caoql98 / sdm Goto Github PK
View Code? Open in Web Editor NEWCodes and dataset (iSAID-5i) for Scale-aware Detailed Matching for Few-Shot Aerial Image Semantic Segmentation
Codes and dataset (iSAID-5i) for Scale-aware Detailed Matching for Few-Shot Aerial Image Semantic Segmentation
Hello, thank for sharing your great work.
I wanna know when training the network, are the backbone parameters frozen?
It seems the parameters of the backbone will be updated.
Look forward to your reply!
Thanks for your great work! I am wondering how many episodes are sampled during meta-testing. Also, are the results presented the average of N independent runs? If so, what is the exact number of N? I would appreciate your help sincerely!
Thank you for your good work.
Now, I have not baidu cloud account, so I cannot download the data.
Therefore, could you give me another download link?
Thanks for your brilliant work. I run the FPMMs successfully following default settings. But I failed to run FPMMs_vgg.
Traceback (most recent call last):
File "train.py", line 135, in
train(args)
File "train.py", line 106, in train
logits = model.forward_5shot(query_img, support_img, support_mask,query_mask)
File "/home/linhan/projects/SDM/networks/FPMMs_vgg.py", line 127, in forward_5shot
exit_feat_in_ = self.f_v_concate(query_feature, vec, feature_size)
File "/home/linhan/projects/SDM/networks/FPMMs_vgg.py", line 146, in f_v_concate
fea_pos = vec_pos.expand(-1, -1, feature_size[0], feature_size[1]) # tile for cat
RuntimeError: The expanded size of the tensor (41) must match the existing size (256) at non-singleton dimension 3. Target sizes: [-1, -1, 41, 41]. Tensor sizes: [3, 256]
Could you please give me some hints?
It is notable that the PMMs in the experimental results denotes the FRPMMs network.
If I want to run my dataset, there are only 4 categories, how do I get data_list and what parts do I need to pay attention to changing? Looking forward to your reply, thank you
Thanks for your work! But it has no NetworkInNetwork.py
File "D:/SDM/train.py", line 17, in
from networks import *
File "D:\SDM\networks\resnet50_34.py", line 7, in
from models.backbone import NetworkInNetwork as modeln
ImportError: cannot import name 'NetworkInNetwork' from 'models.backbone' (unknown location)
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.