praj441

In multi_cfg.py, why num_class=1 for extra_head ?

1

The **model configs** are mentioned as follow in file config/multi_cfg.py : model = dict( type='SingleStageDetector', backbone=dict( type='SimpleVoxel', num_input_features=4, use_norm=True, num_filters=[32, 64], with_distance=False), neck=dict( type='SpMiddleFHD', output_shape=[150,440,440], num_input_features=4, num_hidden_features=64 * 19, ),...

TypeError: grid_sample() got an unexpected keyword argument 'align_corners'

1

While training for multi_class, I am getting this error. My PyTorch version is 1.1.0. I searched on google and find out that the attribute 'align_corners' is introduced in PyTorch 1.3.0....

Hi, I am not able to understand what is 'anchor_offsets' in the anchor_generation setting in the file configs/car_cfg.py. What does it signify? How the particular values are chosen? Please kindly,...

Runtime error in data loader due to variable size of tensors

7

When trying to run the train.py on my custom dataset, I am getting the following error:- "RuntimeError: stack expects each tensor to be equal size, but got [4, 1000, 3]...