scouly / muscle Goto Github PK
View Code? Open in Web Editor NEWthe implementation of: A Multi-Strategy Contrastive Learning Framework for Weakly Supervised Semantic Segmentation (MuSCLe)
the implementation of: A Multi-Strategy Contrastive Learning Framework for Weakly Supervised Semantic Segmentation (MuSCLe)
hi,
打扰您了,我想知道这三个权重之间的区别:MuSCL-b7_63.35_66.6.pth,MCL_55.35_58.5.pth,IRN_pretrained.pth之间的区别。
同时我想知道在运行python infer_mcl.py 之后生成的cam是npy的格式,要如何进行可视化呢。
谢谢!
在运行infer_seg.py文件时,发生错误:RuntimeError: unexpected EOF, expected 4643038 more bytes. The file might be corrupted.
显示权重文件好像损坏了,是我这边下载的有问题吗
File "/home/lcl/ToCo-main/MuSCLe-main/train_mcl.py", line 17, in
from src.loss_multilabel import *
File "/home/lcl/ToCo-main/MuSCLe-main/src/loss_multilabel.py", line 6, in
from qpth.qp import QPFunction
ModuleNotFoundError: No module named 'qpth'
Traceback (most recent call last):
File "/home/lcl/MuSCLe-main/train_mcl.py", line 18, in
from src.MuSCLe import *
File "/home/lcl/MuSCLe-main/src/MuSCLe.py", line 6, in
from src.edge import *
File "/home/lcl/MuSCLe-main/src/edge.py", line 10, in
from EffSeg import *
ModuleNotFoundError: No module named 'EffSeg'
--infer_list PATH_TO_INFER_LIST
中PATH_TO_INFER_LIST应该是什么呀
Using MCL_55.15_58.5.pth as the weight, run the max miou:42.71176333180985 obtained by train_mcl.py?
The max miou in the paper is 58.4?
Traceback (most recent call last):
File "/home/lcl/MuSCLe-main/train_mcl.py", line 155, in
for iter, pack in enumerate(train_data_loader):
File "/home/lcl/anaconda3/envs/muscle1/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 633, in next
data = self._next_data()
File "/home/lcl/anaconda3/envs/muscle1/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1345, in _next_data
return self._process_data(data)
File "/home/lcl/anaconda3/envs/muscle1/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1371, in _process_data
data.reraise()
File "/home/lcl/anaconda3/envs/muscle1/lib/python3.8/site-packages/torch/_utils.py", line 644, in reraise
raise exception
FileNotFoundError: Caught FileNotFoundError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/lcl/anaconda3/envs/muscle1/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "/home/lcl/anaconda3/envs/muscle1/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/lcl/anaconda3/envs/muscle1/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 51, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/lcl/MuSCLe-main/src/data.py", line 327, in getitem
name, img, view1, view2, coord1, coord2, ori_coord = super().getitem(idx)
File "/home/lcl/MuSCLe-main/src/data.py", line 310, in getitem
img = PIL.Image.open(get_img_path(name, self.voc12_root)).convert("RGB")
File "/home/lcl/anaconda3/envs/muscle1/lib/python3.8/site-packages/PIL/Image.py", line 2975, in open
fp = builtins.open(filename, "rb")
FileNotFoundError: [Errno 2] No such file or directory: 'data/JPEGImages/2008_008212.jpg'
论文中公式2和代码是不是不太一样
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.