machine-learning - 模型 = CSRNet() | TypeError: super(type, obj): obj 必须是类型的实例或子类型

Question

transform=transforms.Compose([
                      transforms.ToTensor(),transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                    std=[0.229, 0.224, 0.225]),
])

root = '/home/meet/CSRNet-pytorch/ShanghaiTech/'
part_A_train = os.path.join(root,'part_A/train_data','images')
part_A_test = os.path.join(root,'part_A/test_data','images')
part_B_train = os.path.join(root,'part_B/train_data','images')
part_B_test = os.path.join(root,'part_B/test_data','images')
path_sets = [part_A_test]

#defining the image path
img_paths = []
for path in path_sets:
    for img_path in glob.glob(os.path.join(path, '*.jpg')):
       img_paths.append(img_path)

model = CSRNet()
model = model.cuda()

在运行 model = CSRNet() 我得到一个“Typeerror: super(type, obj): obj must be an instance or subtype of type”

我指的是从人群图像中获取人数的教程。

这是我指的教程：

https://www.analyticsvidhya.com/blog/2019/02/building-crowd-counting-model-python/

这是内核输出窗口：-

model = CSRNet() 下载：“ https://download.pytorch.org/models/vgg16-397923af.pth ”到 /home/meet/.torch/models/vgg16-397923af.pth 回溯（最近一次通话最后）：

文件“”，第 1 行，模型 = CSRNet()

文件“/home/meet/CSRNet-pytorch/model.py”，第 16 行，在init mod = models.vgg16(pretrained = True)

文件“/home/meet/anaconda3/lib/python3.7/site-packages/torchvision/models/vgg.py”，第 152 行，在 vgg16 model.load_state_dict(model_zoo.load_url(model_urls['vgg16']))

文件“/home/meet/anaconda3/lib/python3.7/site-packages/torch/utils/model_zoo.py”，第 66 行，在 load_url _download_url_to_file(url, cached_file, hash_prefix, progress=progress)

_download_url_to_file 中的文件“/home/meet/anaconda3/lib/python3.7/site-packages/torch/utils/model_zoo.py”，第 73 行 u = urlopen(url, stream=True)

文件“/home/meet/anaconda3/lib/python3.7/site-packages/requests/api.py”，第 70 行，在 get return request('get', url, params=params, **kwargs)

文件“/home/meet/anaconda3/lib/python3.7/site-packages/requests/api.py”，第 55 行，在以 session.Session() 作为会话的请求中：

文件“/home/meet/anaconda3/lib/python3.7/site-packages/requests/sessions.py”，第 346 行，在init self.mount('https://', HTTPAdapter())

文件“/home/meet/anaconda3/lib/python3.7/site-packages/requests/adapters.py”，第 117 行，在init super(HTTPAdapter, self) 中。初始化（）

标签： machine-learningheatmap