def load_instances(sFilename, cMaxInstances=None):
return nn.load_data(data_filename(sFilename), cMaxInstances)
def load_data():
(x_train, y_train), (x_test, y_test) = nn.load_data()
x_train = np.divide(x_train, 255.)
x_test = np.divide(x_test, 255.)
return (x_train, y_train), (x_test, y_test)
def load_data():
(x_train, y_train), (x_test, y_test) = nn.load_data()
x_train = np.expand_dims(np.divide(x_train, 255.), -1)
x_test = np.expand_dims(np.divide(x_test, 255.), -1)
return (x_train, y_train), (x_test, y_test)
#!/usr/bin/python
import nn
n = nn.read_from_file('net.pic')
d = nn.load_data('test_img')
f0 = [nn.feed_forward(n, q.listDblFeatures)[0] for q in d if q.iLabel == 0]
f1 = [nn.feed_forward(n, q.listDblFeatures)[0] for q in d if q.iLabel == 1]
print >>open('d0', 'w'), '\n'.join(map(str, sorted(f0)))
print >>open('d1', 'w'), '\n'.join(map(str, sorted(f1)))
from nn import load_data
def slicer(arr, slice_size):
i = 0
assert arr.shape[0] >= slice_size
while True:
arr_slice = arr[i:i+slice_size, :]
if arr_slice.shape[0] < slice_size:
i = 0
continue
i += slice_size
yield arr_slice
X, Y, test = load_data()
sess = tf.Session()
x = tf.placeholder(tf.float32, [None, 784])
w = tf.Variable(tf.zeros([784, 10]))
y = tf.nn.softmax(tf.matmul(x, w))
y_ = tf.placeholder(tf.float32, [None, 10])
max_w_op = tf.reduce_max(w)
min_w_op = tf.reduce_min(w)
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
sq_err = tf.scalar_mul(1/2, tf.reduce_sum(tf.square(y - y_)))
def load_data():
(x_train, y_train), (x_test, y_test) = nn.load_data()
x_train = np.divide(x_train, 255.).reshape([-1, 784])
x_test = np.divide(x_test, 255.).reshape([-1, 784])
return (x_train, y_train), (x_test, y_test)
def load_instances(sFilename, cMaxInstances=None):
return nn.load_data(data_filename(sFilename), cMaxInstances)
#!/usr/bin/python
import nn
n = nn.read_from_file('net.pic')
d = nn.load_data('test_img')
f0 = [nn.feed_forward(n, q.listDblFeatures)[0] for q in d if q.iLabel == 0]
f1 = [nn.feed_forward(n, q.listDblFeatures)[0] for q in d if q.iLabel == 1]
print >> open('d0', 'w'), '\n'.join(map(str, sorted(f0)))
print >> open('d1', 'w'), '\n'.join(map(str, sorted(f1)))
