Week 3, C3W3_Assignment in section 4-5, classify and evaluate, How to pass the tf.data.Dataset.from_tensor_slices output to model, to get the prediction

[Deepti_Prasad]

You asked about pred first. now you are asking a different query.

please be specific about your issue. You aren’t suppose to use expand_dim at all to get pred. You are referring the week 2 first grade cell codes but

check what I mentioned in my previous comment? I stated to get model output using the sentence_vectorized? when did you use this code to get model output? not where we try to convert IDs to tensor, check the grade cell where you predict word. go through the Assignments carefully.

or refer the below link where arvy mention the same function you need to use to get pred using test_gen

Predict grader cell issue

Remember what the model’s last layer does: [image] it concatenates the outputs. So when you call model.predict(*) you get the concatenated output (1, 256) which you now need to split back into v1 and v2. (the v1v2[0] and v1v2[-1] would not work, since it’s the same thing in this case). You probably have successfully implemented that in Exercise 4 (the classify function). What you need again here is to get: v1.shape - (1, 128) v2.shape - (1, 128) Here is the entire thing For (“When will I…