It's about a question related to LSTM

TensorFlow General Discussion
1

I met with this question at StackOverflow please help out.
[python - Im trying to improve one hot encode to the input of a LSTM Neural Network and i get errors about the shape of the input array - Stack Overflow]
I also want to know the cause of error

4

Hi @gajna_selvi ,

This error occurs because the LSTM layer in TensorFlow model expects a 3-dimensional input, but it’s receiving a 2-dimensional input.

  • The model is expecting input with shape (None, 100, 57):
  • None: represents the batch size (can be any number)
  • 100: represents the time steps or sequence length
  • 57: represents the number of features at each time step
  • However, the input data being provided has shape (None, 57):
  • It’s missing the middle dimension (100) that represents the time steps

you need to reshape your input data to match the expected input shape of the LSTM layer. If your data isn’t naturally in this format,

For example, if X is your input data, you might need to reshape it like this:

X = X.reshape((X.shape[0], 100, 57))

Hope this Resolve the Issue ,

Thank You .