import tensor.Variable as var
import tensor.Operator as op
from layers.base_conv import Conv2D
from layers.pooling import MaxPooling
from layers.fc import FullyConnect
from layers.relu import Relu
from layers.softmax import Softmax
import cv2
import numpy as np
img = cv2.imread('layers/test.jpg')
img = img[np.newaxis, :]
a = var.Variable((1, 128, 128, 3), 'a')
label = var.Variable([1, 1], 'label')
import random
label.data = np.array([random.randint(1, 9)])
label.data = label.data.astype(int)
conv1_out = op.Conv2D((3, 3, 3, 3),
input_variable=a,
name='conv1',
padding='VALID').output_variables
relu1_out = op.Relu(input_variable=conv1_out, name='relu1').output_variables
pool1_out = op.MaxPooling(ksize=2, input_variable=relu1_out,
name='pool1').output_variables
fc1_out = op.FullyConnect(output_num=10, input_variable=pool1_out,
name='fc1').output_variables
sf_out = op.SoftmaxLoss(predict=fc1_out, label=label, name='sf').loss
#dropout2_out = op.DropOut(input_variable=relu2_out, name='dropout2', phase='train', prob=0.7).output_variables
pool2_out = op.MaxPooling(input_variable=relu1_out, ksize=2, name='pool2').output_variables
fc_out = op.FullyConnect(input_variable=pool2_out, output_num=output_num, name='fc').output_variables
return fc_out
batch_size = 64
global_step = 0
# set method
for k in var.GLOBAL_VARIABLE_SCOPE:
s = var.GLOBAL_VARIABLE_SCOPE[k]
if isinstance(s, var.Variable) and s.learnable:
s.set_method_adam()
img_placeholder = var.Variable((batch_size, 28, 28, 1), 'input')
label_placeholder = var.Variable([batch_size, 1], 'label')
# set train_op
prediction = inference(img_placeholder, 10)
sf = op.SoftmaxLoss(prediction, label_placeholder, 'sf')
images, labels = load_mnist('./data/mnist')
test_images, test_labels = load_mnist('./data/mnist', 't10k')
# save train curve config
loss_collect = []
acc_collect = []
print ('new')
with open('logs/%s_log.txt'%VERSION, 'wb') as logf:
import tensor.Operator as op
# from layers.base_conv import Conv2D
# from layers.pooling import MaxPooling
# from layers.fc import FullyConnect
# from layers.relu import Relu
# from layers.softmax import Softmax
# import cv2
import numpy as np
# img = cv2.imread('layers/test.jpg')
# img = img[np.newaxis, :]
e=1e-3
a = var.Variable((1, 128, 128, 3), 'a')
b = var.Variable((1, 128, 128, 3), 'b')
b.data = a.data.copy()
a.data[0,0,0,1] += e
b.data[0,0,0,1] -= e
# label = var.Variable([1, 1], 'label')
# import random
# label.data = np.array([random.randint(1,9)])
# label.data = label.data.astype(int)
import numpy as np
conv1_out = op.Conv2D((3, 3, 3, 3), input_variable=a, name='conv1',padding='VALID').output_variables
conv2_out = op.Conv2D((3, 3, 3, 3), input_variable=b, name='conv2',padding='VALID').output_variables
from tensor import Graph, Variable, placeholder, Session
from tensor.Activation import sigmoid, softmax
if __name__ == '__main__':
from base_tests import add, matmul
# 创建一个新 graph
Graph().as_default()
x = placeholder()
w = Variable([1, 1])
b = Variable(0)
p = sigmoid(add(matmul(w, x), b))
session = Session()
print(session.run(p, {x: [3, 2]}))
# softmax
# 创建一些集中于 (-2, -2) 的红点
red_points = np.random.randn(50, 2) - 2 * np.ones((50, 2))
# 创建一些集中于 (2, 2) 的蓝点
blue_points = np.random.randn(50, 2) + 2 * np.ones((50, 2))
# 创建一个新 graph
Graph().as_default()
X = placeholder()
# 为两种输出类别创建一个权矩阵:
# 蓝色的权向量是 (1, 1) ，红色是 (-1, -1)
W = Variable([[1, -1], [1, -1]])
Args:
a_value: First matrix value
b_value: Second matrix value
"""
return a_value.dot(b_value)
if __name__ == '__main__':
# Create a new graph
Graph().as_default()
# graph_init()
print(get_default())
# Create variables
A = Variable([[1, 0], [0, -1]])
b = Variable([1, 1])
# Create placeholder
x = placeholder()
# Create hidden node y
y = matmul(A, x)
# Create output node z
z = add(y, b)
session = Session()
output = session.run(z, {
x: [1, 2]
})
import tensor.Operator as op
import tensor.Variable as var
import tensor.Activation as activation
import numpy as np
### grad_check
e = 1e-3
a = var.Variable((1, 28, 28, 3), 'a')
b = var.Variable((1, 28, 28, 3), 'b')
c = var.Variable((1, 28, 28, 3), 'c')
b.data = a.data.copy()
c.data = a.data.copy()
a.data += e
b.data -= e
## conv2d
conv1_out = op.Conv2D(a, (3, 3, 3, 3), name='conv1', stride=1,
padding=1).output_variables
conv2_out = op.Conv2D(b, (3, 3, 3, 3), name='conv2', stride=1,
padding=1).output_variables
conv3_out = op.Conv2D(c, (3, 3, 3, 3), name='conv3', stride=1,
padding=1).output_variables
conv1 = var.GLOBAL_VARIABLE_SCOPE['conv1']
conv2 = var.GLOBAL_VARIABLE_SCOPE['conv2']
conv3 = var.GLOBAL_VARIABLE_SCOPE['conv3']
var.GLOBAL_VARIABLE_SCOPE['conv1'].weights.data = var.GLOBAL_VARIABLE_SCOPE[
'conv2'].weights.data
var.GLOBAL_VARIABLE_SCOPE['conv1'].bias.data = var.GLOBAL_VARIABLE_SCOPE[