-
The imbalance of the action classes in the ROAD dataset also needs to be addressed (see Fig. 8 for class instance counts). One simple solution is to over-sample the low-instance classes while training…
-
The link in the README.md for the tensorflow model is being directed to a page not found location. Wanted to confirm is the model in use here is the ModelGarden-RetinaNet
Thanks for the assistance
-
Hi, I have tried several pre-trained Resnet50.npy models to train the RetinaNet using the exact commands provided in the readme here.
However, after 40 50 iterations the loss becomes NaN everytime.
…
-
我根据JDet/projects/retinanet/README.md文件当中的链接https://cloud.tsinghua.edu.cn/f/f12bb566d4be43bfbdc7/下载文件ckpt_30.pkl，并复制到目录JDet/projects/retinanet/work_dirs/retinanet_gaofen/checkpoints当中，运行命令
python run_…
-
## ❓ How to use Detectron2
How to apply the EQL in object detection such as RetinaNet?
-
@tianzhi0549 I trained object detection with FCOS
MODEL:
META_ARCHITECTURE: "GeneralizedRCNN"
WEIGHT: "/py36_torch_v11/VoVNet-FCOS-master/VoV_model/vovnet39_ese_state_dict.pth"
BACKBONE:
…
-
### Checklist
- [X] I have searched related issues but cannot get the expected help.
- [X] 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/tree/main/docs/en/faq.md) but …
-
静态图里都有，但动态图里没有
-
I used mtq.INT8_default_CFG as recommended for CNN networks (mtq.quantize(model, config, forward_loop). My initial model ran at 80FPS after quantization it dropped to 40FPS? I checked the model struct…
-
It'd be great to have object detection models (e.g. RetinaNet and MaskRCNN) incorporated as part of our models repository.
saeta updated
4 years ago