Computer vision

source code: model = IR_SE_152(input_size = [112, 112]) //changed to IR_152 also failed model.load_state_dict(torch.load("Head_ArcFace_Epoch_112_Batch_2547328_Time_2019-07-13-02-59_checkpoint.pth")) model.eval() .................

no, its not broken, I just tried

@xsacha could you share the python script on converting .pth to .pb file? thank you

@xsacha sorry, it was pt file, not pb

hi @Kikedao , could you please share your training code? model compression seems interesting. thank you

@Kikedao thank you so much for the information. I want to put person segmentation on mobile/edge devices, so I retrained the person segmentation model(lite version) from dennis (https://github.com/dennisbappert/u-2-net-portrait), with supervisely...

BTW, We trained the u2net-lite of this repo for about 300 epochs, the train loss is around 0.2, and the tar is around 0.02, although it is not small enough,...

@dennisbappert hi dennis, I tested on your demo.py with your checkpoint, it seems that square_pad is harmful, I tested with this image: https://i.ibb.co/ZGPFCZj/1-5-Pedestrian.jpg the result is much better if we...

而且我试了几张restoration，效果跟gpen差距比较远

@junyanz how about StyleGAN so far?