this is my first deep neural network and I have a problem in this code while implementing it. beside the error the code is slow and it is another thing.
Here is the code:
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD, Adam
from sklearn.datasets import make_moons
from sklearn.model_selection import train_test_split
x, y = make_moons(n_samples=1000, noise=0.1, random_state=0)
plt.plot(x[y == 0, 0], x[y == 0, 1], 'ob', alpha=0.5)
plt.plot(x[y == 1, 0], x[y == 1, 1], 'xr', alpha=0.5)
plt.legend(['0', '1'])
plt.show()
print(x.shape)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=.3, random_state=42)
model = Sequential
model.add(Dense(1, input_shape=(2,), activation='sigmoid'))
model.compile(Adam(lr=0.5), 'binary_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train,epochs=200, verbose=0)
results = model.evaluate(x_test, y_test)
print('The Accuracy score on the Train set is:\t{:0.3f}'.format(results[1]))
Here is the error
> Using TensorFlow backend. 2017-11-24 17:03:32.402292: W
> C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but
> these are available on your machine and could speed up CPU
> computations. 2017-11-24 17:03:32.402768: W
> C:\tf_jenkins\home\workspace\rel-win\M\windows\PY\36\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but
> these are available on your machine and could speed up CPU
> computations. (1000, 2) Traceback (most recent call last): File
> "E:/Tutorial/Deep Learning.py", line 18, in <module>
> model.add(Dense(1, input_shape=(2,), activation='sigmoid')) TypeError: add() missing 1 required positional argument: 'layer'
You are missing parentheses after Sequential:
model = Sequential()
If you want to compile tensorflow to make use of special x86 instructions such as AVX then see How to compile Tensorflow with SSE4.2 and AVX instructions? but this might be more effort than it is worth.