Comments (5)
It seems that your reproduction results are lower than ours for K7 RGB
. I guess the FLOW results may have the same problem.
Our experimental settings are Python 3.5.2, PyTorch 0.4.1 with cuda9.0
for K7 RGB+FLOW
. For pytorch1.6 we only tested the inference results without reproducing it.
Would you mind using pytorch0.4.1 to reproduce it again?
BTW, the performance gap is about 0.5-2.0 for N10 w/o flip for our released model (depends on the evaluation metric).
from moc-detector.
Thanks for fast response. Ok, I'll try with PyTorch 0.4.1
from moc-detector.
Hi!
I've tried with recommended parameters to train rgb model. Results are the same:
(scores are located as follows: [email protected] | [email protected] | @0.5 | @0.75 | 0.5:0.95):
(paper) ucf_dla34_K7_rgb_coco.pth: 73.14 | 78.81 | 51.02 | 27.05 | 26.51
ucf_dla34_K7_rgb_coco_N100_flip 71.56 | 78.40 | 50.24 | 26.18 | 26.16
ucf_dla34_K7_rgb_coco_N10 70.24 | 77.78 | 47.64 | 25.22 | 24.61
Again, I'm more curious about why inference with N100 + flip significantly better than N10 w/o flip which is opposite to your results. And variance of scores is also a bit high. I checked this on different machines. So I don't know where to look.
Hope you give me some advice.
Thank you again
from moc-detector.
For our RGB model, the experimental results are:
ucf_dla34_K7_rgb_coco_N100_flip: 73.14 | 78.81 | 51.02 | 27.05 | 26.51
ucf_dla34_K7_rgb_coco_N10: 72.05 | 78.23 | 50.77 | 26.10 | 26.16
(The performance gap is 0.5-1.1)
It seems that your reproduction results are a little lower than ours.(For example, the [email protected] for RGB K=7 should be at least 72.xx. And I got the similar results on my machine.)
As for N10 w/o flip
, I wonder this may be just a coincidence for my own model.
I have not mentioned it in our paper because it was just an accidental discovery when I organized the code after the paper is accepted.
Here I give you more experimental results:
K=5 RGB
ucf_dla34_K5_rgb_coco_N100_flip: 71.63 | 77.74 | 49.55 | 27.04 | 26.09
ucf_dla34_K5_rgb_coco_N10: 70.10 | 76.08 | 49.14 | 26.28 | 25.70
ImageNet pretrain
ucf_dla34_K7_rgb_flow_ImageNet_N100_flip: 76.92 | 81.26 | 54.43 | 29.49 | 28.42
ucf_dla34_K7_rgb_flow_ImageNet_N10: 76.03 | 80.75 | 53.47 | 27.16 | 27.52
I this this performance gap is acceptable because it significantly boosts the inference speed.
Thanks for your correction and I will revise it.
from moc-detector.
Thank you so much. It helps me.
from moc-detector.
Related Issues (20)
- the standard of pkl HOT 4
- FLOPs analysis HOT 3
- Confused about the `sample_cuboids` constraints HOT 2
- Question about `down_ratio` HOT 4
- model for K7 RGB + FLOW COCO on UCF101-24
- How to pretrain an optical flow model on COCO? HOT 7
- train on the one gpu error HOT 9
- Import Error HOT 13
- Reproduction of paper results HOT 1
- how to infer with only rgb model? HOT 1
- training problem HOT 4
- about branch construction HOT 2
- Some questions about spatial-temporal action detection HOT 1
- more details about 3D CNN
- Inference with flow model HOT 2
- DCNv2 HOT 5
- Disable cudnn batch normalization HOT 1
- Why ninput = 5 when input modality is flow? HOT 1
- How to interpret the 3-channel in jpg image of optical flow?
- undefined symbol: __cudaRegisterFatBinaryEnd. HOT 4
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 moc-detector.