python - Tensorflow：tflite 模型和输出数组的不兼容形状

Question

我正在遵循一个非常基本的 tf.keras 教程来构建二进制图像分类器。然后我将完成的模型转换为 .tflite 文件，我正试图将其合并到一个 android 应用程序中。

创建顺序 tf.keras 模型的代码。

import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D
from tensorflow.keras.layers import Activation, Dropout, Flatten, Dense
from tensorflow.keras import backend as K
from tensorflow.keras.callbacks import TensorBoard, ReduceLROnPlateau
from sklearn.utils import class_weight
import numpy as np


# dimensions of our images.====================================================================================================
img_width, img_height = 200, 200

train_data_dir = 'augmentedImg/200/training_data'#=============================================================================
validation_data_dir = 'augmentedImg/200/validation_data'#=============================================================================
nb_train_samples = 9009
nb_validation_samples = 2252
epochs = 100
batch_size = 32

layer_size = 64

if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)

model = Sequential()
model.add(Conv2D(layer_size, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(layer_size, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(layer_size, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(layer_size, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())

#model.add(Dropout(0.5))

model.add(Dense(1))
model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    rotation_range=90,
    width_shift_range=0.1,
    height_shift_range=0.1,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True
    )

test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    color_mode='grayscale',
    batch_size=batch_size,
    class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    color_mode='grayscale',
    batch_size=batch_size,
    class_mode='binary')

class_weights = class_weight.compute_class_weight(
               'balanced',
                np.unique(train_generator.classes), 
                train_generator.classes)

model.fit_generator(
    train_generator,
    class_weight=class_weights,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples# // batch_size,
    #callbacks=[tensorboard, reduce_lr]
    )

model.save_weights('model.h5')
print("End of program")

代码转换为 tflite 模型：

import tensorflow as tf

converter = tf.lite.TFLiteConverter.from_keras_model_file("models/1Data_aug_200x200.h5")
tflite_model = converter.convert()
open("models/convertedModels/1Data_aug_200x200.tflite", "wb").write(tflite_model)

然后我在模型上调用“运行”，传入 ByteBuffer（要分类的图像）和输出数组。

输出数组：

private float[][] labelProbArray = new float[1][numLabels]; //numLabels=2

但是，当我打电话时，tflite.run(imgData, labelProbArray);我收到了一个错误。

java.lang.IllegalArgumentException: Cannot copy between a TensorFlowLite tensor with shape [1, 1] and a Java object with shape [1, 2].

张量也应该具有 [1,2] 形状吗？或者有没有其他方法可以让我返回预测的类别和概率？

标签： pythontensorflowkerastf.keras