2_mnist error with Step 2.6 "Build the complete graph for feeding inputs, training, and saving checkpoints."

[magicmathmandarin]

trafficstars

Hi, I just downloaded the code tonight. I was able to run 0_tf_hello_world.ipynb and 1_linear_regression_model.ipynb without problem, except some warning messages.

But I got error running 2_mnist.ipynb, starting from Step 2.6. The error messages are "ValueError: Only call sparse_softmax_cross_entropy_with_logits with named arguments (labels=..., logits=..., ...)".

I am using TensorFlow version 1.1, Python 3.5 and Window 10.

[wolffg]

These notebooks are almost certainly out of date.

I would recommend installing a newer version of TensorFlow and checking out http://github.com/tensorflow/workshops for up-to-date notebooks. I'll leave this bug open to remind me to note that on the repo. Good luck!

On Mon, Jan 29, 2018 at 7:06 PM, Sarah Chen [email protected] wrote:

Hi, I just downloaded the code tonight. I was able to run 0_tf_hello_world.ipynb and 1_linear_regression_model.ipynb without problem, except some warning messages.

But I got error running 2_mnist.ipynb, starting from Step 2.6. The error messages are "ValueError: Only call sparse_softmax_cross_entropy_ with_logits with named arguments (labels=..., logits=..., ...)".

I am using TensorFlow version 1.1, Python 3.5 and Window 10.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/wolffg/tf-tutorial/issues/10, or mute the thread https://github.com/notifications/unsubscribe-auth/AA1YDlbFcgwNl28wZP0pkeT4IASmikH2ks5tPoc7gaJpZM4RxskM .

[magicmathmandarin]

Thanks for your response! I did use http://github.com/tensorflow/workshops and was able to run a similar practice.