DL之CNN：基于mnist手写数字识别数据集利用DeepConvNet(自定义的深度卷积神经网络【7+1】)模型训练、模型评估、模型预测(从99%→99.4%)

DL之CNN：基于mnist手写数字识别数据集利用DeepConvNet(自定义的深度卷积神经网络【7+1】)模型训练、模型评估、模型预测(从99%→99.4%)

目录

利用自定义DeepConvNet【7+1】算法对mnist数据集训练实现手写数字识别并预测(超过99%)

输出结果

设计思路

核心代码

利用自定义DeepConvNet【7+1】算法对mnist数据集训练实现手写数字识别、模型评估(99.4%)

输出结果

设计思路

核心代码

---

利用自定义DeepConvNet【7+1】算法对mnist数据集训练实现手写数字识别并预测(超过99%)

输出结果

准确度都在99%以上

1、出错记录

col = np.zeros((N, C, filter_h, filter_w, out_h, out_w))
MemoryError

设计思路

1、网络结构

2、总体框架

核心代码

class DeepConvNet:

    def __init__(self, input_dim=(1, 28, 28),
                 conv_param_1 = {'filter_num':16, 'filter_size':3, 'pad':1, 'stride':1},
                 conv_param_2 = {'filter_num':16, 'filter_size':3, 'pad':1, 'stride':1},
                 conv_param_3 = {'filter_num':32, 'filter_size':3, 'pad':1, 'stride':1},
                 conv_param_4 = {'filter_num':32, 'filter_size':3, 'pad':2, 'stride':1},
                 conv_param_5 = {'filter_num':64, 'filter_size':3, 'pad':1, 'stride':1},
                 conv_param_6 = {'filter_num':64, 'filter_size':3, 'pad':1, 'stride':1},
                 hidden_size=50, output_size=10):
        # 初始化权重===========
            ……


    def predict(self, x, train_flg=False):
            ……


    def loss(self, x, t):    
            ……


        return acc / x.shape[0]

    def gradient(self, x, t):
        # forward
        self.loss(x, t)

        # backward
            ……


        return grads

    def save_params(self, file_name="params.pkl"):
            ……

    def load_params(self, file_name="params.pkl"):
            ……


        for i, layer_idx in enumerate((0, 2, 5, 7, 10, 12, 15, 18)):
            self.layers[layer_idx].W = self.params['W' + str(i+1)]
            self.layers[layer_idx].b = self.params['b' + str(i+1)]

利用自定义DeepConvNet【7+1】算法对mnist数据集训练实现手写数字识别、模型评估(99.4%)

输出结果

设计思路

核心代码

network = DeepConvNet()                         


network.load_params("data_input/DeepConvNet/deep_convnet_params.pkl")   

#T1、caluculate accuracy(float64)
print("DeepConvNet【7+1】 on mnist：caluculate accuracy (float64 type) ... ")
print(network.accuracy(x_test, t_test))          #caluculate accuracy(float64)


#T2、caluculate accuracy(float16)
x_test = x_test.astype(np.float16)        
for param in network.params.values():     
    param[...] = param.astype(np.float16)

print("DeepConvNet【7+1】 on mnist：caluculate accuracy (float16 type) ... ")
print(network.accuracy(x_test, t_test))