Comments (2)
jfzhang95
commented on June 14, 2024
Previous code has a problem: the output_stride is 32, but the official code's output_sride is 16.
Now I implement a new separable convolution to solve this problem.
Besides, I think tr.RandomResizedCrop method is not suitable for this task. I cannot
even overfit one image if I train the code with this transformation. Therefore, I change
tr.RandomResizedCrop to tr.FixedResize(512) and change learning rate to 5e-7, then the loss
can decrease normally.
from pytorch-deeplab-xception.
FJR-Nancy
commented on June 14, 2024
@MenSanYan I think the loss value is high because the "size_average" is set to False while computing the loss. You can set it to True or just remove it -- which will use “elementwise_mean” by default in PyTorch. Besides, if you use “elementwise_mean” in loss, you need to increase the initial learning rate accordingly, maybe 0.007, which is the same as the paper.
from pytorch-deeplab-xception.
Related Issues (20)
- TypeError: cannot pickle 'module' object HOT 1
- using drn-105: Missing key(s) in state_dict
- my data are images and its 0,255 masks,,the masks are 0 255 images, it is voc format? HOT 1
- how to chnage the input h w of image?
- @stonessss yes, i write test code. HOT 1
- run inference.py success HOT 2
- self.last_conv() input_channels in file decoder.py HOT 1
- self = reduction.pickle.load(from_parent) error Ran out of input HOT 1
- The training time is so long？
- RuntimeError: CUDA error: device-side assert triggered HOT 4
- validation loss always lower than train loss
- Target 10 out of bounds while training on complete dataset HOT 1
- Could you give us some training details about your Pretrained Model
- Xception Backbone problem HOT 1
- data augmentation on the paper
- xception backbone url doesn't exist HOT 1
- Params And FLOPs HOT 1
- Why do I keep the imou and other parameter values obtained from each epoch unchanged during the training process
- Why force to set the output stride for DRN to 8?
- where's the inference.py file?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pytorch-deeplab-xception.