Comments (3)
Another question. Your tiny flownet is also trained. Why not use pretrained model? I mean first training a tiny flownet, and then fixing it when train RMNet.
from rmnet.
Third question. In your code, you still use global-to-global memory matching. It is strange.
from rmnet.
Thanks for your interest in our work.
- At first, we use 4 1080Ti GPUs. As the memory usage increases (because our method becomes more complex), we use 2 V100 (32GB) GPUs.
- Actually, the weights of TinyFlowNet are partially borrowed from FlowNet-S and fine-tuned on the precomputed optical flow (See also #3).
- The matrix multiplication is highly optimized in PyTorch. We implement an extension for local-to-local matching with PyTorch API and CUBLAS, but the speed is lower than the one in PyTorch. Moreover, we find that PyTorch is optimized for our situation where there are lots of zeros in matrices.
from rmnet.
Related Issues (20)
- About training schedule HOT 6
- Training protocols for youtube finetuning HOT 1
- 光流 .flo 文件 HOT 1
- Could you release your pre-computed results? HOT 1
- About batchsize HOT 1
- Pretrained models for YouTube-VOS dataset HOT 1
- Hyperparameters for static image pretraining HOT 1
- How can I use .flo file instead of tflownet?! HOT 2
- Caught TypeError in DataLoader worker process 0 in DataLoader HOT 3
- "RuntimeError: Error compiling objects for extension" when compiling reg_att_map_generator HOT 3
- About RegionalAttentionMapGenerator() HOT 1
- RMNet26? HOT 1
- Does Table 5 consider the computing time of optical flow? HOT 1
- About training process HOT 1
- Why does the runner.py of RMNet do not train TinyFlowNet? HOT 1
- About network training HOT 1
- reg_att_map_generator.cu(114): error: type name is not allowed HOT 4
- A typo in README.md HOT 1
- Problem with building "reg_att_map_generator" extension HOT 1
- have you implemented KMN? 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 rmnet.