Closed youngwanLEE closed 3 years ago
Hi, I'm impressed by your excellent work.
I have a question.
I wonder which type of the pre-trained weights (224x224 or 384x384 finetuned) is used for object detection.
I know both 224x224 and 384x384 are pre-trained on ImageNet-1k.
Hi, thanks for your interest in our work, we use the 224x224 pretrained model for both detection and segmentation.
@LightDXY Thanks for reply :)
Hi, I'm impressed by your excellent work.
I have a question.
I wonder which type of the pre-trained weights (224x224 or 384x384 finetuned) is used for object detection.
I know both 224x224 and 384x384 are pre-trained on ImageNet-1k.