-
**问题描述**
尝试将faster rcnn r50 fpn模型转为onnx格式 参考了https://github.com/PaddlePaddle/PaddleDetection/issues/5986 ，但进行export_model时失败。（如果删去export_onnx=True则能转换成功，但因为没有去掉控制流的原因，这样得到的模型无法转为onnx。）
**更…
-
https://github.com/czczup/ViT-Adapter/blob/94ffa6b6134b99d838312e2e042d6ac3a52a7ef8/detection/configs/mask_rcnn/dinov2/mask_rcnn_dinov2_adapter_large_fpn_3x_coco.py#L47
has all 127.5 values rather …
-
Is it possible to live object detection Mask RCNN using single GPU...?
-
My aim is to implement this model in edge computing, and one thing i'm trying out is quantising the model.
I've converted the .h5 file into a tf frozen graph following [this](https://github.com/mat…
-
Hi @waleedka,
Do you know about the Light Head RCNN Project? (Paper: https://arxiv.org/abs/1711.07264)
If yes which parts of your model do you think need to be adjusted to make use of this method to…
-
ln -s /PycharmProjects/T-SEA-main/data/INRIAPerson/Test/labels/faster_rcnn-rescale-labels /PycharmProjects/T-SEA-main/eval/inria/demo/v5-demo/faster_rcnn/det-labels
ground truth path : /Pycha…
-
Hello, I have some questions about the preprocess of the Waymo datasets and the evaluation. I use the official code to generate the datasets and when I train the model, some information is as follows,…
-
用7000多张的数据训练这个模型可以收敛，但换了十万多的不同类别的数据训练12个epoch后推理结果都为空，loss一直在80左右，下面是配置文件，4张3090的卡，想问下是哪里的问题。
> dataset_type = 'CocoDataset'
data_root = '/mnt/disk3/Co-DETR/dataset/wxcl/'
img_norm_cfg = dict(
…
-
python tools/merge_weights.py --clip_path --base_path --save_path --base_model
Hello author, this is a great job. Can you provide a complete example?
-
When I perform the code, I met the problem "No module named "rcnn.cython.bbox"". I find that there eixts bbox.pyx. After I install VS2015, the problem still exits. Is there anybody who have addressed …