-
hi! I want to train cascade-rcnn on my own dataset (three classes). I don't know how to modify the files(eg. examples/voc/). Can you give me some instructions? Thank you!
-
mmdetection v1.0 cascade rcnn模型 转成v2后finetune，与直接在mmdet v1.0 finetune对比，发现v2版本 loss刚开始为8.1，第一个epoch后map 为74.8。
`2021-07-24 16:36:45,713 - mmdet - INFO - Epoch [1][100/14009] lr: 4.653e-05, eta: 13 …
-
而且我用retinanet的时候在visdrone上没有问题，但是用cascade rcnn却总是会出现nan，我调了参数比如lr也没用。
这是我目前遇到的问题。
-
Hello,
I hope you are doing well. I am working on a project where I would like to use the InternImage dataset solely for object detection without involving segmentation. I attempted to use it with …
-
Table 2 in the SWIN transformer paper mentioned the result with DEIT backbone with cascaded RCNN. I wonder if it is possible to also share the code and configuration file for reproducing this result. …
-
When there is a problem with demo.py, we first use the demo.py given by the author @jwyang and report an error import error: no module named fast_ rcnn.faster_ rcnn_ cascade。 It was found that the dem…
-
It seems the x101-32*8d backbone is even worse than resnet101 when I experiment on cascade rcnn.
-
Hi,
When I am trying to run a training epoch using pretrained weights, I am getting a warning that the model and state dict do not match exactly. As I have not modified anything, I suspect that it …
-
## Instructions To Reproduce the Issue and Full Logs:
```python
from detectron2.modeling import build_model
from detectron2.model_zoo import get_config
from torch.cuda.amp import autocast
# conf …
-
我使用2.0rc版本的PaddleDetection，当我在dygraph尝试运行Cascade-Faster-RCNN-CBResNet200vd-FPN的算例时，出现了AssertionError: the module CBResNet is not registered，检查了一下dygraph下的backbones路径，确实没有cb_resnet.py，而在PaddleDetection…
ghost updated
3 years ago