aqibsaeed/genetic-algorithm-rnn

Using Genetic Algorithms to optimize Recurrent Neural Network's Configuration

genetic-algorithm-rnn's Issues

stop at "r = algorithms.eaSimple()"

Traceback (most recent call last):
File "run.py", line 79, in
r = algorithms.eaSimple(population, toolbox, cxpb = 0.4, mutpb = 0.1, ngen = num_generations, verbose = False)
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/deap/algorithms.py", line 152, in eaSimple
ind.fitness.values = fit
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/deap/base.py", line 185, in setValues
self.wvalues = tuple(map(mul, values, self.weights))
TypeError: Both weights and assigned values must be a sequence of numbers when assigning to values of <class 'deap.creator.FitnessMax'>. Currently assigning value(s) 0.076375786869707959 of <type 'numpy.float64'> to a fitness with weights (-1.0,).

Can you provide a dataset?

Error in this line ```r = algorithms.eaSimple(population, toolbox, cxpb = 0.4, mutpb = 0.1, ngen = num_generations, verbose = False)``` while implementation in colab.

/usr/local/lib/python3.7/dist-packages/deap/creator.py:141: RuntimeWarning: A class named 'FitnessMax' has already been created and it will be overwritten. Consider deleting previous creation of that class or rename it.
RuntimeWarning)
/usr/local/lib/python3.7/dist-packages/deap/creator.py:141: RuntimeWarning: A class named 'Individual' has already been created and it will be overwritten. Consider deleting previous creation of that class or rename it.
RuntimeWarning)

Window Size: 56 , Num of Units: 7
Epoch 1/5

UnimplementedError Traceback (most recent call last)
in ()
19
20 population = toolbox.population(n = population_size)
---> 21 r = algorithms.eaSimple(population, toolbox, cxpb = 0.4, mutpb = 0.1, ngen = num_generations, verbose = False)

8 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
58 ctx.ensure_initialized()
59 tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
---> 60 inputs, attrs, num_outputs)
61 except core._NotOkStatusException as e:
62 if name is not None:

UnimplementedError: Cast string to float is not supported
[[node model_3/Cast (defined at :32) ]] [Op:__inference_train_function_4464]

Function call stack:
train_function****

stop at "r = algorithms.eaSimple()"

Traceback (most recent call last):
File "run.py", line 79, in
r = algorithms.eaSimple(population, toolbox, cxpb = 0.4, mutpb = 0.1, ngen = num_generations, verbose = False)
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/deap/algorithms.py", line 152, in eaSimple
ind.fitness.values = fit
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/deap/base.py", line 185, in setValues
self.wvalues = tuple(map(mul, values, self.weights))
TypeError: Both weights and assigned values must be a sequence of numbers when assigning to values of <class 'deap.creator.FitnessMax'>. Currently assigning value(s) 0.076375786869707959 of <type 'numpy.float64'> to a fitness with weights (-1.0,).