-
## Instructions To Reproduce the 🐛 Bug:
1. what changes you made (`git diff`) or what code you wrote
Use default codes and COCO dataset.
2. what exact command you run:
run `python train_net.py…
-
TridentNet: I have a rtx2080s with 8G memory and it’s fine to train in batch size=2.but when I test the model use test_branch_idx=-1(which uses all three branches to test instead of only the middle br…
-
Hey @jfix71
We need to enable support of infering model like FasterRCNN which has dynamic operators like NMS and NonZero. Reference model from onnx model zoo is https://github.com/onnx/models/blob…
-
## ❓ Questions and Help
Can I install detectron2 on CPU? Currently, I'm getting the following error while building detectron2 on manjaro.
Env:
```
--------------------- --------------------…
-
## REPRODUCTION OF THE ISSUE
### Modification
- No modification
### Environment
```
------------------------ -------------------------------------------------------------------------------
sys…
-
my dataset classes are classes = ('wajueji', 'zhatuche', 'yaluji',)
but when I test my dataset, the mAP classes are as follows:
+-----------+-------+--------+--------+-------+
| class | gts | dets…
-
Hi guys, we are working on the new open-source IDE for data science called [Musket ML](http://musket-ml.com)
And we are basing our instance segmentation tools on MM Detection - This is a [demo](htt…
-
I tried use my own dataset with cocoformat, here is my own surmmary about total bboxes:
**Number of images containing all the classes: 2546
[673, 2478, 2223, 1725]**
However, when i applied th…
-
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
…
-
(base) ai@ai-Precision-Tower-5810:~/detectron2$ python demo/demo.py --config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml --input input1.jpg input2.jpg --opts MODEL.WEIGHTS dete…