使用深度学习检测疟疾

我们修复我们的图像尺寸、批量大小，和纪元，并编码我们的分类的类标签。TensorFlow 2.0 于 2019 年三月发布，这个练习是尝试它的完美理由。

import tensorflow as tf
 
# Load the TensorBoard notebook extension (optional)
%load_ext tensorboard.notebook
 
tf.random.set_seed(42)
tf.__version__
 
# Output
'2.0.0-alpha0'

深度学习训练

在模型训练阶段，我们将构建三个深度训练模型，使用我们的训练集训练，使用验证数据比较它们的性能。然后，我们保存这些模型并在之后的模型评估阶段使用它们。

模型 1：从头开始的 CNN

我们的第一个疟疾检测模型将从头开始构建和训练一个基础的 CNN。首先，让我们定义我们的模型架构，

inp = tf.keras.layers.Input(shape=INPUT_SHAPE)
 
conv1 = tf.keras.layers.Conv2D(32, kernel_size=(3, 3), 
                               activation='relu', padding='same')(inp)
pool1 = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(conv1)
conv2 = tf.keras.layers.Conv2D(64, kernel_size=(3, 3), 
                               activation='relu', padding='same')(pool1)
pool2 = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(conv2)
conv3 = tf.keras.layers.Conv2D(128, kernel_size=(3, 3), 
                               activation='relu', padding='same')(pool2)
pool3 = tf.keras.layers.MaxPooling2D(pool_size=(2, 2))(conv3)
 
flat = tf.keras.layers.Flatten()(pool3)
 
hidden1 = tf.keras.layers.Dense(512, activation='relu')(flat)
drop1 = tf.keras.layers.Dropout(rate=0.3)(hidden1)
hidden2 = tf.keras.layers.Dense(512, activation='relu')(drop1)
drop2 = tf.keras.layers.Dropout(rate=0.3)(hidden2)
 
out = tf.keras.layers.Dense(1, activation='sigmoid')(drop2)
 
model = tf.keras.Model(inputs=inp, outputs=out)
model.compile(optimizer='adam',
                loss='binary_crossentropy',
                metrics=['accuracy'])
model.summary()
 
 
# Output
Model: "model"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, 125, 125, 3)]     0         
_________________________________________________________________
conv2d (Conv2D)              (None, 125, 125, 32)      896       
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 62, 62, 32)        0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 62, 62, 64)        18496     
_________________________________________________________________
...
...
_________________________________________________________________
dense_1 (Dense)              (None, 512)               262656    
_________________________________________________________________
dropout_1 (Dropout)          (None, 512)               0         
_________________________________________________________________
dense_2 (Dense)              (None, 1)                 513       
=================================================================
Total params: 15,102,529
Trainable params: 15,102,529
Non-trainable params: 0
_________________________________________________________________

（编辑：核心网）

【声明】本站内容均来自网络，其相关言论仅代表作者个人观点，不代表本站立场。若无意侵犯到您的权利，请及时与联系站长删除相关内容!