Hello I am facing this error when running the computing_metrics function: InvalidArgumentError: Incompatible shapes: [361,32] vs. [361] [Op:SquaredDifference] The function receives this parameters: mse, mae = compute_metrics(series_valid, rnn_forecast) It seems “series_valid” and “rnn_forecas” …

Your model output is incompatible with the validation series. Please ensure that your model produces the correct number of features per timestep at the output layer. Here are a couple of examples to interpret the output shape: (10, ): model produces 10 timesteps of output with 1 feature per time…

Error in computing_metrics function (incompatible shapes)

Course Q&A TensorFlow Developer Professional Natural Language Processing in TensorFlow

Boris_Martinez November 4, 2022, 4:37pm 3

Yes, thank you very much. I solved the issue!

Incompatible shapes: [1150,64] vs. [1150] [Op:SquaredDifference]

Topic		Replies	Views
Week 4 : Assignment: Shape Error during Metric Evaluation Sequences, Time Series and Prediction week-4	12	772	July 14, 2022
There was a problem grading your submission. Details: Incompatible shapes: [1150,64] vs. [1150] [Op:SquaredDifference] Sequences, Time Series and Prediction week-4	30	1096	February 5, 2023
InvalidArgumentError after model compilation Sequences, Time Series and Prediction week-4	5	587	May 12, 2023
Getting the grading issue in Tensorflow Course4 week4 Sequences, Time Series and Prediction week-4	3	530	April 17, 2023
InvalidArgumentError: required broadcastable shapes [Op:SquaredDifference] Generative Deep Learning with TensorFlow week-3	8	1044	July 14, 2023

Error in computing_metrics function (incompatible shapes)

Related topics