# fix random seed rng = np.random.RandomState(37148) # create instance of HED model net = HED() net.cuda() # load the weights for the model net.load_state_dict(torch.load(arg_Model)) # batch size nBatch = 1 # make test list for infer make_txt(arg_DataRoot,'test') # create data loaders from dataset testPath = os.path.join(arg_DataRoot, 'test.lst') print(testPath) # create data loaders from dataset std = [0.229, 0.224, 0.225] mean = [0.485, 0.456, 0.406] # std=[0.229, 0.224, 0.225] # mean=[0.185, 0.156, 0.106] transform = transforms.Compose([ transforms.ToTensor(), #transforms.Normalize(mean, std)
# max epoch nEpoch = 150 # load the images dataset dataRoot = 'data/dam_material_falloff/' modelPath = 'model/vgg16.pth' pretrain_bool = True filter_bool = False option = '' valPath = dataRoot + 'val.lst' trainPath = dataRoot + 'train.lst' # write txt file make_txt(dataRoot, 'train') make_txt(dataRoot, 'val') make_txt(dataRoot, 'test') # create data loaders from dataset std = [0.229, 0.224, 0.225] mean = [0.485, 0.456, 0.406] transform = transforms.Compose( [transforms.ToTensor(), transforms.Normalize(mean, std)]) targetTransform = transforms.Compose([transforms.ToTensor()]) # # trans = transforms.Compose([ # transforms.RandomChoice([ # transforms.RandomRotation((0, 0)),