gregorlen / anfistensorflow2.0 Goto Github PK

Hello,

I have a problem with the training section, would you please guide me. in the below code I have got the error.

y_pred = fis.model.fit(X_train, y_train,
epochs=param.n_epochs,
batch_size=param.batch_size,
validation_data=(X_test, y_test),
callbacks=[tensorboard_callback])

Error:
InvalidArgumentError: Graph execution error:

Node: 'myanfis/ruleLayer/Reshape_1'
Input to reshape is a tensor with 104 values, but the requested shape requires a multiple of 16
[[{{node myanfis/ruleLayer/Reshape_1}}]] [Op:__inference_train_function_2861]

Thank you in advance

Hello,

I have a problem with the prediction section, would you please guide me. in the below code I have got the error.

y_pred = fis.model.predict(X_test)

Error:
InvalidArgumentError: Graph execution error:

Input to reshape is a tensor with 32 values, but the requested shape has 1
[[{{node myanfis/sumLayer/Reshape}}]] [Op:__inference_predict_function_68010]

Thank you in advance

Hello Gregor, i got this error while i'm trying to predict the result using fis.model.predict(X)

Input to reshape is a tensor with 32 values, but the requested shape has 1
[[{{node myanfis/sumLayer/Reshape}}]] [Op:__inference_predict_function_154498]

May i know why? And what should i do regarding this matter? Thank you!

Hello,

How to deal with multiple inputs using this anfis? I have 8 variables as the inputs to predict one output, but the run.py gives an error that is "This ANFIS implementation works with 2 to 6 inputs", so how to deal with this issue, please give some suggestions, thanks.

i have stock data and try to predict it with anfis, and I got problem in InvalidArgumentError: slice index 15 of dimension 0 out of bounds. [[{{node ruleLayer_2/strided_slice_15}}]] when fit the model, I have 900 row with 1 column for data training and 96 with 1 column in data test

Hi Gregor. I ran into error trying to make prediction on Mackey-Glass time series.

y_pred = fis(X)

I ran a code from examples and got:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-26-c4f5faf6ff99> in <module>()
     27 fis.model.summary()
     28 
---> 29 y_pred = fis(X)
     30 
     31 # f, axs = plt.subplots(2,1,figsize=(8,10))

2 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in autograph_handler(*args, **kwargs)
   1127           except Exception as e:  # pylint:disable=broad-except
   1128             if hasattr(e, "ag_error_metadata"):
-> 1129               raise e.ag_error_metadata.to_exception(e)
   1130             else:
   1131               raise

ValueError: in user code:

    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1621, in predict_function  *
        return step_function(self, iterator)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1611, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1604, in run_step  **
        outputs = model.predict_step(data)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 1572, in predict_step
        return self(x, training=False)
    File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler
        raise e.with_traceback(filtered_tb) from None

    ValueError: Exception encountered when calling layer "defuzzLayer" (type DefuzzyLayer).
    
    in user code:
    
        File "<ipython-input-16-5fe3aebfbcaa>", line 33, in call  *
            print(tf.multiply(w_norm, a + self.CP_bias))
    
        ValueError: Dimensions must be equal, but are 16 and 32 for '{{node myanfis/defuzzLayer/Mul}} = Mul[T=DT_FLOAT](myanfis/normLayer/truediv, myanfis/defuzzLayer/add)' with input shapes: [16,25], [32,25].
    
    
    Call arguments received:
      • w_norm=tf.Tensor(shape=(16, 25), dtype=float32)
      • Xs=tf.Tensor(shape=(32, 2), dtype=float32)

Cold you please help to solve that issue.
My Colab is here

Dear Gregor,

I hope this email finds you well, first of all, thank you so much for sharing your code on GitHub. I have a problem working with it. I have 3 inputs and 1 output, and it gives the below error:

`/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
53 ctx.ensure_initialized()
54 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 55 inputs, attrs, num_outputs)
56 except core._NotOkStatusException as e:
57 if name is not None:

Incompatible shapes: [16,1] vs. [15,1]`

I found that 16 is my batch size and when I change it, this number changes.

(I found a solution and the solution is batch_size=1) which is SGD

Thank you in advance

Kind regards

Hamed

We can predict the data we have. So how do we predict for the future?