print("Results ----------") print("mAP: {:.1%}".format(mAP)) print("CMC curve") for r in ranks: print("Rank-{:<3}: {:.1%}".format(r, cmc[r - 1])) print("------------------") return cmc[0] ####################################################################################################### print("Model is being initialized") model = ResNet.ResNet50().to(device) #SAVED_MODEL_PATH = 'saved_models/p1.pth.tar' #checkpoint = torch.load(SAVED_MODEL_PATH) #model.load_state_dict(checkpoint['state_dict']) #start_epoch = checkpoint['epoch'] print("Model size: {:.5f}M".format( sum(p.numel() for p in model.parameters()) / 1000000.0)) optim = torch.optim.Adam(model.parameters()) if stepsize > 0: scheduler = lr_scheduler.StepLR(optim, step_size=stepsize, gamma=0.1) num_epochs = 242
print("Results ----------") print("mAP: {:.1%}".format(mAP)) print("CMC curve") for r in ranks: print("Rank-{:<3}: {:.1%}".format(r, cmc[r - 1])) print("------------------") return cmc[0] ####################################################################################################### print("Training of model has been started") print("Model is being initialized") model = ResNet.ResNet50(num_classes=dataset.num_train_pids, num_fcs=2).to(device) print("Model size: {:.5f}M".format( sum(p.numel() for p in model.parameters()) / 1000000.0)) optim = torch.optim.Adam(model.parameters()) if stepsize > 0: scheduler = lr_scheduler.StepLR(optim, step_size=stepsize, gamma=0.1) start_epoch = 0 num_epochs = 250 if args.resume: print("Loading checkpoint from '{}'".format(args.resume)) checkpoint = torch.load(args.resume) model.load_state_dict(checkpoint['state_dict']) start_epoch = checkpoint['epoch']