search

potterhsu / easy-faster-rcnn.pytorch

An easy implementation of Faster R-CNN (https://arxiv.org/pdf/1506.01497.pdf) in PyTorch.
MIT License
165 stars 57 forks source link

size mismatch #29

Open qzk1193564654 opened 4 years ago

qzk1193564654 commented 4 years ago

Hello! Excuse me, what's the problem with this situation? How to solve it! thank you

size mismatch for detection._proposal_class.weight: copying a param with shape torch.Size([21, 2048]) from checkpoint, the shape in current model is torch.Size([6, 2048]). size mismatch for detection._proposal_class.bias: copying a param with shape torch.Size([21]) from checkpoint, the shape in current model is torch.Size([6]). size mismatch for detection._proposal_transformer.weight: copying a param with shape torch.Size([84, 2048]) from checkpoint, the shape in current model is torch.Size([24, 2048]). size mismatch for detection._proposal_transformer.bias: copying a param with shape torch.Size([84]) from checkpoint, the shape in current model is torch.Size([24]).

batooooo commented 4 years ago

Do you solve that?

qzk1193564654 commented 4 years ago

Do you solve that? no,i do not know how to solve?

Ayuan66 commented 3 years ago

check this #8