'Train TensorFlow Sequential model using soft labels
How can I train a TensorFlow Sequential model using soft labels (vectors of p(Y_i|X)) instead of hard labels? e.g. instead of using y = [0, 1, 0, 0, 1] I want to use y = [[0.2, 0.8], [0.9, 0.1], [0.3, 0.7], [0.01, 0.99], [0.65, 0.35]].
I tried but I get this error:
ValueError: `logits` and `labels` must have the same shape, received ((None, 1) vs (None, 2)).
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|