Error in tutorial - max_steps_per_epoch

[CurlsForScience]

Hello,

I believe there is an error in the tutorial Tutorial_for_iedb_dataset.ipynb. For the following command, I believe "steps_per_epoch" should be "max_steps_per_epoch" according to the source code.

ffn.train(
epochs=1,
steps_per_epoch=1,
batch_size=8
)

Additionally, when going through the tutorial, I get an error on the following command.

print(ffn.model.summary())
AttributeError: 'ModelSa' object has no attribute 'summary'

I also get an error with the following command.
ffn2.load_model(fn_tmp)
Traceback (most recent call last):
File "", line 1, in
TypeError: load_model() missing 1 required positional argument: 'fn_model'

I believe this error arises since load_model requires two arguments, fn_settings and fn_model. I was able to work around this error using save_model_full and specifying save_train_data=True. If I do not specify save_train_data=True, errors arise regarding the x_train.shape which is not saved otherwise. Then I used load_model_full instead of load_model. However, the ffn2.evaluate() takes a very long time after this.

I appreciate any help you can give me on troubleshooting these errors.

[davidsebfischer]

Thanks for the issue!

I believe there is an error in the tutorial Tutorial_for_iedb_dataset.ipynb. For the following command, I believe "steps_per_epoch" should be "max_steps_per_epoch" according to the source code.

That sounds reasonable.

Additionally, when going through the tutorial, I get an error on the following command.

print(ffn.model.summary())
AttributeError: 'ModelSa' object has no attribute 'summary'

Looks like a error in the tutorial indeed, you want this summary, check out the keras model instance ModelSa.training_model

tcellmatch/tcellmatch/models/models_ffn.py

Line 325 in ddd344e

self.training_model = tf.keras.models.Model(

I also get an error with the following command.
ffn2.load_model(fn_tmp)
Traceback (most recent call last):
File "", line 1, in
TypeError: load_model() missing 1 required positional argument: 'fn_model'

I believe this error arises since load_model requires two arguments, fn_settings and fn_model. I was able to work around this error using save_model_full and specifying save_train_data=True. If I do not specify save_train_data=True, errors arise regarding the x_train.shape which is not saved otherwise. Then I used load_model_full instead of load_model. However, the ffn2.evaluate() takes a very long time after this.

Indeed!

tcellmatch/tcellmatch/estimators/estimator_ffn.py

Line 1437 in ddd344e

def load_model(

takes the hyperparameter file and the weight file.
I think you could do sth like

• save weights

  tcellmatch/tcellmatch/estimators/estimator_ffn.py

  Line 1490 in ddd344e

  def initialise_model_from_settings(self):

• save model settings

  tcellmatch/tcellmatch/estimators/estimator_ffn.py

  Line 1453 in ddd344e

  def save_estimator_args(

  
  new instance:
• load model

  tcellmatch/tcellmatch/estimators/estimator_ffn.py

  Line 1490 in ddd344e

  def initialise_model_from_settings(self):

  
  which is (if you look into that permalink:
• load model settings

  tcellmatch/tcellmatch/estimators/estimator_ffn.py

  Line 1473 in ddd344e

  def load_model_settings(

• init model from settings

  tcellmatch/tcellmatch/estimators/estimator_ffn.py

  Line 1490 in ddd344e

  def initialise_model_from_settings(self):

You dont need to reload data to reuse a model, you can of course. if evaluate takes long it just means that your data or model is big for your hardware.