Open alaa-shubbak opened 1 year ago
data_preprocessor = dict( type='SelfSupDataPreprocessor', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
If you train a classification model, just use original data_preprocessor.
data_preprocessor = dict(
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
to_rgb=True)
what about using HRnet backbone on self-supervised approach ? for example use it within the simclr model .
I am trying to do so , and got some error on this issue
error is : raise ValueError( ValueError: Input dimension should be at least 3
any suggestion? please.
Branch
main branch (mmpretrain version)
Describe the bug
i am trying to pretrain the HRNet model on my custom dataset.
I ran this command :
python tools/train.py configs/hrnet/hrnet-w32_4xb32_ACID_part.py --work-dir train_dir/just_test/hrnet-w32_ACID_part/
my dataset consist of one class ,and only training set, there is no test and val.
I got this error message:
Environment
Other information
i modified the config file of hrnet model as bellow :
my dataset (ACID_part_n.py) file contains the following lines