Segmentation models with pretrained backbones. PyTorch.
models
image-processing
pytorch
neural-networks
imagenet
segmentation
pretrained-models
image-segmentation
unet
semantic-segmentation
pretrained-weights
pspnet
fpn
deeplabv3
unet-pytorch
deeplab-v3-plus
linknet
segmentation-models
unetplusplus
pretrained-backbones
-
Updated
Jun 29, 2022 - Python
What is the Map in pascal voc 07 dataset using this code? As i read your code, i find that you do not fix the BN parameters. The batchsize is small, following the paper FPN or Mask RCNN, you need to set the training and trainbale to False for the slim.batch_norm op. I am testing whether this is the problem for the bad generalization for mutiple objects.