{moderator edit: code removed}
In am facing the following error : Layer lstm expects 13 inputs, but it received 3 input tensors. Inputs received: [<tf.Tensor ‘input_7:0’ shape=(None, None, 1, 90) dtype=float32>, <tf.Tensor ‘c0_6:0’ shape=(None, 64) dtype=float32>, <tf.Tensor ‘a0_6:0’ shape=(None, 64) dtype=float32>]
This number keeps increasing, 3 then 5, 7, 9, 11, 13, 15…it keeps increasing by 2
I cannot solve. Please help
{comment removed by the author}
Oops, never mind, I was looking at the djmodel() function.
In LSTM_cell(), the initial state variables are in the wrong order.
yes, its the music_inference_model function
Any help please ?? I am still not able to solve it
I have changed and tried it sir, it still dosen’t seem to work.
Please post the entire contents of the inference_model summary.
{moderator edit: code removed}
I did not say to post your code. That breaks the course Honor Code.
I asked you to post the outputs of the cell that contains the summary.
Sorry about that
here is the output
ValueError Traceback (most recent call last)
in
----> 1 inference_model = music_inference_model(LSTM_cell, densor, Ty = 50)
in music_inference_model(LSTM_cell, densor, Ty)
38 for t in range(Ty):
39 # Step 2.A: Perform one step of LSTM_cell. Use “x”, not “x0” (≈1 line)
—> 40 a, _, c = LSTM_cell(x, initial_state = [c, a])
41
42 # Step 2.B: Apply Dense layer to the hidden state output of the LSTM_cell (≈1 line)
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/layers/recurrent.py in call(self, inputs, initial_state, constants, **kwargs)
707 # Perform the call with temporarily replaced input_spec
708 self.input_spec = full_input_spec
→ 709 output = super(RNN, self).call(full_input, **kwargs)
710 # Remove the additional_specs from input spec and keep the rest. It is
711 # important to keep since the input spec was populated by build(), and
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in call(self, *args, **kwargs)
924 if _in_functional_construction_mode(self, inputs, args, kwargs, input_list):
925 return self._functional_construction_call(inputs, args, kwargs,
→ 926 input_list)
927
928 # Maintains info about the Layer.call stack.
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py in _functional_construction_call(self, inputs, args, kwargs, input_list)
1090 # TODO(reedwm): We should assert input compatibility after the inputs
1091 # are casted, not before.
→ 1092 input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
1093 graph = backend.get_graph()
1094 # Use self._name_scope() to avoid auto-incrementing the name.
/opt/conda/lib/python3.7/site-packages/tensorflow/python/keras/engine/input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
156 str(len(input_spec)) + ’ inputs, ’
157 'but it received ’ + str(len(inputs)) +
→ 158 ’ input tensors. Inputs received: ’ + str(inputs))
159 for input_index, (x, spec) in enumerate(zip(inputs, input_spec)):
160 if spec is None:
ValueError: Layer lstm expects 15 inputs, but it received 3 input tensors. Inputs received: [<tf.Tensor ‘input_8:0’ shape=(None, None, 1, 90) dtype=float32>, <tf.Tensor ‘c0_7:0’ shape=(None, 64) dtype=float32>, <tf.Tensor ‘a0_7:0’ shape=(None, 64) dtype=float32>]
Regarding the music_inference_model():
Did you modify that line of code? Because it does not look correct. And it is outside the area you were supposed to modify.
In Step 2, the order of the variables in the initial_state =[…] is incorrect.
I changed it because x0 had 2 dimensions, but had 3 dimensions, so I thought maybe doing this would help. I will change it back, but still it was not working.
Do not change parts of the provided code outside of the marked places.
If the notebook was wrong in such an obvious way, we would have fixed it a long time ago,
@abir did you figure this out? any hints?