search

Shaosifan / HSENet

Hybrid-Scale Self-Similarity Exploitation for Remote Sensing Image Super-Resolution (accepted by TGRS)
37 stars 5 forks source link

OutOfMemory #6

Closed Zhang-Jinwei closed 10 months ago

Zhang-Jinwei commented 1 year ago

Hello, thank you very much for your sharing. We ran into some problems when reproducing your code, may I ask you? We tried to use the pre-training model to test some of our data, but no matter we chose x4 or x2, it would be reported out of memory, and there was no load on our gpu. Besides, we observed that your pre-training model was not large. image

Shaosifan commented 1 year ago

Hi, I wonder what is the size of your test data. If the size of your data is too large, I suggest you super-resolve it block-by-block by adding the parameter "--test_block": python demo_deploy.py --model=HSENET --scale=4 --test_block