tensorflow2搭建squeezenet

原创

已于 2023-04-10 13:44:38 修改 · 485 阅读

1 ·

CC 4.0 BY-SA版权

文章标签：

#深度学习 #机器学习 #人工智能 #python #tensorflow

于 2023-03-09 23:00:41 首次发布

该文展示了如何用TensorFlow构建SqueezeNet卷积神经网络模型，并详细描述了数据预处理、训练集和测试集的构建过程。模型在特定数据集上进行训练，测试集准确率约为72%-79%。

model

import numpy as np
import tensorflow as tf
NUM_CLASSES = 10

class FireModule(tf.keras.layers.Layer):
    def __init__(self, s1, e1, e3):
        super(FireModule, self).__init__()
        self.squeeze_layer = tf.keras.layers.Conv2D(filters=s1,
                                                    kernel_size=(1, 1),
                                                    strides=1,
                                                    padding="same")
        self.expand_1x1 = tf.keras.layers.Conv2D(filters=e1,
                                                 kernel_size=(1, 1),
                                                 strides=1,
                                                 padding="same")
        self.expand_3x3 = tf.keras.layers.Conv2D(filters=e3,
                                                 kernel_size=(3, 3),
                                                 strides=1,
                                                 padding="same")

    def call(self, inputs, **kwargs):
        x = self.squeeze_layer(inputs)
        x = tf.nn.relu(x)
        y1 = self.expand_1x1(x)
        y1 = tf.nn.relu(y1)
        y2 = self.expand_3x3(x)
        y2 = tf.nn.relu(y2)
        return tf.concat(values=[y1, y2], axis=-1)


class SqueezeNet(tf.keras.Model):
    def __init__(self):
        super(SqueezeNet, self).__init__()
        self.conv1 = tf.keras.layers.Conv2D(filters=96,
                                            kernel_size=(7, 7),
                                            strides=2,
                                            padding="same")
        self.maxpool1 = tf.keras.layers.MaxPool2D(pool_size=(3, 3),
                                                  strides=2)
        self.fire2 = FireModule(s1=16, e1=64, e3=64)
        self.fire3 = FireModule(s1=16