About the crop size for training and testing

class BaseNet(nn.Module):
    def __init__(self, nclass, backbone, aux, se_loss, dilated=True, norm_layer=None,
                 base_size=576, crop_size=608, mean=[.485, .456, .406],
                 std=[.229, .224, .225], root='~/.encoding/models'):

Previously, I noticed that you choose base_size=520, crop_size=480 and now you change them to base_size=576, crop_size=608.

However, I still have a concern about it, the 608 should be larger than the largest highth or width in your dataset, so we should increase this parameter if we are dealing with larger datasets.

Besides, I noticed that you mentioned that your MultiEvalModule only support single image evalution, but you also provide the batch size parameter, which is contradictory....... I guess we can only set the batch size as 1 during testing phase.

  def forward(self, image):
        """Mult-size Evaluation"""
        # only single image is supported for evaluation

Start with the BaseNet.init entry point and the MultiEvalModule.forward method shown in the issue. Compare the crop-size defaults with the dataset image dimensions and verify how the evaluation batch-size parameter relates to the stated single-image support. Done means the intended crop-size and evaluation batch-size behavior is resolved and documented or corrected.