Comments (5)
The training is happening, the output is printed every 50 steps, so it might take some time until you see the next step, you can modify the train function to remove this 50 step output condition as needed.
from fc-densenet-tensorflow.
yes,you are right!,but i think it is so slow for me ,It takes about 20 seconds to process a picture,I wonder if it is normal?I have used GPU
from fc-densenet-tensorflow.
The tiramisu is a deep network, and it's memory consumption is quadratic because of how tensorflow computes gradients. Also, your images are high resolution. Combined all these facts, it will be slow. You can either try reducing the dense blocks, number of layers or your image size to make it faster.
If you have access to a better GPU (V100s), that should also help, but I realize not everyone does.
from fc-densenet-tensorflow.
OK,thank you very much ,but I wonder Why does the loss not converge? I am doing multi-class segmentation.
from fc-densenet-tensorflow.
60 iterations is too low, the Tiramisu is known to be difficult to optimize, see, try training it longer.
from fc-densenet-tensorflow.
Related Issues (20)
- about the upsampling HOT 3
- two bugs? HOT 2
- Could not create cudnn handle: CUDNN_STATUS_NOT_INITIALIZED and Possibly insufficient driver version: 384.81.0 Segmentation fault (core dumped) HOT 1
- Some minor bugs. HOT 2
- Infer fail due to model shape not match HOT 3
- out of memory HOT 1
- How to set the dataset? HOT 1
- the iou always equals to 0.5 when I use my dataset to train the model HOT 6
- normalize_data problem why image/255 and mask/255 when training HOT 1
- the outputs are a vertical line HOT 1
- Cant read Inputfiles HOT 4
- seems error of logits reshape when num_classes != 2
- Why set 'training' True in phase of infer HOT 1
- HI~Can i ask about this error? HOT 1
- How to load the pretrained model? HOT 4
- how to solve this error HOT 1
- Pictures in output are all black HOT 1
- about testing HOT 1
- Why not change the training mode to 'False' in the line # 339? HOT 1
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 fc-densenet-tensorflow.