zhangrui
zhangrui
What is your TensorFlow and TensorLayer version?
It seems that your code is different with the official code [here](https://github.com/tensorlayer/tensorlayer/blob/master/example/tutorial_mnist.py)
yes, it will have better performance
1. The demo code use image with width and heigh around 1200~2000, and crop sub-image with 384x384. 2. No limit. 3. 1000 images should be good.
@ontheway16 For 1st question, you can use larger image but don't be too large, because but the current model is designed for the demo dataset. If you want larger image,...
It is possible to use `tl.vis.read_images` and `tl.vis.save_images` to convert all JPG into PNG?
memory is not enough
Either programming or data preparation.
You can't load the model, unless you already trained the model