I can't fit my data (it works on sklearn though).
I keep getting this
AttributeError: 'float' object has no attribute 'exp'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/home/negm/PycharmProjects/testa2/a2_1.py", line 47, in
nn_model.fit(x_train, y_train)
File "/home/negm/PycharmProjects/testa2/venv/lib/python3.6/site-packages/mlrose/neural.py", line 528, in fit
restarts=0, init_state=init_weights)
File "/home/negm/PycharmProjects/testa2/venv/lib/python3.6/site-packages/mlrose/algorithms.py", line 188, in random_hill_climb
problem.set_state(init_state)
File "/home/negm/PycharmProjects/testa2/venv/lib/python3.6/site-packages/mlrose/opt_probs.py", line 224, in set_state
self.fitness = self.eval_fitness(self.state)
File "/home/negm/PycharmProjects/testa2/venv/lib/python3.6/site-packages/mlrose/opt_probs.py", line 98, in eval_fitness
fitness = self.maximize*self.fitness_fn.evaluate(state)
File "/home/negm/PycharmProjects/testa2/venv/lib/python3.6/site-packages/mlrose/neural.py", line 290, in evaluate
self.y_pred = self.output_activation(outputs)
File "/home/negm/PycharmProjects/testa2/venv/lib/python3.6/site-packages/mlrose/activation.py", line 77, in sigmoid
fx = 1/(1 + np.exp(-x))
TypeError: loop of ufunc does not support argument 0 of type float which has no callable exp method`
The weird thing is i tried different activation functions, but it always maps back to 'sigmoid' !!
I'm not quite sure what is causing this issue. I haven't come across it before, but would be interested to hear if anyone else has and if they have found a way of solving it.
I can't fit my data (it works on sklearn though). I keep getting this
The weird thing is i tried different activation functions, but it always maps back to 'sigmoid' !!