Blocked on unet_model for U-net assignment

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi I am stuck with an error for the unet_model, saying:
“ValueError: Layer conv2d_8 expects 1 inputs, but it received 2 input tensors. Inputs received: [<tf.Tensor ‘max_pooling2d_2/MaxPool:0’ shape=(None, 48, 64, 32) dtype=float32>, <tf.Tensor ‘conv2d_7/Relu:0’ shape=(None, 96, 128, 32) dtype=float32>]”
I don’t understand what is the conv2d_8 because we don’t define it anywhere in the script. And I can’t find what is causing the problem.
Would anyone have any idea?
Thanks

2

Unless you specify a name when you create the layer, the names of the layers are generated automatically.
You could try adding names to the layers to identify which one is causing the issue.

3

Here is a thread that discusses a similar issue:

4

Thank you TMosh. I realized that I had to select one element of the conv_block and not the full block. That was creating the error.

1 Like