Robin Cole
Robin Cole
Switching to `MultiLabelClassificationTask` and I am getting `RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same or input should be a MKLDNN tensor and weight is a...
Anyone still experiencing this? I've spent much time debugging why I get differences between my legacy code and one of the differences is the use of `.to(self.device)` introduced to work...
I've also got some functions which will convert the output of JSONSink to coco_json, for importing as pre-annotations. This currently has to calc the area and parse the xyxyxyxy with...
I still think it would be a nice feature to have out of the box, along with xyxy for the polygon - I can make a PR if required
That appears to result in the entire area array being saved for every row:
A related feature request, DataFrameSink as a convenience to avoid ```python csv_path = f'/tmp/{image_id}.csv' with sv.CSVSink(csv_path) as sink: sink.append(detections, {}) df = pd.read_csv(csv_path) ```
[example_32648.tif.zip](https://github.com/user-attachments/files/16817902/example_32648.tif.zip) I've no issue opening with rasterio
OK the issue is there are also png files in that folder
I feel it would be good to at least raise a warning if a non tif is opened