def densenet161(pretrained=False, **kwargs): if pretrained: model = DenseNet(num_init_features=96, growth_rate=48, block_config=(6, 12, 36, 24), **kwargs) pattern = re.compile( r'^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$' ) pretrained_state_dict = torch.load( './Authority/densenet161-8d451a50.pth' ) # load_url函数根据model_urls字典下载或导入相应的预训练模型 for key in list(pretrained_state_dict.keys()): res = pattern.match(key) if res: new_key = res.group(1) + res.group(2) pretrained_state_dict[new_key] = pretrained_state_dict[key] del pretrained_state_dict[key] now_state_dict = model.state_dict() # 返回model模块的字典 pretrained_state_dict.pop('classifier.weight') pretrained_state_dict.pop('classifier.bias') now_state_dict.update(pretrained_state_dict) model.load_state_dict(now_state_dict) # 最后通过调用model的load_state_dict方法用预训练的模型参数来初始化你构建的网络结构, # 这个方法就是PyTorch中通用的用一个模型的参数初始化另一个模型的层的操作。load_state_dict方法还有一个重要的参数是strict, # 该参数默认是True,表示预训练模型的层和你的网络结构层严格对应相等(比如层名和维度) return model return DenseNet(num_init_features=96, growth_rate=48, block_config=(6, 12, 36, 24), **kwargs)
def __init__(self, smg_config=None): if not smg_config: smg_config = defaultconfig self.cammodel = DenseNet(block_config=(6, 12, 48, 32), num_classes=4) self.gbpmodel = DenseNet(block_config=(6, 12, 48, 32), num_classes=4) self.cammodel.load_state_dict( torch.load(smg_config["pretrain_path"], map_location='cpu')["state_dict"]) self.gbpmodel.load_state_dict( torch.load(smg_config["pretrain_path"], map_location='cpu')["state_dict"]) self.cammodel.eval() self.gbpmodel.eval() self.gradcam = GradCam(self.cammodel, "features.denseblock4", smg_config["use_cuda"]) self.guidebp = GuidedBackpropReLUModel(self.gbpmodel, smg_config["use_cuda"]) self.useunet = False if smg_config["unet_path"]: self.useunet = True self.unet = UNet(3, 3) self.unet.load_state_dict( torch.load(smg_config["unet_path"], map_location='cpu')) self.unet.eval() if smg_config["use_cuda"]: self.unet.cuda()
def densenet169(pretrained=False, model_path=None, **kwargs): r"""Densenet-169 model from `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`_ Args: pretrained (bool): If True, returns a model pre-trained on ImageNet """ model = DenseNet(num_init_features=64, growth_rate=32, block_config=(6, 12, 32, 32), **kwargs) if pretrained: # '.'s are no longer allowed in module names, but pervious _DenseLayer # has keys 'norm.1', 'relu.1', 'conv.1', 'norm.2', 'relu.2', 'conv.2'. # They are also in the checkpoints in model_urls. This pattern is used # to find such keys. pattern = re.compile( r'^(.*denselayer\d+\.(?:norm|relu|conv))\.((?:[12])\.(?:weight|bias|running_mean|running_var))$' ) if model_path is not None: state_dict = torch.load(model_path) else: state_dict = model_zoo.load_url(model_urls['densenet169']) for key in list(state_dict.keys()): res = pattern.match(key) if res: new_key = res.group(1) + res.group(2) state_dict[new_key] = state_dict[key] del state_dict[key] model.load_state_dict(state_dict) return model
def DENSENets(arch, cfg, model_path): """ 自定义接口 for model_factory :param arch: dense121, dense201, dense161, dense264 :param cfg: arch configs :param model_path: state_dict.pth :return: a blank model or pre-trained model """ pattern = re.compile( r'^(.*denselayer\d+\.(?:norm|relu|conv))\.' r'((?:[12])\.(?:weight|bias|running_mean|running_var))$') model = DenseNet(**cfg) state_dict = {} if os.path.isfile(model_path): print('\n=> loading model.pth from %s.' % model_path) state_dict = torch.load(model_path) elif model_path == 'download': print('\n=> downloading model.pth from %s.' % model_urls[arch]) state_dict = model_zoo.load_url(model_urls[arch]) else: assert model_path == '', '<model_path> must refer to valid-model.ckpt || ' 'download' ' || "".' if state_dict: for key in list(state_dict.keys()): res = pattern.match(key) if res: new_key = res.group(1) + res.group(2) state_dict[new_key] = state_dict[key] del state_dict[key] model.load_state_dict(state_dict) print('\nSuccess: loaded model.pth from %s.\n' % model_path) return model
def __init__(self): super(DenseNetModel, self).__init__() self.dense_net = DenseNet(growth_rate=32, block_config=(6, 12, 32, 32), num_classes=2) self.criterion = nn.CrossEntropyLoss()
def test_pytorch(): import torch from torchvision.models import DenseNet model = DenseNet() t = torch.randn(1, 3, 224, 224) out = model(t) assert out.shape[1] == 1000
def __init__(self, NUM_CLASSES): super(DenseNet201, self).__init__() self.model_name = "DenseNet201" self.model = DenseNet( num_init_features=64, growth_rate=32, block_config=(6, 12, 48, 32), num_classes=NUM_CLASSES, )
def __init__(self, NUM_CLASSES): super(DenseNet161, self).__init__() self.model_name = "DenseNet161" self.model = DenseNet( num_init_features=96, growth_rate=48, block_config=(6, 12, 36, 24), num_classes=NUM_CLASSES, )
def dn_bc_100_12_fc(): model = DenseNet(growth_rate=12, block_config=(16, 16, 16), num_init_features=24, num_classes=100) conv = nn.Conv2d(3, 24, kernel_size=3, padding=1, bias=False) nn.init.kaiming_normal_(conv.weight) model.features.conv0 = conv del model.features.norm0, model.features.relu0 return model
def densenet161(num_classes=17, pretrained=False): model = DenseNet(num_init_features=96, growth_rate=48, block_config=(6, 12, 36, 24), num_classes=num_classes) if pretrained: # load model dictionary model_dict = model.state_dict() # load pretrained model pretrained_dict = model_zoo.load_url(model_urls['densenet161']) # update model dictionary using pretrained model without classifier layer model_dict.update({ key: pretrained_dict[key] for key in pretrained_dict.keys() if 'classifier' not in key }) model.load_state_dict(model_dict) return model
def load_model(model_path): device = torch.device('cuda') checkpoint = torch.load(model_path, map_location=lambda storage, loc: storage) # load checkpoint to CPU and then put to device https://discuss.pytorch.org/t/saving-and-loading-torch-models-on-2-machines-with-different-number-of-gpu-devices/6666 model = DenseNet(growth_rate=checkpoint["growth_rate"], block_config=checkpoint["block_config"], num_init_features=checkpoint["num_init_features"], bn_size=checkpoint["bn_size"], drop_rate=checkpoint["drop_rate"], num_classes=checkpoint["num_classes"]).to(device) model.load_state_dict(checkpoint["model_dict"]) print( f"total params: \t{sum([np.prod(p.size()) for p in model.parameters()])}" ) model.eval() return model, device
def __init__(self, growth_rate=32, block_config=(6, 12, 24, 16), num_init_features=64, bn_size=4, drop_rate=0.2, num_classes=14): super(LungXnet, self).__init__() self.model = DenseNet(growth_rate=growth_rate, block_config=block_config, num_init_features=num_init_features, bn_size=bn_size, drop_rate=drop_rate, num_classes=num_classes) self.n_filters = self.model.classifier.in_features self.model.classifier = nn.Sequential( OrderedDict([('linear', nn.Linear(self.n_filters, num_classes)), ('sigmoid', nn.Sigmoid())]))
es = s / (percent + .00001) rs = es - s return '%s (- %s)' % (asMinutes(s), asMinutes(rs)) #specify if we should use a GPU (cuda) or only the CPU print(torch.cuda.get_device_properties(gpuid)) torch.cuda.set_device(gpuid) device = torch.device(f'cuda:{gpuid}' if torch.cuda.is_available() else 'cpu') # + #build the model according to the paramters specified above and copy it to the GPU. finally print out the number of trainable parameters model = DenseNet(growth_rate=growth_rate, block_config=block_config, num_init_features=num_init_features, bn_size=bn_size, drop_rate=drop_rate, num_classes=num_classes).to(device) #model = DenseNet(growth_rate=32, block_config=(6, 12, 24, 16), #these represent the default parameters # num_init_features=64, bn_size=4, drop_rate=0, num_classes=3) print( f"total params: \t{sum([np.prod(p.size()) for p in model.parameters()])}") # - #this defines our dataset class which will be used by the dataloader class Dataset(object): def __init__(self, fname, img_transform=None): #nothing special here, just internalizing the constructor parameters
OUTPUT_DIR = args.outdir resize = args.resize batch_size = args.batchsize patch_size = args.patchsize stride_size = patch_size//2 # ----- load network device = torch.device(args.gpuid if args.gpuid!=-2 and torch.cuda.is_available() else 'cpu') checkpoint = torch.load(args.model, map_location=lambda storage, loc: storage) #load checkpoint to CPU and then put to device https://discuss.pytorch.org/t/saving-and-loading-torch-models-on-2-machines-with-different-number-of-gpu-devices/6666 model = DenseNet(growth_rate=checkpoint["growth_rate"], block_config=checkpoint["block_config"], num_init_features=checkpoint["num_init_features"], bn_size=checkpoint["bn_size"], drop_rate=checkpoint["drop_rate"], num_classes=checkpoint["num_classes"]).to(device) model.load_state_dict(checkpoint["model_dict"]) model.eval() print(f"total params: \t{sum([np.prod(p.size()) for p in model.parameters()])}") # ----- get file list if not os.path.exists(OUTPUT_DIR): os.makedirs(OUTPUT_DIR) files = [] basepath = args.basepath # basepath = basepath + os.sep if len(