Tarik Sahin

I added the print(self.callbacks.callbacks[0].value) but this command prints always the same value

@lululxvi thx for the reply. What about getting the results after each epoch? With adam it is possible. I could not figure it out how one can achieve that using...

I think I figured it out. I added step_callback function in `_train_tensorflow_compat_v1_scipy` from model.py ```python def step_callback(y): if self.train_state.step % display_every == 0: print(y[:len(self.external_trainable_variables)]) ``` This function prints out the...

This merge request includes the following changes: - If an external optimizer function (e.g. L-BFGS) is used, it was not outputting or writing the external trainable variables after each epoch...

@lululxvi I could not get why the tests could not pass? Is it because of formatting?

@lululxvi I could not comment on the file but for line 562 in model.py I have a comment. ```python . . . self.train_state.set_data_train(*self.data.train_next_batch(self.batch_size)) self.train_state.set_data_test(*self.data.test()) self._test() self.callbacks.on_train_begin() # Line 562 ....

I have another remark regarding on outputting of the loss values in case of an external optimizer is used. Fetches contain only the training loss so it does not include...

> > I have another remark regarding on outputting of the loss values in case of an external optimizer is used. Fetches contain only the training loss so it does...

@lululxvi I have implemented PointSetOperatorBC and tested for an example of solid mechanics. I will make a PR as soon as I have time!

time is your input, right? Then, define T_inf as a function of your input. Do not forget use tf functions if your backend is tf, such as tf.exp ...