I’m testing my model for dog breeds identification.
i get results with ~90-91% of accuracy, score on kaggle ~0.25 . This result seems to be far from what Jeremy gets in video, although i reproduce same steps on same data. Does anyone have same problem ? Can this depend on environment i run it on ? I use kaggle data, resnext50, make same steps as in video …
although 91% is much less, than possible, it still seems to be decent. But when i run predictions on individual images from google, i got 7 mistakes from 7 tries. Not even close guess to the breed on the image, e.g.:
I resize images to something around 300-600 px, dogs are in the middle… but my model’s predictions are disappointing.
Any ideas on how to ‘troubleshoot’ quality issues with the model ?