Hi, the error "AttributeError: The layer “lstm has multiple inbound nodes, with different input shapes. Hence the notion of “input shape” is ill-defined for the layer. Use get_input_shape_at(node_index) instead.” returned when I run the test on function “modelf” and I couldn’t find the reason. What could be wrong and how can I address that?
I am guessing the issue here should be Step 3 of modelf function, I think you are not passing the right input to the model!
# Step 3: Create model instance taking three inputs and returning the list of outputs. (≈ 1 line)
I followed the instruction on the page and coded “)”, I don’t think here lies the error, or could it? 
Perhaps your one step attention is not right, butI cannot guess further without seeing the code! Send me a copy exercise 1 and 2 in private message!
Hi! For your information, the codes are:
If more information needed, please let me know.
Bests,
Yunxuan
You are to supposed to share it on public!!! I said private message…
But I saw the code, I do not see any issue, you have to wait for another mentor who is more familiar with the course to pick this up!
Sorry about that. I thought replying through email is private
If you search for that on the forums, you will find lots of posts. E.g. here’s one that has some helpful discussion.
Thank you for your help! I’ll check these immediately.
在 2025-04-29 23:05:56，“Paul Mielke via DeepLearning.AI” notifications@dlai.discoursemail.com 写道：
| paulinpaloalto Super Mentor - DLS
April 29 |
- | - |
Yunxuan:
lstm has multiple inbound nodes
If you search for that on the forums, you will find lots of posts. E.g. here’s one that has some helpful discussion.
Visit Topic or reply to this email to respond.
To unsubscribe from these emails, click here.
To send a private message via the forum, you view the topic in a browser, then click on a username, and a popup will appear that has a “Message” button.