-
I keep running to the following error whilst trying to train a model on Colab.
```python
---------------------------------------------------------------------------
TypeError …
-
Hi! I was reading your code and found something strange. In Ln. [151](https://github.com/Majiker/BalancedMetaSoftmax-InstanceSeg/blob/b7d4bd9c71c583cf3ad9e349e2e1a693b5ad4012/detectron2/modeling/roi_h…
-
Hello folks,
Thanks for you detectron2 and special thanks for providing the lvis dataset. So awesome to see something like google-open-images-v5
Coming to the issue,
Noticed there is a pre-tra…
-
I noticed a problem in lvis api wrapper. From [lvis spec](https://www.lvisdataset.org/dataset) the expected fields for annotations are 'id', 'area', 'bbox', 'bbox_mode', 'category_id', 'segmentation'…
-
Verification script cannot find the following files even though they are intact and located in the same CUDA bin directory as other files which are found successfully.
2021-06-02 14:16:50.299737: W…
-
### System information
- **Have I written custom code (as opposed to using a stock example script
provided in TensorFlow)**:
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**:Ma…
-
When training an LVIS model out of the box on a single GPU, training begins and then immediately fails with error `RuntimeError: CUDA error: invalid device function (ROIAlign_forward_cuda at /pasteur/…
-
Hi,
Perhaps I have some misunderstanding about the dataset, but I had thought if a category (from annotations['categories']) has an 'image_count' and 'instance_count' set to zero, it would not appe…
-
Hi, I've been training some things with detectron2 and have had a really really good experience with it. I think this is going to be my go to repo for a long time when training detection models. Thank…
joaqo updated
3 years ago
-
## 📚 Documentation
Hi! Again. Thanks for opensouring the code.
I wonder the **main differences** between "CustomCascadeROIHeads" "CustomFastRCNNOutputLayers" and original "CascadeROIHeads" and "Fast…
lxtGH updated
3 years ago