How to let custom datasets support the fast path for computing the aspect ratio? about deep-learning-for-image-processing HOT 3 CLOSED

这是因为你没有在my_dataset.py文件中实现获取img_sieze的功能，建议你直接关闭aspect-ratio-group功能。
直接将--aspect-ratio-group-factor值改为-1，关闭此功能

parser.add_argument('--aspect-ratio-group-factor', default=-1, type=int)

from deep-learning-for-image-processing.

感谢up，我直接关闭aspect-ratio-group功能，会报RuntimeError: received 0 items of ancdata错误，加入了get_height_and_width功能，将--workers设置为0之后就不用遍历整个数据集了。
def get_height_and_width(self, idx): data = self.img_data[idx] data_height = int(data["heigh"]) data_width = int(data["width"]) return data_height, data_width

from deep-learning-for-image-processing.

恩，自己实现下get_height_and_width方法，不让它自动去挨个读取图像然后统计height和width是最好的。

from deep-learning-for-image-processing.