EfficientDet.Pytorch
EfficientDet.Pytorch copied to clipboard

Published 20 hours ago •

toandaominh1997

Reame
Issues

when I load pretrained model EfficientDet-D1(with Weight)

Open XDhughie opened this issue 5 years ago • 7 comments

RuntimeError: Error(s) in loading state_dict for EfficientDet: size mismatch for bbox_head.retina_cls.weight: copying a param with shape torch.Size([180, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([9, 256, 3, 3]). size mismatch for bbox_head.retina_cls.bias: copying a param with shape torch.Size([180]) from checkpoint, the shape in current model is torch.Size([9]).

Dec 29 '19 02:12 XDhughie

你好！你遇到RuntimeError: CUDA error: out of memory ？这样的情况了吗？

Dec 29 '19 11:12 qtw1998

why can't you speak in English ?

Dec 30 '19 01:12 heartInsert

你好！你遇到RuntimeError: CUDA error: out of memory ？这样的情况了吗？我之前也遇到这个情况，后面把batch size调低，改到2或者1就可以了。

Dec 30 '19 04:12 frankite

你好！你遇到RuntimeError: CUDA error: out of memory ？这样的情况了吗？我之前也遇到这个情况，后面把batch size调低，改到2或者1就可以了。

我遇到了，也是调整batchsize

Dec 30 '19 13:12 XDhughie

why can't you speak in English ?

can u answer my question，thinks

Dec 30 '19 13:12 XDhughie

你好！你遇到RuntimeError: CUDA error: out of memory ？这样的情况了吗？我之前也遇到这个情况，后面把batch size调低，改到2或者1就可以了。

我遇到了，也是调整batchsize

你好，你有试着训练efficientdet-d2或者d3/d4...吗，是否比d1的效果要好呢？

Dec 30 '19 13:12 frankite

I guess they just dont understand. LOL

Dec 31 '19 01:12 tryanbot