-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and f…
-
One of the large differences between this and the original implementation is this implementation follows the diagram in the original paper and extracts feature levels 3, 4, 5, 6 and 7 by changing leve…
-
## 🚀 Feature
I'm an enthusiastic user of D2, compared with others sw it's more easy, complete, and extensible to use.
I have just one question: it seems that modelzoo is not so much updated, compare…
-
Буду тут рассказывать что пробовал и какой вышел результат.
* Пока лучший результат дала модель FPN из репы qubvel. 0.722 Local. 0.708 LB
Хочу понять какой способ мерджить предикты в конце лучше…
-
## 🚀 Feature
Implementation of Efficient-Net and Efficient-Det in Pytorch Lightning
### Motivation
These two algorithms are the state of the art in Image classification and Object detection. Pr…
-
Does anyone can help to provide a GhostNet config?thanks!!!
-
当YOLOv5x为主体与标准结构的区别是：（1）首先去掉14和19的CBAM模块（2）降低与P2关联的通道数（128）（3）在输出头之前会添加SPP模块，注意SPP的kernel随着P的像素减小而减小（4）在CBAM之后进行输出（5）只保留backbone以及最后一层输出的TransBlock（6）采用BiFPN作为neck
我看官方实现的TPH的代码中也和您对网络做了同样的更改，想请问下为…
-
# Prerequisites
Please answer the following questions for yourself before submitting an issue.
- [Y] I am using the latest TensorFlow Model Garden release and TensorFlow 2.
- [Y] I am reporting…
-
Hi , I see you using a lot of backbone as effi,mb2,mb3,..do you compare the backbone to each other ? - do you have the performance of each one ? - i find effi quite good, why don't you use!
Thanks !
-
I am currently training using the Efficient D3 model.
Then, I am trying to modify the min_level and max_level of FPN in multiscale_anchor_generator in pipeline.config.
Several bugs occur.
- bas…