ImageToTensor

class mmcv.transforms.ImageToTensor(keys: dict)

Convert image to torch.Tensor by given keys.

The dimension order of input image is (H, W, C). The pipeline will convert it to (C, H, W). If only 2 dimension (H, W) is given, the output would be (1, H, W).

Required keys:

• all these keys in keys

Modified Keys:

• all these keys in keys

Parameters

keys (Sequence[str]) – Key of images to be converted to Tensor.

transform(results: dict) → dict

Transform function to convert image in results to torch.Tensor and transpose the channel order.

Parameters

results (dict) – Result dict contains the image data to convert.

Returns

The result dict contains the image converted to :obj:torch.Tensor and transposed to (C, H, W) order.

Return type

dict