mlp_mnist_simple.ipynb => `softmax_cross_entropy_with_logits` with named arguments (labels=..., logits=..., ...) #17

aydenkim · 2017-11-16T23:50:26Z

About https://github.com/sjchoi86/Tensorflow-101/blob/master/notebooks/mlp_mnist_simple.ipynb

Recently updated Tensorflow (1.4) will make the following error.

ValueError: Only call softmax_cross_entropy_with_logits with named arguments (labels=..., logits=..., ...)

Just simply adding named arguments will solve this issue.

cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits =pred, labels=y))

FYI, http://www.edwith.org/deeplearningchoi/lecture/15552/ has the right code.

hierarchyJK · 2021-08-11T03:30:23Z

got it

aydenkim changed the title ~~softmax_cross_entropy_with_logits with named arguments (labels=..., logits=..., ...)~~ mlp_mnist_simple.ipynb => softmax_cross_entropy_with_logits with named arguments (labels=..., logits=..., ...) Nov 16, 2017

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

mlp_mnist_simple.ipynb => `softmax_cross_entropy_with_logits` with named arguments (labels=..., logits=..., ...) #17

mlp_mnist_simple.ipynb => `softmax_cross_entropy_with_logits` with named arguments (labels=..., logits=..., ...) #17

aydenkim commented Nov 16, 2017 •

edited

hierarchyJK commented Aug 11, 2021

mlp_mnist_simple.ipynb => softmax_cross_entropy_with_logits with named arguments (labels=..., logits=..., ...) #17

mlp_mnist_simple.ipynb => softmax_cross_entropy_with_logits with named arguments (labels=..., logits=..., ...) #17

Comments

aydenkim commented Nov 16, 2017 • edited

hierarchyJK commented Aug 11, 2021

mlp_mnist_simple.ipynb => `softmax_cross_entropy_with_logits` with named arguments (labels=..., logits=..., ...) #17

mlp_mnist_simple.ipynb => `softmax_cross_entropy_with_logits` with named arguments (labels=..., logits=..., ...) #17

aydenkim commented Nov 16, 2017 •

edited