在 TensorFlow Lite 中运行 Keras 模型时的不同预测

使用预训练的Keras图像分类器试用TensorFlow Lite,将H5转换为tflite格式后,我得到的预测更糟。这是预期的行为(例如,权重量化),错误还是在使用解释器时忘记了某些东西?


例子

from imagesoup import ImageSoup

from tensorflow.keras.applications.resnet50 import ResNet50, preprocess_input, decode_predictions

from tensorflow.keras.preprocessing.image import load_img, img_to_array


# Load an example image.

ImageSoup().search('terrier', n_images=1)[0].to_file('image.jpg')

i = load_img('image.jpg', target_size=(224, 224))

x = img_to_array(i)

x = x[None, ...]

x = preprocess_input(x)


# Classify image with Keras.

model = ResNet50()

y = model.predict(x)

print("Keras:", decode_predictions(y))


# Convert Keras model to TensorFlow Lite.

model.save(f'{model.name}.h5')

converter = tf.contrib.lite.TocoConverter.from_keras_model_file

tflite_model = converter(f'{model.name}.h5').convert()

with open(f'{model.name}.tflite', 'wb') as f:

    f.write(tflite_model)


# Classify image with TensorFlow Lite.

f = tf.contrib.lite.Interpreter(f'{model.name}.tflite')

f.allocate_tensors()

i = f.get_input_details()[0]

o = f.get_output_details()[0]

f.set_tensor(i['index'], x)

f.invoke()

y = f.get_tensor(o['index'])

print("TensorFlow Lite:", decode_predictions(y))

凯拉斯:[[('n02098105','soft-coated_wheaten_terrier',0.70274395),('n02091635','otterhound',0.0885325),('n02090721','Irish_wolfhound',0.06422518),('n02093991','Irish_terrier' , 0.040120784), ('n02111500', 'Great_Pyrenees', 0.03408164)]]


TensorFlow Lite:[[('n07753275','菠萝',0.94529104),('n03379051','football_helmet',0.033994876),('n03891332','parking_meter',0.011431991),('n04522168','花瓶', 0.0029440755),('n02094114','Norfolk_terrier',0.0022089847)]]


扬帆大鱼
浏览 278回答 2
2回答

Cats萌萌

from_keras_model_fileTensorFlow 1.10 中存在一个错误。它在 8 月 9 日每晚发布的此提交中得到修复。nightly 可以通过pip install tf-nightly. 此外,它将在 TensorFlow 1.11 中修复。
打开App,查看更多内容
随时随地看视频慕课网APP

相关分类

Python