Tensorflow 2.0 [condition X == Y Did Not Hold Element-wise:]

I am training a chess program using TensorFlow 2 and Keras. Previously, I had this working if I loaded the data in the same script as the training of the model, but as the dataset

Solution 1:

The Dense layer expects the flattened data.

Try:

   tf.keras.layers.Flatten() 

before calling the dense layer.

Solution 2:

The problem is that your loss functions receives 2 tensors with different shapes

[Condition x == y did not hold element-wise:] [x (loss/output_1_loss/SparseSoftmaxCrossEntropyWithLogits/Shape_1:0) = ] [32 1] [y (loss/output_1_loss/SparseSoftmaxCrossEntropyWithLogits/strided_slice:0) = ] [32 8]

So one of inputs has shape [32, 1] and other is [32, 8], but loss function requires input shape to be equal. As I understood, you have 8 classes, so you need your model output to be [32, 8]. Replace units=600 by units=8 in

tf.keras.layers.Dense(activation='relu', units=600)

or add other layers to have the output shape (batch_size, 8)

Solution 3:

I had this error message also when x-values were out of the range (0,1)