pytorch-retinanet

pytorch-retinanet copied to clipboard

q248953144

Where can I get a pre-training model？

2

[net.load_state_dict(torch.load('./model/net.pth'))](https://github.com/kuangliu/pytorch-retinanet/blob/master/train.py#L48)

zihaozhang9

Loss is coming nan

21

ridhajuneja123

This pytorch version is quite helpful for research! I want to do a transfer learning on other datasets. Is there anyone willing to share the pretrain model on voc or...

XuandongZhao

aboy2018

Use Sigmoid instead of Softmax in Focal Loss

10

@kuangliu Could you please tell me why you use log_softmax to compute the focal loss instead of the sigmod layer mentioned in the paper?Or I made a mistake in understanding?

Mendel1

Ttt749

focal_loss_alt VS focal_loss

3

Why there are two version of focal loss methods in _"class FocalLoss(nn.Module): URL: [https://github.com/kuangliu/pytorch-retinanet/blob/2199fd9711fd787ae409800a499db73e6d466fd7/loss.py](url)" ????

LifeBeyondExpectations

how to run train.py???

2

python train.py ==> Preparing data.. Epoch: 0 Traceback (most recent call last): File "train.py", line 114, in train(epoch) File "train.py", line 75, in train loss = criterion(loc_preds, loc_targets, cls_preds, cls_targets)...

237014845

DataEncoder init File "G:\python\Smile\Smile\activation\encoder.py", line 117, in decode anchor_boxes = self._get_anchor_boxes(input_size) File "G:\python\Smile\Smile\activation\encoder.py", line 57, in _get_anchor_boxes xy = (xy*grid_size).view(fm_h,fm_w,1,2).expand(fm_h,fm_w,9,2) RuntimeError: shape '[75, 75, 1, 2]' is invalid for input...

WHG555