from common_func import *
from es_net import *
from es_nn_layer import *
from mnist import load_mnist
if __name__=='__main__':
(train_data, train_label), (test_data, test_label) = load_mnist(flatten=False)
scale=0.01
image_size = 28 * 28
hidden_nodes = 100
output_nodes = 10
input_dim = (1, 28, 28)
update_class = Momentum
# random init the dnn param
dnn = es_net()
# Conv layer
filter_num = 30
filter_size = 5
filter_pad = 0
filter_stride = 1
input_size = input_dim[1]
conv_output_size = (input_size - filter_size + 2*filter_pad) / filter_stride + 1
pool_output_size = int(filter_num * (conv_output_size/2) * (conv_output_size/2))
scale = weight_init_scale(input_size=28*28, active_func='relu')
dnn_weight_arr = scale * \
np.random.randn(filter_num, input_dim[0], filter_size, filter_size)
dnn_bias_arr = np.zeros(filter_num)
updater_obj = update_class(learning_rate=0.1)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import sys, os
import pickle
import numpy as np
import matplotlib.pyplot as plt
from active_func import *
from common_func import *
from es_net import *
from mnist import load_mnist
if __name__ == '__main__':
(train_data, train_label), (test_data, test_label) = load_mnist()
with open("sample_weight.pkl", 'rb') as f:
nn_param = pickle.load(f)
accuracy_cnt = 0
dnn = es_net(layers=3, active_func=sigmoid, out_func=softmax)
dnn.setup_nn_param(0, weight_arr=nn_param['W1'], bias_arr=nn_param['b1'])
dnn.setup_nn_param(1, weight_arr=nn_param['W2'], bias_arr=nn_param['b2'])
dnn.setup_nn_param(2, weight_arr=nn_param['W3'], bias_arr=nn_param['b3'])
batch_size = 100
for i in range(0, len(test_data), batch_size):
y_batch = dnn.forward_inference(test_data[i:i + batch_size])
result_batch = np.argmax(y_batch, axis=1)
accuracy_cnt += np.sum(result_batch == test_label[i:i + batch_size])
print("Final Accuracy: " + str(float(accuracy_cnt) / len(test_data)))
import numpy as np
import matplotlib.pyplot as plt
from active_func import *
from common_func import *
from es_net import *
from mnist import load_mnist
if __name__ == '__main__':
(train_data, train_label), (test_data, test_label) = load_mnist()
weight_init_std = 0.01
image_size = 28 * 28
hidden_nodes = 30
output_nodes = 10
# random init the dnn param
dnn = es_net(layers=2, active_func=ReLU, out_func=softmax)
dnn_weight_arr = weight_init_std * np.random.randn(image_size,
hidden_nodes)
dnn_bias_arr = np.zeros(hidden_nodes)
dnn.setup_nn_param(0, weight_arr=dnn_weight_arr, bias_arr=dnn_bias_arr)
dnn_weight_arr = weight_init_std * np.random.randn(hidden_nodes,
output_nodes)
dnn_bias_arr = np.zeros(output_nodes)
dnn.setup_nn_param(1, weight_arr=dnn_weight_arr, bias_arr=dnn_bias_arr)
train_data_num = train_data.shape[0]
batch_size = 100
iter_per_epoch = max(train_data_num / batch_size, 1)
training_iters = 1001
hidden_nodes = 100
output_nodes = 10
input_dim = (1, 28, 28)
# conv param
filter_num = 30
filter_size = 5
filter_pad = 0
filter_stride = 1
input_size = input_dim[1]
conv_output_size = (input_size - filter_size + 2*filter_pad) / filter_stride + 1
pool_output_size = int(filter_num * (conv_output_size/2) * (conv_output_size/2))
# cnn use SGD
cnn_default = es_net()
update_class = SGD
# Conv layer
scale = weight_init_scale(input_size=28*28, active_func='default')
dnn_weight_arr = scale * \
np.random.randn(filter_num, input_dim[0], filter_size, filter_size)
dnn_bias_arr = np.zeros(filter_num)
updater_obj = update_class(learning_rate=0.1)
layer_tmp = conv_layer(dnn_weight_arr, dnn_bias_arr, filter_stride, \
filter_pad, updater=updater_obj)
cnn_default.add_layer(layer_obj=layer_tmp)
# ReLU layer
layer_tmp = ReLU_layer()
cnn_default.add_layer(layer_obj=layer_tmp)
hidden_nodes = 100
output_nodes = 10
input_dim = (1, 28, 28)
# conv param
filter_num = 30
filter_size = 5
filter_pad = 0
filter_stride = 1
input_size = input_dim[1]
conv_output_size = (input_size - filter_size + 2*filter_pad) / filter_stride + 1
pool_output_size = int(filter_num * (conv_output_size/2) * (conv_output_size/2))
# cnn use SGD
cnn_sgd = es_net()
update_class = SGD
# Conv layer
dnn_weight_arr = weight_init_std * \
np.random.randn(filter_num, input_dim[0], filter_size, filter_size)
dnn_bias_arr = np.zeros(filter_num)
updater_obj = update_class(learning_rate=0.1)
layer_tmp = conv_layer(dnn_weight_arr, dnn_bias_arr, filter_stride, \
filter_pad, updater=updater_obj)
cnn_sgd.add_layer(layer_obj=layer_tmp)
# ReLU layer
layer_tmp = ReLU_layer()
cnn_sgd.add_layer(layer_obj=layer_tmp)