please help me to solve this problem.
Has anyone encountered a similar situation?
pascal_test
Total of 365 db items loaded!
Total of 5 classes!
Traceback (most recent call last):
File "E:\code\github\Feature-Weighting-and-Boosting-main\main_official.py", line 445, in
main()
File "E:\code\github\Feature-Weighting-and-Boosting-main\main_official.py", line 155, in main
datalayer = SSDatalayer(args.group, args.num_shots)
File "E:\code\github\Feature-Weighting-and-Boosting-main\ss_datalayer.py", line 348, in init
self.setup()
File "E:\code\github\Feature-Weighting-and-Boosting-main\ss_datalayer.py", line 389, in setup
process.start()
File "E:\anaconda\envs\point\lib\multiprocessing\process.py", line 112, in start
self._popen = self._Popen(self)
File "E:\anaconda\envs\point\lib\multiprocessing\context.py", line 223, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "E:\anaconda\envs\point\lib\multiprocessing\context.py", line 322, in _Popen
return Popen(process_obj)
File "E:\anaconda\envs\point\lib\multiprocessing\popen_spawn_win32.py", line 89, in init
reduction.dump(process_obj, to_child)
File "E:\anaconda\envs\point\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
TypeError: 'NoneType' object is not callable
Hello, when I run the "main_official.py" file, I got this result:
data/val_pascal_0_4_new.pkl
Traceback (most recent call last):
File "", line 1, in
File "D:\Anaconda\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "D:\Anaconda\lib\multiprocessing\spawn.py", line 124, in _main
preparation_data = reduction.pickle.load(from_parent)
EOFError: Ran out of input
Maybe there should be a file named "data/val_pascal_0_4_new.pkl" in the "Feature-Weighting-and-Boosting-main\data" folder, but I didn't find this or some other file named like "data/val_{}{}{}_new.pkl" (at line146 in main_official.py). So if it's convenient for you, could you upload the file or just tell me what should be involved in that file, so that I can use my own dataset to create that ".pkl" file.
On the main folder command:
'tensorboad' --logdir=logs/[logging_folder]
should be :
"tensorboard" --logdir=logs/[logging_folder]
Could you please commit the complete implementation?
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.