I’m running the code 01_intro.ipynb.
#id first_training
#caption Results from the first training
# CLICK ME
from fastai.vision.all import *
path = untar_data(URLs.PETS)/'images'
def is_cat(x): return x[0].isupper()
dls = ImageDataLoaders.from_name_func(
path, get_image_files(path), valid_pct=0.2, seed=42,
label_func=is_cat, item_tfms=Resize(224))
learn = cnn_learner(dls, resnet34, metrics=error_rate)
learn.fine_tune(1)
learn.show_results()
In the book, the error_rate is 0.005, but my results look pretty bad.
And the result of show_results also looks wierd.
Does anyone know the cause of the problem?
fastbook.__version__
0.0.16