search

nuclearboy95 / Anomaly-Detection-PatchSVDD-PyTorch

246 stars 56 forks source link

how split the image into smaller patch_size for training, and make sure the network can work? #24

Open 754467737 opened 1 year ago

754467737 commented 1 year ago

I spilt the image into smaller 32x32 patch size for training the network, but it results are not good. Do you have any suggestion?

crazyn2 commented 1 year ago

Same issue. Could you give more details about how split image into patch