Closed boxbox2 closed 5 months ago
One more thing, because my single card only 16g so I changed to multiple card to run unet_model,but the seg_model didn't. Maybe it doesn't support multi-card running?I don't know. Has anyone encountered and solved this problem?
I solved it. in the past,When I selected multi-card when training, but eval.py did not write multi-card function, the problem of missing key will occur. I chose to exercise strict = false at 385. But something went wrong. I solved the problem by adding 381 lines in eval.py
Because training on the entire MVTEC dataset is too time-consuming, I only trained the 'carpet' category. This is my args.json, batchsize = 4,epochs = 1500,Different from the author's batchsize = 16 and epoch = 3000
after 1500,train loss is 3.232
when i run eval.py,it will say missing key so i changed the eval.py,(line 381)
after this It can be found that out_mask has better results, but recon_con is still a Gaussian image.
Isn’t this training a model per category? Why can Segmentation Sub-network training be successful, but Norm-guided One-step Denoising does not have good results?Or is it because I didn’t train enough rounds? Or must all categories be trained to avoid possible missing keys problems?
Looking forward to your reply