Multiple outputs using PSPNet pre-trained model on Cityscapes

[Swaraj Reddy Chada]

Hello,
When the PSPNet pre-trained model is used, the output is a tuple of 2 tensors. Can someone clarify what they are and how to achieve 1 output among them such that computation time can be saved?

net = get_model('pspnet_resnetd101b_cityscapes',pretrained_backbone=True,pretrained = True)
yp = net(X)
yp.size()

This throws an error:
AttributeError Traceback (most recent call last)
in
1 yp = net(X) # model outputs 2 different learning rates
----> 2 yp.size()

AttributeError: 'tuple' object has no attribute 'size'

[Oleg Sémery]

Check the following:

from pytorchcv.model_provider import get_model as ptcv_get_model
import torch
net = ptcv_get_model("pspnet_resnetd101b_cityscapes", pretrained=True, aux=False)
net.eval()
x = torch.randn(1, 3, 480, 480)
y = net(x)

[Swaraj Reddy Chada]

Thanks for the response. It really helped me. One another thing I would like to know is about other input sizes which can be used.

I would like to use multi-scale processing which needs (3,240,240) and (3,120,120) as inputs to the network. Is it possible to achieve that using the model? Thank you.

[Oleg Sémery]

Technically, yes:

net = ptcv_get_model("pspnet_resnetd101b_cityscapes", pretrained=True, in_size=(120, 120), aux=False)

[Swaraj Reddy Chada]

Thank you for the reply. It helped me a lot with my project.

[Swaraj Reddy Chada]

The pretrained_backbone option provided hasn't seemed to be having a major effect on the predictions. I have tried both booleans and the results did not differ much.
Could you please let me know whether it is to be used any differently to improve the predictions. Thank you.

[Oleg Sémery]

The pretrained_backbone option is for training.

[Swaraj Reddy Chada]

Thank you for the quick response.