Comments (3)
@devilztt
Hi, thanks for your attention.
GFLOPs doesn't correspond to the runtime because of different implementation.
In Pytorch implementation, the convolutional layers are executed in series, even though we connect the different branches in parallel. So, the speed of HRNets are actually slower than ResNets, which is similar to Group Convolution vs Standard Convolution.
Training and inference speed for our HRNet could be improved if Pytorch supports the parallel convolutions.
from hrnet-image-classification.
@sunke123
Thank you for your reply. I will close this issues.
from hrnet-image-classification.
Have you tried timing the forward pass by tracing the model with torchscript (jit) first ?
from hrnet-image-classification.
Related Issues (20)
- the loss become nan HOT 1
- Torch.jit.script not working with this model HOT 2
- Redistributing pre-trained model
- about self.class_weights
- guide to use pre-trained model HOT 1
- How to train on single GPU HOT 3
- It doesn't work HOT 3
- A solution: HRNet Backbone Adopt_different_blocks_bug(BASIC//BOTTLENECK) HOT 2
- How to convert the pretrained cls model to the required model for pose estimation
- Could someone help to put the pretrained models in google drive? HOT 1
- new pretrained model "HRNet-W48-C (w/ CosineLR + CutMix + 300epochs)" HOT 6
- which scrips use to caculate the GFLOPs?
- BRANCHES instead of RANCHES
- how to train my own dataset with different categories?
- about--- HRNet-W48-C-ssld (converted from PaddlePaddle) HOT 1
- No module named 'utils.modelsummary'
- How To Perform Inference
- The differences between HRNet-W18-C-Small-v1 and HRNet-W18-C-Small-v2
- How to train with CPU only HOT 1
- How to add tensorboard or using wandb to visual trainning process
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 hrnet-image-classification.