def show_bias(self):
if len(self.weights) is 1:
mp = myplot.MyPlot()
mp.set_labels('Step', 'Bias')
mp.show_list(self.biases)
else:
print('Cannot show the bias! Call print_bias mehtod.')
def show_weight(self):
print('shape=', self.weights)
if len(self.weights[0]) is 1:
mp = myplot.MyPlot()
mp.set_labels('Step', 'Weight')
mp.show_list(self.weights)
else:
print('Cannot show the weight! Call print_weight method.')
# Get a image randomly and classify
r = random.randint(0, mnist.test.num_examples - 1)
print("Label: ", sess.run(tf.argmax(mnist.test.labels[r:r + 1], 1)))
print(
"Prediction: ",
sess.run(tf.argmax(logits, 1), feed_dict={X: mnist.test.images[r:r + 1]}))
import matplotlib.pyplot as plt
plt.imshow(mnist.test.images[r:r + 1].reshape(28, 28),
cmap='Greys',
interpolation='nearest')
plt.show()
import myplot
guy = myplot.MyPlot()
guy.set_labels('Epoch', 'Error')
guy.show_list(error_list)
'''
Epoch: 0001 cost = 141.207671860
Epoch: 0002 cost = 38.788445864
Epoch: 0003 cost = 23.977515479
Epoch: 0004 cost = 16.315132428
Epoch: 0005 cost = 11.702554882
Epoch: 0006 cost = 8.573139748
Epoch: 0007 cost = 6.370995680
Epoch: 0008 cost = 4.537178684
Epoch: 0009 cost = 3.216900532
Epoch: 0010 cost = 2.329708954
Epoch: 0011 cost = 1.715552875
Epoch: 0012 cost = 1.189857912
def show_error(self):
mp = myplot.MyPlot()
mp.set_labels('Step', 'Error')
mp.show_list(self.costs)
def show_bias(self):
mp = myplot.MyPlot()
mp.set_labels('Step', 'Bias')
mp.show_list(self.biases)
def show_weight(self):
mp = myplot.MyPlot()
mp.set_labels('Step', 'Weight')
mp.show_list(self.weights)
# sampling rate Ts = 1.0 / Fs # sampling interval t = np.arange(0, 1, Ts) # time vector freq1 = 5 # frequency of the signal freq2 = 10 # frequency of the signal freq3 = 20 wave1 = np.sin(2 * np.pi * freq1 * t) wave2 = np.sin(2 * np.pi * freq2 * t) wave3 = np.sin(2 * np.pi * freq3 * t) signal = wave1 + wave2 + wave3 mplot1 = myplot.MyPlot() mplot1.crossplot(t, signal) n = len(signal) # length of the signal k = np.arange(n) T = n / Fs frq = k / T # two sides frequency range frq = frq[range(n // 2)] # one side frequency range fftsignal = np.fft.fft(signal) / n # fft computing and normalization fftsignal = fftsignal[range(n // 2)] mplot2 = myplot.MyPlot() mplot2.crossplot(frq, abs(fftsignal))