Comments (11)
The performance may vary depending on the environment, seed, and others.
I recommend using the pre-trained model for precise reproduction.
Thanks!
from wtal-uncertainty-modeling.
The performance may vary depending on the environment, seed, and others.
I recommend using the pre-trained model for precise reproduction.
Thanks!
Thank for your reply.I used the pre-trained model that you have updated to test,but the result is :
Step: 0
Test_acc: 0.8905
average_mAP: 0.4038
[email protected]: 0.6551
[email protected]: 0.5836
[email protected]: 0.5052
[email protected]: 0.4158
[email protected]: 0.3245
[email protected]: 0.2266
[email protected]: 0.1161
The result is worse than your paper.I think the envirment is not detemined with the test result.And the enviroment that I test your pre-trained model is in Google Colab.Is the pre-trained model you offerd newest?
from wtal-uncertainty-modeling.
The environment, in fact, affects the performance.
For instance, some numpy functions behave differently according to the numpy version.
Please ensure that your environment is identical to the requirements.
For the model file, I updated it last day.
from wtal-uncertainty-modeling.
The environment, in fact, affects the performance.
For instance, some numpy functions behave differently according to the numpy version.
Please ensure that your environment is identical to the requirements.
For the model file, I updated it last day.
Thank you for your quick reply.I will make the environment same to your requirements and test the model again.
from wtal-uncertainty-modeling.
The environment, in fact, affects the performance.
For instance, some numpy functions behave differently according to the numpy version.
Please ensure that your environment is identical to the requirements.
For the model file, I updated it last day.
Hello.
Thank you for your reply. I make the environment match your requirements,but I still can't reproduce the result .And the rsult is still as before:
Step: 0
Test_acc: 0.8905
average_mAP: 0.4038
[email protected]: 0.6551
[email protected]: 0.5836
[email protected]: 0.5052
[email protected]: 0.4158
[email protected]: 0.3245
[email protected]: 0.2266
[email protected]: 0.1161
And my environment is:
Name Version Build Channel | | | | |
_libgcc_mutex 0.1 main | | | | |
absl-py 0.11.0 pypi_0 pypi | | | | |
astor 0.8.1 pypi_0 pypi | | | | |
ca-certificates 2020.12.8 h06a4308_0 | | | | |
cached-property 1.5.2 pypi_0 pypi | | | | |
certifi 2020.12.5 py36h06a4308_0 | | | | |
docopt 0.6.2 pypi_0 pypi | | | | |
future 0.18.2 pypi_0 pypi | | | | |
gast 0.2.2 pypi_0 pypi | | | | |
google-pasta 0.2.0 pypi_0 pypi | | | | |
grpcio 1.34.0 pypi_0 pypi | | | | |
h5py 3.1.0 pypi_0 pypi | | | | |
importlib-metadata 3.3.0 pypi_0 pypi | | | | |
joblib 0.13.0 pypi_0 pypi | | | | |
keras-applications 1.0.8 pypi_0 pypi | | | | |
keras-preprocessing 1.1.2 pypi_0 pypi | | | | |
ld_impl_linux-64 2.33.1 h53a641e_7 | | | | |
libedit 3.1.20191231 h14c3975_1 | | | | |
libffi 3.3 he6710b0_2 | | | | |
libgcc-ng 9.1.0 hdf63c60_0 | | | | |
libstdcxx-ng 9.1.0 hdf63c60_0 | | | | |
markdown 3.3.3 pypi_0 pypi | | | | |
ncurses 6.2 he6710b0_1 | | | | |
numpy 1.19.0 pypi_0 pypi | | | | |
openssl 1.1.1i h27cfd23_0 | | | | |
opt-einsum 3.3.0 pypi_0 pypi | | | | |
pandas 0.23.4 pypi_0 pypi | | | | |
pillow 8.0.1 pypi_0 pypi | | | | |
pip 20.3.3 py36h06a4308_0 | | | | |
pqi 2.0.6 pypi_0 pypi | | | | |
protobuf 3.14.0 pypi_0 pypi | | | | |
python 3.6.12 hcff3b4d_2 | | | | |
python-dateutil 2.8.1 pypi_0 pypi | | | | |
pytz 2020.4 pypi_0 pypi | | | | |
readline 8.0 h7b6447c_0 | | | | |
scikit-learn 0.20.0 pypi_0 pypi | | | | |
scipy 1.1.0 pypi_0 pypi | | | | |
setuptools 51.0.0 py36h06a4308_2 | | | | |
six 1.15.0 pypi_0 pypi | | | | |
sqlite 3.33.0 h62c20be_0 | | | | |
tensorboard 1.15.0 pypi_0 pypi | | | | |
tensorboard-logger 0.1.0 pypi_0 pypi | | | | |
tensorflow 1.15.2 pypi_0 pypi | | | | |
tensorflow-estimator 1.15.1 pypi_0 pypi | | | | |
termcolor 1.1.0 pypi_0 pypi | | | | |
tk 8.6.10 hbc83047_0 | | | | |
torch 1.6.0 pypi_0 pypi | | | | |
torchvision 0.7.0 pypi_0 pypi | | | | |
tqdm 4.31.1 pypi_0 pypi | | | | |
typing-extensions 3.7.4.3 pypi_0 pypi | | | | |
werkzeug 1.0.1 pypi_0 pypi | | | | |
wheel 0.36.2 pyhd3eb1b0_0 | | | | |
wrapt 1.12.1 pypi_0 pypi | | | | |
xz 5.2.5 h7b6447c_0 | | | | |
And my cuda versionis 10.2:
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2019 NVIDIA Corporation
Built on Wed_Oct_23_19:24:38_PDT_2019
Cuda compilation tools, release 10.2, V10.2.89
I don't know the reason that casue the problem.Maybe you change something that you ignored,but you forgot. I hope you can help me solve this problem.Because it' s very important for me.I'm waiting for your reply.
Thank you.
from wtal-uncertainty-modeling.
The environment, in fact, affects the performance.
For instance, some numpy functions behave differently according to the numpy version.
Please ensure that your environment is identical to the requirements.
For the model file, I updated it last day.
Hello.Can you tell me why the average result is 1.5 lower than your paper?Because it's very important for me.
from wtal-uncertainty-modeling.
Sorry, but I have no idea about what causes the performance difference, as I cannot look into the exact status of your environment.
I tried reproducing this repo on another environment and got the same result as mine.
A possible source is that you may be using the old code.
Make sure to use the latest code as well as the model file.
from wtal-uncertainty-modeling.
Sorry, but I have no idea about what causes the performance difference, as I cannot look into the exact status of your environment.
I tried reproducing this repo on another environment and got the same result as mine.
A possible source is that you may be using the old code.
Make sure to use the latest code as well as the model file.
Thank you for your reply.I have updated the newest code and the newest model.But the results don't change.Maybe you use some tricks that you ignored。
from wtal-uncertainty-modeling.
I'm sorry.
I found that the link to the pre-trained model was wrong, which is corrected now.
Please update the model file and re-evaluate the model.
Thanks!
from wtal-uncertainty-modeling.
I'm sorry.
I found that the link to the pre-trained model was wrong, which is corrected now.
Please update the model file and re-evaluate the model.
Thanks!
Thank you for your reply.
I can reproduce the result that used the newest pre-trained model now.Could you please update the code again? Maybe you forgot some details.
How long can you get the best model?
from wtal-uncertainty-modeling.
I'm sorry.
I found that the link to the pre-trained model was wrong, which is corrected now.
Please update the model file and re-evaluate the model.
Thanks!Thank you for your reply.
I can reproduce the result that used the newest pre-trained model now.Could you please update the code again? Maybe you forgot some details.
How long can you get the best model?
Hi @xumh-9 , have you reproduced the result in paper? I tried many times, but I cannot get the result as good as pretrained model, even tried different random seeds.
from wtal-uncertainty-modeling.
Related Issues (20)
- Results of your provided pre-trained model HOT 2
- Cannot get provided feature. HOT 1
- Some questions in your paper HOT 6
- questions about thumos feature HOT 1
- Why there is a dropout when generate pseudo action features? HOT 1
- Act1.2 and act1.3 feature? HOT 1
- Can anyone reproduce the results in the paper?
- hi, about test code -upsample and down HOT 1
- GPU utilization is low HOT 1
- How long is the training time HOT 2
- How to get WUM_result_numpy
- Why choose softmax as the activation function instead of sigmoid? HOT 2
- Dataloader of ActivityNet 1.3
- An Error implement about `nms` HOT 3
- Confusion of proposal HOT 2
- question about feat_magnitudes
- Question about Figure 2 in paper. HOT 2
- ActivityNet 1.3 Features and model HOT 1
- the newest result 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 wtal-uncertainty-modeling.