Created
December 22, 2021 07:01
-
-
Save danielcwq/aa1423774c4033c22d40c596ea7ae1c4 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
x = dls.vocab | |
image = (path/'images/00000181_035.png') #some random image from the database | |
def match(raw, vocab): | |
return [[vocab[0],(raw[0].item()*100)],[vocab[1],(raw[1].item()*100)],[vocab[2],(raw[2].item()*100)],[vocab[3],(raw[3].item()*100)],[vocab[4],(raw[4].item()*100)],[vocab[5],(raw[5].item()*100)],[vocab[6],(raw[6].item()*100)],[vocab[7],(raw[7].item()*100)],[vocab[8],(raw[8].item()*100)],[vocab[9],(raw[9].item()*100)],[vocab[10],(raw[10].item()*100)],[vocab[11],(raw[11].item()*100)],[vocab[12],(raw[12].item()*100)],[vocab[13],(raw[13].item()*100)],[vocab[14],(raw[14].item()*100)]] | |
def list_preds(img_path): | |
prediction, indice, losses = learn.predict(img_path) | |
arr = match(losses, x) | |
return(arr) | |
list_preds(image) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment