A description of what you tried .
In the following, I tried to access the best model via a dictionary (as suggested here by the poster of the same issue):
First, I ran Analyze with the scan_object to find the round w/ best result using rounds2high. Say we store the best model number into model_no:
analyze_object_rh = talos.Analyze(scan_object)
model_no = analyze_object_rh.rounds2high('out.reg.vae_func_correlation_coefficient')# get the round with the best result
Then I tried the following, but it failed:
ruh_best_model = talos.utils.best_model.activate_model({scan_object,{'myCsutomLayer': myCsutomLayer}} , model_no)
due to sytaxterr:
(after all, how should I know which model is the best to choose the corresponding .csv file in the ?! Here I randomly chose 012621170617.csv just to see if this workaround works, but it failed anyways)
Well, here is my model.compile() (it is a multi-task learning model)
2) Include the output of:
talos.__version__
1.0.03) Explain clearly what you expect to happen
I have the same problem as here.
A description of what you tried . In the following, I tried to access the best model via a dictionary (as suggested here by the poster of the same issue):
First, I ran
Analyze
with thescan_object
to find the round w/ best result usingrounds2high
. Say we store the best model number intomodel_no
:Then I tried the following, but it failed:
ruh_best_model = talos.utils.best_model.activate_model({scan_object,{'myCsutomLayer': myCsutomLayer}} , model_no)
due tosytaxterr
:SyntaxError: positional argument follows keyword argument
So, then I tired another workaround suggested by the talos developer here:
It also did fail with the following err:
KeyError: 'val_acc'
(after all, how should I know which model is the best to choose the corresponding
.csv
file in the ?! Here I randomly chose012621170617.csv
just to see if this workaround works, but it failed anyways)Well, here is my
model.compile()
(it is a multi-task learning model)