Manthan Patel

Is it possible to continue further re-training of the network created from NATS bench? The issue is that for one to one comparison for DrNAS, DARTS and GDAS we need...

Checkpoint restart training

2

Hi, When I try to restart my training from the stored checkpoint it takes some random architecture instead of the one already stored. Is there any way to avoid this?...

Unable to process .pgm or grayscale images

4

Current model is unable to process the .pgm images. While the actual grounding DINO model can process these type of images(Tested on the colab notebook https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/zero-shot-object-detection-with-grounding-dino.ipynb#scrollTo=VKzXm8mNR2XS)

Format of labels is xyxy

6

Hi, I am using autodistill-grounding-dino to annotate imgaes for yolov8 training. Yolov8 model expects the labels in format (class x_center y_center width height). - Is the format returned by autodistill-grounding-dino...