zehuichen123 / ddod Goto Github PK
View Code? Open in Web Editor NEW[ACM MM 2021, TMM 2023] Disentangle your Dense Object Detector
License: Apache License 2.0
[ACM MM 2021, TMM 2023] Disentangle your Dense Object Detector
License: Apache License 2.0
大佬你好,想请教一下,论文中的table 5里面的reg和cls的alph,与成本矩阵中的alph是什么关系?不是alph与1-alph的关系吗。感谢
For WIDER FACE, the paper describes the batch size.
"The model is trained with a batch size of 24 on 6 Titan V100s."
For COCO, is the total batch size 32?
tools/dist_train.sh coco_cfg/ddod_r50_1x.py 8
samples_per_gpu=4,
Can we achieve similar AP with a total batch size of 16 and lr=0.01
?
柠檬,DDDD
如题
How is anchor set when ddod is applied to widerface?(including base_sizes, ratios, scales_per_octave, octave_base_scale)
The heatmap in fig.2. is so cool!
How to implement GradCAM in your detector?
Environment info:
sys.platform: linux
Python: 3.7.13 (default, Oct 18 2022, 18:57:03) [GCC 11.2.0]
CUDA available: True
GPU 0,1: NVIDIA A100 80GB PCIe
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 11.1, V11.1.74
GCC: gcc (Ubuntu 9.3.0-17ubuntu1~20.04) 9.3.0
PyTorch: 1.10.0
PyTorch compiling details: PyTorch built with:
您好,我在mmdetection上根据您论文里Implementation Details的介绍(关于训练widerface),对ddod的优化器部分进行了以下改动:
optimizer = dict(type='SGD', lr=0.0075, momentum=0.9, weight_decay=0.0005)
optimizer_config = dict(grad_clip=None)
lr_config = dict(
policy='CosineRestart',
warmup='linear',
warmup_iters=500,
warmup_ratio=0.1,
periods=[
30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30, 30,
30, 30
],
restart_weights=[
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1
],
min_lr_ratio=0.01)
runner = dict(type='EpochBasedRunner', max_epochs=600)
此外,我也将reg loss改为了DIoU loss,但是每个epoch报告的mAP均为0。请问是什么情况呢?
请问将backbone由r50换成r34检测不出目标是什么原因呢?
Thank you for your great work! As the title says, I have a little question about "X".
When ddod is applied to wideface, does the testing process adopt the method in tinaface?
In addition, could you release the code to apply ddod to widerface?
Hi, thanks for your great work!.
It seems that there is no FCOS version of DDOD (Use anchor point instead of anchor) implemented as indicated in the Table 3 of your paper, could you also share that part of code and config for reference?
Thanks!
Hi! Awesome work!
Do you have any plans to upload COCO weights?
Especially,
It would be great if you also could provide configs for DDOD-X because the arXiv v1 seems to lack the explanation of DDOD-X and the details of multi-scale testing and stronger data augmentation.
Hi, thanks for your great work. But when I run this code, it threw an error with AttributeError: 'ConfigDict' object has no attribute 'retina_assigner'
. I guess self.train_cfg.retina_assigner
in atss_r50_1x.py
is missing. Can you please provide it?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.