# C5W1A3 - Jazz Improvisation - \*\*UPDATE\*\* Issue solved | ERROR at "model = djmodel(Tx=30, LSTM\_cell=LSTM\_cell, densor=densor, reshaper=reshaper)" **URL:** \ **Category:** Sequence Models\ **Tags:** coursera-platform\ **Created:** [August 10, 2021, 4:49am UTC](https://community.deeplearning.ai/t/c5w1a3-jazz-improvisation-update-issue-solved-error-at-model-djmodel-tx-30-lstm-cell-lstm-cell-densor-densor-reshaper-reshaper/26378 "2021-08-10T04:49:20Z")\ **Posts on this page:** 11\ **Page:** 1
**Author:** ![rajeshm99](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/rajeshm99/32/5066_2.png) [@rajeshm99](https://community.deeplearning.ai/u/rajeshm99)\ **Post date:** [August 10, 2021, 4:49am UTC](https://community.deeplearning.ai/t/c5w1a3-jazz-improvisation-update-issue-solved-error-at-model-djmodel-tx-30-lstm-cell-lstm-cell-densor-densor-reshaper-reshaper/26378/1 "2021-08-10T04:49:21Z")
**UPDATE** Issue solved = Had to restart kernel. I followed the hints correctly and filled in the appropriate code in the djmodel() function. But I seem to get the below error when running the next code cell not matter what I do. Kindly help me understand this error! djmodel Code: {moderator edit: code removed} ## Error: ValueError Traceback (most recent call last) in ----\> 1 model = djmodel(Tx=30, LSTM\_cell=LSTM\_cell, densor=densor, reshaper=reshaper) in djmodel(Tx, LSTM\_cell, densor, reshaper) 46 a, \_, c = LSTM\_cell(inputs=x, initial\_state=[a, c]) 47 # Step 2.D: Apply densor to the hidden state output of LSTM\_Cell —\> 48 out = densor(a) 49 # Step 2.E: add the output to “outputs” 50 outputs.append(out) /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) 214 ’ incompatible with the layer: expected axis ’ + str(axis) + 215 ’ of input shape to have value ’ + str(value) + → 216 ’ but received input with shape ’ + str(shape)) 217 # Check shape. 218 if spec.shape is not None: ValueError: Input 0 of layer dense is incompatible with the layer: expected axis -1 of input shape to have value 90 but received input with shape [None, 64] ---
**Author:** ![TMosh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/tmosh/32/9321_2.png) [@TMosh](https://community.deeplearning.ai/u/TMosh)\ **Post date:** [August 10, 2021, 6:06am UTC](https://community.deeplearning.ai/t/c5w1a3-jazz-improvisation-update-issue-solved-error-at-model-djmodel-tx-30-lstm-cell-lstm-cell-densor-densor-reshaper-reshaper/26378/2 "2021-08-10T06:06:11Z")
I think the problem is in your call to LSTM\_cell(). Try removing the “inputs=” label from the '‘x’ variable. ---
**Author:** ![rajeshm99](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/rajeshm99/32/5066_2.png) [@rajeshm99](https://community.deeplearning.ai/u/rajeshm99)\ **Post date:** [August 10, 2021, 6:18am UTC](https://community.deeplearning.ai/t/c5w1a3-jazz-improvisation-update-issue-solved-error-at-model-djmodel-tx-30-lstm-cell-lstm-cell-densor-densor-reshaper-reshaper/26378/3 "2021-08-10T06:18:36Z")
@TMosh thanks for the reply. It worked fine after I restarted the Kernel, no changes made. ---
**Author:** ![TMosh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/tmosh/32/9321_2.png) [@TMosh](https://community.deeplearning.ai/u/TMosh)\ **Post date:** [August 10, 2021, 6:31am UTC](https://community.deeplearning.ai/t/c5w1a3-jazz-improvisation-update-issue-solved-error-at-model-djmodel-tx-30-lstm-cell-lstm-cell-densor-densor-reshaper-reshaper/26378/4 "2021-08-10T06:31:20Z")
Thanks for your report. ---
**Author:** ![PolarBarrel](https://avatars.discourse-cdn.com/v4/letter/p/d9b06d/32.png) [@PolarBarrel](https://community.deeplearning.ai/u/PolarBarrel)\ **Post date:** [October 25, 2021, 7:28pm UTC](https://community.deeplearning.ai/t/c5w1a3-jazz-improvisation-update-issue-solved-error-at-model-djmodel-tx-30-lstm-cell-lstm-cell-densor-densor-reshaper-reshaper/26378/5 "2021-10-25T19:28:13Z")
Had the same issue and a kernel restart worked for me as well ---
**Author:** ![ferdinando.randisi](https://avatars.discourse-cdn.com/v4/letter/f/71c47a/32.png) [@ferdinando.randisi](https://community.deeplearning.ai/u/ferdinando.randisi)\ **Post date:** [June 25, 2022, 6:40pm UTC](https://community.deeplearning.ai/t/c5w1a3-jazz-improvisation-update-issue-solved-error-at-model-djmodel-tx-30-lstm-cell-lstm-cell-densor-densor-reshaper-reshaper/26378/6 "2022-06-25T18:40:44Z")
Similar issue, but with a different error. My code looked exactly like the one above and worked correctly after a kernel restart ---
**Author:** ![anon57530071](https://avatars.discourse-cdn.com/v4/letter/a/46a35a/32.png) [@anon57530071](https://community.deeplearning.ai/u/anon57530071)\ **Post date:** [June 25, 2022, 6:51pm UTC](https://community.deeplearning.ai/t/c5w1a3-jazz-improvisation-update-issue-solved-error-at-model-djmodel-tx-30-lstm-cell-lstm-cell-densor-densor-reshaper-reshaper/26378/7 "2022-06-25T18:51:24Z")
Please see this [thread](https://community.deeplearning.ai/t/not-understanding-why-getting-this-error/141808). The problem is LSTM\_cell is defined as a global variable, and is easily broken during debugging. So, you need to reset LSTM\_cell like this if there is an error. > LSTM\_cell = LSTM(n\_a, return\_state = True) Of course, this resets trained weights as well. So, once you fix an error, it is better to re-run all cells. But, do not need to restart kernel everytime for debugging. ---
**Author:** ![Rashmi](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/rashmi/32/17812_2.png) [@Rashmi](https://community.deeplearning.ai/u/Rashmi)\ **Post date:** [June 29, 2022, 9:39am UTC](https://community.deeplearning.ai/t/c5w1a3-jazz-improvisation-update-issue-solved-error-at-model-djmodel-tx-30-lstm-cell-lstm-cell-densor-densor-reshaper-reshaper/26378/8 "2022-06-29T09:39:02Z")
Hi Rajeshm99, Posting the codes at this platform is a violation. If the query is resolved completely, kindly remove it. Thanks! ---
**Author:** ![rajeshm99](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/rajeshm99/32/5066_2.png) [@rajeshm99](https://community.deeplearning.ai/u/rajeshm99)\ **Post date:** [June 29, 2022, 2:41pm UTC](https://community.deeplearning.ai/t/c5w1a3-jazz-improvisation-update-issue-solved-error-at-model-djmodel-tx-30-lstm-cell-lstm-cell-densor-densor-reshaper-reshaper/26378/9 "2022-06-29T14:41:50Z")
Hi Rashmi, I’m unable to delete the code as I’m not able to edit the post. Thanks! ---
**Author:** ![Rashmi](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/rashmi/32/17812_2.png) [@Rashmi](https://community.deeplearning.ai/u/Rashmi)\ **Post date:** [June 30, 2022, 7:30am UTC](https://community.deeplearning.ai/t/c5w1a3-jazz-improvisation-update-issue-solved-error-at-model-djmodel-tx-30-lstm-cell-lstm-cell-densor-densor-reshaper-reshaper/26378/10 "2022-06-30T07:30:47Z")
Oh, yes. Even I’m not able to do so. I think it would be done by the moderator. ---
**Author:** ![TMosh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/tmosh/32/9321_2.png) [@TMosh](https://community.deeplearning.ai/u/TMosh)\ **Post date:** [October 8, 2022, 3:00am UTC](https://community.deeplearning.ai/t/c5w1a3-jazz-improvisation-update-issue-solved-error-at-model-djmodel-tx-30-lstm-cell-lstm-cell-densor-densor-reshaper-reshaper/26378/11 "2022-10-08T03:00:53Z")