PVT
PVT copied to clipboard
whai362
Official implementation of PVT series
Paper offers convolution free architecture but implementation contains convolution, at pvt2 paper authors says spatial reduction done with conv but I could not see that in pvt1. Is there any...
Hi @whai362 I was wondering why the pooling size is set to 7 for all stages? Have you tried a higher pooling size (e.g. more keys and values) for the...
Hi, may I ask for the logs for PVT v2 in the ImageNet classification task under all sizes?
Gradient overflow. Skipping step, loss scaler 0 reducing loss scale to 0.03125, I use 4 gpus , but where could I change the batch size?
Can I try your PVT and PVTv2 to Faster-RCNN? Will it also give a big improvement (if you tried simulating this)?
Hi, when I run " python demo.py demo.jpg ./configs/retinanet_pvt_v2_b5_fpn_1x_coco.py ./checkpoints/retinanet_pvt_v2_b5_fpn_1x_coco.pth', I got this error: KeyError: 'RetinaNet: "pvt_v2_b5: \'pretrained\'"' How should I solve this problem?
What could be the best learning rate if I have 1 GPU, and I set the samples_per_gpu=1 and workers_per_gpu=1?
hi I would like to finetune this model on my data for classification! Is it possible?
