search

kaixin96 / PANet

Code for our ICCV 2019 paper PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment
322 stars 64 forks source link

Question about test image size #15

Closed LinglanZhao closed 4 years ago

LinglanZhao commented 4 years ago

Hi Kaixin, It seems that during both training and testing both the support and query images are resized to a fixed size (e.g. [417, 417]). However, in many few-shot segmentation works, the segmentation mask output is resized to the original image resolution for evaluation. How can I get the original query images and the corresponding ground-truth masks during testing phase? I also output some unused key-value pairs in the dataloader dictionary, but they seem to be of the same fixed shape: sample_batched['support_images_t'][0][0].shape = torch.Size([1, 3, 417, 417]) sample_batched['query_images_t'][0].shape = torch.Size([1, 3, 417, 417]) sample_batched['query_masks'][0][0].shape = torch.Size([1, 1, 417, 417]) sample_batched['query_labels'][0].shape = torch.Size([1, 417, 417])

kaixin96 commented 4 years ago

Hi @LinglanZhao , sorry for the late reply.

You can set transforms to None in https://github.com/kaixin96/PANet/blob/master/test.py#L60 and modify https://github.com/kaixin96/PANet/blob/master/models/fewshot.py#L55 to forward support and query images separately.

Thank you.

LinglanZhao commented 4 years ago

Thanks for your reply!