Converting Deeplabv3 for inference

[Kishor_G]

Found this post.

How could I train on multi-gpu and infer with single gpu

I train a model on two gpus, and then save the model like this: net = nn.DataParallel(net) ..... torch.save(net, save_path) Then I load the model and run inference with single gpu: CUDA_VISIBLE_DEIVCES=0 python infer.py the infer.py is like this: im = cv2.imread('./cropped.jpg') im = cv2.resize(im, (224, 224)).transpose(2, 0, 1) im = torch.tensor([im, im, im], dtype = torch.float32) model_path = './res/model.pytorch' model = torch.load(model_path) mode…

Will try this method, and let you know if it works