Let's first download the pre-trained Torch model from https://github.com/DmitryUlyanov/online-neural-doodle/blob/master/pretrained/starry_night.t7 and save it in the current folder (where we are planning to run the following code from). Create a folder named output on the current path to save the generated image by the model.
The next code block demonstrates how to perform an NST (with Starry Night style) to an input content image. First, use the cv2.dnn.readNetFromTorch() function to load the pre-trained model.
Next, create a 4-dimensional blob from the image with the cv2.dnn.blobFromImage() function by subtracting the mean values from the RGB channels. Finally, perform a forward pass to obtain ...