-
Given the importance of first-wave activity, it is likely that a "real" input layer would have more of a synchronous initial activity pattern -- currently input is just uniform poisson spiking.
* S…
-
## Instructions To Reproduce the 🐛 Bug:
I train a custom data set on two computers at the same time. The models are "COCO-Detection/faster_rcnn_R_50_C4_3x.yaml" and "COCO-Detection/faster_rcnn_R_50…
-
I am trying to fine-tune a PointRend model on a new dataset, but when I run the training script I get the error:
`KeyError: "No object named 'PointRendMaskHead' found in 'ROI_MASK_HEAD' registry!"`
…
-
Hello, I'm sorry to bother you but I get into trouble these days. As far as I know, AP is the average of per-category precision. That's same for APr, APc, APf. Therefore, we should have the following …
-
I trained on my custom dataset with 4 classes; when I used RPNHead, it worked normally. However, when I used rpn_head is RankBasedRPNHead and got an error: AssertionError: The `num_classes` (1) in Ran…
-
keep forgetting to try that.
-
I am trying to test your pretrained model from the TAO dataset and this is the error I am getting:
```
100%|██████████| 1/1 [00:00
ghost updated
3 years ago
-
I use your code and the model provided to infer RS-yolact. The inference effect is shown in the figure below. What is the reason?
 pick e.g., central 2x2 set of pools, for TEO can do entire layers.. somewhat expensive but can just do intermittently over a sample of data recorded periodically.
…