A question about pascal voc pre-trained model
RumengYi opened this issue · comments
Hi, why you load train2_iter_20000.caffemodel instead of init.caffemodel from http://liangchiehchen.com/projects/released/deeplab_aspp_resnet101/prototxt_and_model.zip as initial weights? I think the latter should be loaded.
The model is initialized with init.caffemodel
.
Line 147 in 4219467
deeplab-pytorch/configs/voc12.yaml
Line 34 in 4219467
The deeplabv1_resnet101-coco.pth
file are converted from init.caffemodel
as mentioned in README.
Thank you for your reply, but on PASCAL VOC 2012, the model is initialized with train2_iter_20000.caffemodel, https://github.com/kazuto1011/deeplab-pytorch/blob/master/convert.py#L170, why you load train2_iter_20000.caffemodel instead of init.caffemodel?
Yes, python convert.py --dataset voc12
loads train2_iter_20000.caffemodel
trained on PASCAL VOC 2012 already, however, the converted weights are not used in training. This is just for those who do not want to train by themselves.
Please run python convert.py --dataset coco
to produce the initial weights from init.caffemodel
.