The solution was not to use the new Tensor API and just use PIL as the image reader. I have done various tests, but I cannot get the result I want. This transform can accept or Tensors, in short, the resizing does not produce the same image, one is way softer than the other. 1 I'm trying to change the size of an image, turning larger images into smaller images and vice versa, with PIL. Initially I thought that it was fastai's fault, but all the problem came from the new interaction between the tochvision.io.images.read_image and the. So, I have to make the reading and preprocessing of images as close as possible as fastai Transform pipeline, to get accurate model outputs.Īfter converting the transforms to ansforms I noticed that my model performance dropped significantly.
#Pil image resize commang install#
(I am waiting to finally be able to install only the fastai vision part, without the NLP dependencies, this is coming soon, probably in fastai 2.3, at least it is in Jeremy's roadmap). In our deployment env we are not including fastai as requirements and rely only on pure pytorch to process the data and make the inference.
It is a simple image classifier trained with fastai. If size is a sequence like (h, w), the output size will be matched to this. size ( sequence or int) Desired output size. Yesterday I was refactoring some code to put on our production code base. img ( PIL Image or Tensor) Image to be resized.
0 kommentar(er)
