{ "

Carvana Dataset for the U-Net experiment

\n

You can find the download instructions on Kaggle.

\n

Save the training images inside _^_0_^_ folder and the masks in _^_1_^_ folder.

\n": "

U-Net \u5b9e\u9a8c\u7684 Carvana \u6570\u636e\u96c6

\n

\u4f60\u53ef\u4ee5\u5728 Kaggle \u4e0a\u627e\u5230\u4e0b\u8f7d\u8bf4\u660e\u3002

\n

\u5c06\u8bad\u7ec3\u56fe\u50cf\u4fdd\u5b58\u5728_^_0_^_\u6587\u4ef6\u5939\u4e2d\uff0c\u5c06\u8499\u7248\u4fdd\u5b58\u5728_^_1_^_\u6587\u4ef6\u5939\u4e2d\u3002

\n", "

Carvana Dataset

\n": "

Carvana \u6570\u636e\u96c6

\n", "

Get an image and its mask.

\n\n": "

\u83b7\u53d6\u56fe\u50cf\u53ca\u5176\u8499\u7248\u3002

\n\n", "

Size of the dataset

\n": "

\u6570\u636e\u96c6\u7684\u5927\u5c0f

\n", "

Get a dictionary of images by id

\n": "

\u6309 id \u83b7\u53d6\u56fe\u50cf\u8bcd\u5178

\n", "

Get a dictionary of masks by id

\n": "

\u901a\u8fc7 id \u83b7\u53d6\u53e3\u7f69\u5b57\u5178

\n", "

Get image id

\n": "

\u83b7\u53d6\u56fe\u7247\u7f16\u53f7

\n", "

Image ids list

\n": "

\u6620\u50cf ID \u5217\u8868

\n", "

Load image

\n": "

\u52a0\u8f7d\u56fe\u7247

\n", "

Load mask

\n": "

\u88c5\u8f7d\u63a9\u7801

\n", "

Return the image and the mask

\n": "

\u8fd4\u56de\u56fe\u50cf\u548c\u8499\u7248

\n", "

Testing code

\n": "

\u6d4b\u8bd5\u4ee3\u7801

\n", "

The mask values were not _^_0_^_, so we scale it appropriately.

\n": "

\u63a9\u7801\u503c\u4e0d\u662f_^_0_^_\uff0c\u56e0\u6b64\u6211\u4eec\u5bf9\u5176\u8fdb\u884c\u4e86\u9002\u5f53\u7684\u7f29\u653e\u3002

\n", "

Transform image and convert it to a PyTorch tensor

\n": "

\u53d8\u6362\u56fe\u50cf\u5e76\u5c06\u5176\u8f6c\u6362\u4e3a PyTorch \u5f20\u91cf

\n", "

Transform mask and convert it to a PyTorch tensor

\n": "

\u53d8\u6362\u63a9\u7801\u5e76\u5c06\u5176\u8f6c\u6362\u4e3a PyTorch \u5f20\u91cf

\n", "

Transformations

\n": "

\u8f6c\u6362

\n", "\n": "\n", "Carvana dataset for the U-Net experiment": "U-Net \u5b9e\u9a8c\u7684 Carvana \u6570\u636e\u96c6", "Carvana dataset for the U-Net experiment.": "U-Net \u5b9e\u9a8c\u7684 Carvana \u6570\u636e\u96c6\u3002" }