An adaptive image toning method, system, storage medium and electronic device
An adaptive, image-based technology, applied in the field of image processing, can solve problems such as RGB three-channel incoordination, convergence difficulties, and the inability to promote batch operations based on algorithm rules
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0068] Example 1, use opencv-python to read the source image and the target image to preprocess the image, and convert the multi-dimensional array data structure ndarray used for mathematical operations in numpy into torch.tensor through the torch.from_numpy() method, where torch. .tensor is a tensor data structure used for mathematical operations in torch, similar to the previous ndarray, but tensor can build a computational graph, which is mostly used for transmission in neural networks. Convert the HWC format to CHW format by rearranging channels 2, 0, and 1 through the tensor.transpose() method, and then add the batch dimension, which should be understood as: the original tensor dimension is C×H×W , and add the batch dimension to the first position to become N×C×H×W. In the Pytorch deep learning framework, the tensor input to the network must have a batch dimension. This operation is to adapt to it and prepare for the input network. Build a convolutional layer with 3 inpu...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


