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),错误还是使用解释器时我忘记了一些东西?
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))
Keras:[[('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','vase',0.0029440755),('n02094114','Norfolk_terrier,0.0022089847)]]
答案 0 :(得分:0)
您是否确保将学习阶段设置为0,以避免在预测阶段出现Dropout和其他不确定性层?
{{3}}
答案 1 :(得分:0)
TensorFlow 1.10中的from_keras_model_file
中存在一个错误。该问题已在8月9日每晚发布的this commit中修复。
每晚可以通过pip install tf-nightly
安装。此外,它将在TensorFlow 1.11中修复。