from fastai import *
from fastai.vision import *
df = pd.read_csv("./myfile.udt.csv")
samples = df[df.path.str.contains("samples")]
url_list = [str(a) for a in list(samples["imageUrl"])]
open("./images.txt", "w").write("\n".join(url_list))
# Download all the sample images into an "images" directory
download_images("./images.txt", "./images", max_pics = 10000)
labels = pd.DataFrame(data={
    "image": (df.index - 1).astype("str").str.zfill(8) + ".jpg",
    "output": df["output"]
})
# OPTIONAL: Delete bad images and remove missing images
verify_images("./images", delete=True)
missing_images = list([img for img in labels["image"] if not(Path("./images") / img).exists()])
labels = labels[~labels["image"].isin(missing_images)]
# Create ImageDataBunch
data = ImageDataBunch.from_df(".", labels, folder="images", seed=42,
                              label_col="output", bs=4, size=224,
                              ds_tfms=get_transforms()).normalize(imagenet_stats)

from fastai import *
from fastai.vision import *
df = pd.read_csv("./myfile.udt.csv")
# Create a filename column with just the filenames, remove the other columns
df["filename"] = [a.split("/")[-1] if isinstance(a,str) else a for a in list(df["imageUrl"])]
df = df[["filename", "output.classification"]]
# Remove any invalid entries
df.set_index("filename", inplace=True)
df.drop(np.NaN, inplace=True)
df.reset_index(inplace=True)
data = ImageDataBunch.from_df(".", idb_df, folder="./images", seed=42,
                              label_col="output.classification", bs=4, size=224,
                              ds_tfms=get_transforms()).normalize(imagenet_stats)