I was following the codelabs tensorflow for poets and the training worked fine but when I runned the script to evaluate a image:
python -m scripts.label_imag
As @Mimii and @Celio mentioned: change ~/scripts/label_image.py, at the line input_layer = "input" to input_layer = "Mul" AND change the input dimensions: input_height = 299 and input_width= 299
input_layer = "input"
input_layer = "Mul"
input_height = 299
input_width= 299