Showing results by author "tensorflow" in All Categories
1 result
-
-
Tensorflow transfer learning EfficientNet on Stanford dogs
- By: tensorflow
- Original Recording
-
Overall0
-
Performance0
-
Story0
in Mandarin/zh, with EfficientNet, with pretrained weights, freeze all the weights, then you can add your top, then fit/train, you can reach satisfied accuracy with very limited training time/epochs; then unfreeze the layers -20: of non BN layers, change its trainable to True, then fit, you can get even better accuracy with very few like 10 epochs. So this is called transfer learning.
Failed to add items
Sorry, we are unable to add the item because your shopping cart is already at capacity.Add to basket failed.
Please try again laterAdd to Wish List failed.
Please try again laterRemove from Wish List failed.
Please try again laterFollow podcast failed
Unfollow podcast failed
-