HAT HAT-L

Dear author, I have been reproducing the neural network model of hat recently. Due to the poor computational power of the server in my laboratory, could you please open source the pre-training model of Hat-L *2? Thank you for your contribution to open source.

May 05 '23 11:05 Bugs-Bunny01

@1222056426 You means the HAT-L SRx2 trained on ImageNet? Unfortunately this intermediate checkpoint is not preserved now.

May 05 '23 16:05 chxy95

@1222056426 You means the HAT-L SRx2 trained on ImageNet? Unfortunately this intermediate checkpoint is not preserved now.

Ok, thank you for your reply. But I still have a question, how can I use my own data set for training, my data set does not have a uniform resolution size, when I set the path in the yml file, still get an error

May 07 '23 05:05 Bugs-Bunny01

Traceback (most recent call last): File "/root/miniconda3/lib/python3.8/runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None, File "/root/miniconda3/lib/python3.8/runpy.py", line 87, in _run_code exec(code, run_globals) File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launch.py", line 260, in main() File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launch.py", line 255, in main raise subprocess.CalledProcessError(returncode=process.returncode, subprocess.CalledProcessError: Command '['/root/miniconda3/bin/python', '-u', 'hat/train.py', '--local_rank=7', '-opt', 'options/train/train_HAT-L_SRx2_finetune_from_ImageNet_pretrain.yml', '--launcher', 'pytorch']' returned non-zero exit status 1.

@1222056426 You means the HAT-L SRx2 trained on ImageNet? Unfortunately this intermediate checkpoint is not preserved now.

Ok, thank you for your reply. But I still have a question, how can I use my own data set for training, my data set does not have a uniform resolution size, when I set the path in the yml file, still get an error

Traceback (most recent call last): File "/root/miniconda3/lib/python3.8/runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None, File "/root/miniconda3/lib/python3.8/runpy.py", line 87, in _run_code exec(code, run_globals) File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launch.py", line 260, in main() File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launch.py", line 255, in main raise subprocess.CalledProcessError(returncode=process.returncode, subprocess.CalledProcessError: Command '['/root/miniconda3/bin/python', '-u', 'hat/train.py', '--local_rank=7', '-opt', 'options/train/train_HAT-L_SRx2_finetune_from_ImageNet_pretrain.yml', '--launcher', 'pytorch']' returned non-zero exit status 1.

May 07 '23 07:05 Bugs-Bunny01