the bool to tensor has a bug, if in init the training is False, the program not start.

fix: Fix the problem where the  model.save_weights() can't save multi-layer weight

fix: inconsistent shape error while training embedding layer

I added `ToArray()` so that there is no "The collection has changed" error after `_delete_tracking`.

refactor: Standardize TensorFlowNET.Keras/Losses/*

fix: type converting errors when loading imdb dataset

feat: Support training of RNN and LSTM.

Fix my bad:

Bad handling between test_function and test_step_multi_inputs_function.

IModel.Dictionary<string, float> evaluate(NDArray, NDArray, ...) is now IModel.Dictionary<string, float> evaluate(Tensor, Tensor, ...)
Merge Model.Evaluate.test_step_multi_inputs_function(...) and Model.Evaluate.test_function(...)

Note: An internal function need to add an explicit cast in Tensor