easy-faster-rcnn.pytorch icon indicating copy to clipboard operation
easy-faster-rcnn.pytorch copied to clipboard

Checkpoint for Resnet50 and Resent18?

Open piyushy1 opened this issue 6 years ago • 4 comments

By any chance, do you have the checkpoints for resnet50 or resnet18? I'm using the inference part of the script because my GPU isn't strong enough for training it. It would be really helpful if you have it.

Thanks!

piyushy1 avatar Jul 25 '19 20:07 piyushy1

Here are more trained models: Resnet-18 trained on VOC2007, got mAP = 0.6791 Resnet-50 trained on VOC2007, got mAP = 0.7438 Resnet-50 trained on COCO2017, got AP = 0.3252 Resnet-50 trained on COCO2017 with a longer schedule, got AP = 0.3447

potterhsu avatar Jul 26 '19 06:07 potterhsu

Hi, Can u provide checkpoints for coco2017-person model.. Thanks

sachingoyal0104 avatar Jan 09 '20 07:01 sachingoyal0104

Here are more trained models: Resnet-18 trained on VOC2007, got mAP = 0.6791 Resnet-50 trained on VOC2007, got mAP = 0.7438 Resnet-50 trained on COCO2017, got AP = 0.3252 Resnet-50 trained on COCO2017 with a longer schedule, got AP = 0.3447

Thank you for your contributions. I would like to ask about the training hyperparameters for Resnet50 on VOC2007.

Hrqingqing avatar Mar 01 '22 02:03 Hrqingqing

Here are more trained models: Resnet-18 trained on VOC2007, got mAP = 0.6791 Resnet-50 trained on VOC2007, got mAP = 0.7438 Resnet-50 trained on COCO2017, got AP = 0.3252 Resnet-50 trained on COCO2017 with a longer schedule, got AP = 0.3447

Thank you for your contributions. I would like to ask about the training hyperparameters for Resnet50 on VOC2007.

What I mean is that without loading the pre-trained model parameters.

Hrqingqing avatar Mar 01 '22 05:03 Hrqingqing