Comments (3)
Hello. Thanks for your interest in our work.
Based on our empirical findings we have also observed in our previous work 'QD-DETR' (CVPR23), we think that the gap exists depending on the machine you use and other dependencies including the cuda version.
Also, we observe that performance changes a bit after the code cleaning process (Even when we did not change any critical details that are used in training).
Although we are not quite sure about why such an issue happens, we expect the performance may decrease for some while it may increase for others.
Sorry for being not able to clearly solve the issue.
from cgdetr.
Thank you for your reply. May I ask what is the configuration of the machine used to obtain this experimental parameter? Such as GPU model, python version, torch version, etc
from cgdetr.
For that experiment, our versions are
GPU : NVIDIA TITAN RTX
CUDA Version : 11.4
Driver Version : 470.141.03
python 3.7.4
below are the dependencies when we check with "pip freeze"
absl-py==0.13.0
asn1crypto==1.2.0
av==8.0.3
backcall==0.1.0
beautifulsoup4==4.8.2
cachetools==4.2.2
certifi==2019.11.28
cffi==1.13.0
chardet==3.0.4
conda==4.8.1
conda-build==3.18.11
conda-package-handling==1.6.0
cryptography==2.8
cycler==0.10.0
dataclasses==0.6
decorator==4.4.1
docopt==0.6.2
ffmpeg==1.4
filelock==3.0.12
future==0.18.2
glob2==0.7
google-auth==1.34.0
google-auth-oauthlib==0.4.5
grpcio==1.39.0
idna==2.8
imageio==2.9.0
importlib-metadata==4.6.3
ipython==7.11.1
ipython-genutils==0.2.0
jedi==0.15.2
Jinja2==2.10.3
joblib==1.0.1
kiwisolver==1.3.1
libarchive-c==2.8
lief==0.9.0
Markdown==3.3.4
MarkupSafe==1.1.1
matplotlib==3.4.2
mkl-fft==1.0.15
mkl-random==1.1.0
mkl-service==2.3.0
numpy==1.17.4
nvidia-cublas-cu11==11.10.3.66
nvidia-cuda-nvrtc-cu11==11.7.99
nvidia-cuda-runtime-cu11==11.7.99
nvidia-cudnn-cu11==8.5.0.96
oauthlib==3.1.1
olefile==0.46
opencv-contrib-python==4.5.3.56
opencv-python==4.5.1.48
pandas==1.3.1
parso==0.5.2
pexpect==4.7.0
pickleshare==0.7.5
Pillow==7.0.0
pkginfo==1.5.0.1
prompt-toolkit==3.0.2
protobuf==3.15.6
psutil==5.6.7
ptyprocess==0.6.0
pyasn1==0.4.8
pyasn1-modules==0.2.8
pycosat==0.6.3
pycparser==2.19
Pygments==2.5.2
pyOpenSSL==19.0.0
pyparsing==2.4.7
PySocks==1.7.1
python-dateutil==2.8.2
pytz==2019.3
PyYAML==5.2
requests==2.22.0
requests-oauthlib==1.3.0
rsa==4.7.2
ruamel-yaml==0.15.46
scikit-learn==0.24.2
scikit-video==1.1.11
scipy==1.7.1
six==1.12.0
soupsieve==1.9.5
tensorboard==2.5.0
tensorboard-data-server==0.6.1
tensorboard-plugin-wit==1.8.0
tensorboardX==2.1
threadpoolctl==2.2.0
torch==1.13.1
torchtext==0.14.1
torchvision==0.10.0
tqdm==4.36.1
traitlets==4.3.3
typing-extensions==3.10.0.0
urllib3==1.24.2
wcwidth==0.1.7
Werkzeug==2.0.1
zipp==3.5.0
from cgdetr.
Related Issues (11)
- About the timing of releasing implementation codes HOT 2
- Customized dataset feature extraction in Charades-STA style HOT 6
- The result on moment retrieval datasets TACoS is from val datasets or test dataset? HOT 1
- About the paper HOT 4
- About Dummy Tokens. HOT 5
- Questions about some details? HOT 1
- Moment-adaptive Saliency Token Generator: Cross-Attention HOT 1
- Unable to reproduce the experimental results in your paper HOT 3
- Question about pre-training HOT 1
- Failed to find metrics for "QVHighlights only CLIP" model. 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 cgdetr.