Tensorflow在预训练的Keras ResNet50模型上服务,返回始终相同的预测



我使用以下代码将预先训练的ResNet50 keras模型导出到tensorflow,用于tensorflow服务:

import tensorflow as tf
sess = tf.Session()
from keras import backend as K
K.set_session(sess)
K.set_learning_phase(0)
# Modelo resnet con pesos entrenados en imagenet
from keras.applications.resnet50 import ResNet50
model = ResNet50(weights='imagenet')
# exportar en tensorflow
import os
version_number = max([ int(x) for x in os.listdir('./resnet-classifier') ]) + 1
export_path = './resnet-classifier/{}'.format(version_number)
with tf.keras.backend.get_session() as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
tf.saved_model.simple_save(sess, export_path,
inputs=dict(input_image=model.input),
outputs={t.name:t for t in model.outputs}
)

我尝试了上面的一些变体,所有这些变体都有相同的结果(tensorflow服务时的预测相同(。

然后我运行tensorflow服务类似:

docker run -p 8501:8501 
-v ./resnet-classifier:/models/resnet-classifier 
-e MODEL_NAME=resnet-classifier -e MODEL_BASE_PATH=/models 
-t tensorflow/serving

最后,我使用以下函数对tensorflow服务进行预测:

def imagepath_to_tfserving_payload(img_path):
import numpy as np
from keras.preprocessing import image
from keras.applications.resnet50 import preprocess_input
img = image.img_to_array(image.load_img(img_path, target_size=(224, 224)))
X = np.expand_dims(img, axis=0).astype('float32')
X = preprocess_input(X)
payload = dict(instances=X.tolist())
payload = json.dumps(payload)
return payload
def tfserving_predict(image_payload, url=None):
import requests
if url is None:
url = 'http://localhost:8501/v1/models/resnet-classifier:predict'
r = requests.post(url, data=image_payload)
pred_json = json.loads(r.content.decode('utf-8'))
from keras.applications.resnet50 import decode_predictions
predictions = decode_predictions(np.asarray(pred_json['predictions']), top=3)[0]
return predictions

然后,我从一个ipython shell中使用上面的两个函数,从本地存储的imagenet的val集中选择随机的imagene。问题是tensorflow服务总是为我发送的所有图像返回相同的预测。

每次我用上面的第一个脚本导出模型时,我都会得到稍微不同的类,第一个类的置信度为"1",其他类为"0",例如:

# Serialization 1, in ./resnet-classifier/1 always returning:
[
[
"n07745940",
"strawberry",
1.0
],
[
"n02104029",
"kuvasz",
1.4013e-36
],
[
"n15075141",
"toilet_tissue",
0.0
]
]
# Serialization 2, in ./resnet-classifier/2 always returning:
[
[
"n01530575",
"brambling",
1.0
],
[
"n15075141",
"toilet_tissue",
0.0
],
[
"n02319095",
"sea_urchin",
0.0
]
]

这可能与Tensorflow有关:服务模型总是返回相同的预测,但我不知道那里的答案(没有被接受的答案(会有什么帮助。

有人知道上面出了什么问题,以及如何解决它吗?

我发现调用sess.run(tf.global_variables_initializer(((会覆盖预先训练的权重,线索在http://zachmoshe.com/2017/11/11/use-keras-models-with-tf.html.

对我来说,解决方案非常简单,只需通过以下内容更改原始问题中的第一块代码,该代码在模型实例化/权重加载之前调用tf.global_variables_initializer((

import tensorflow as tf
sess = tf.Session()
sess.run(tf.global_variables_initializer())
from keras import backend as K
K.set_session(sess)
K.set_learning_phase(0)
# Modelo resnet con pesos entrenados en imagenet
from keras.applications.resnet50 import ResNet50
model = ResNet50(weights='imagenet')
# exportar en tensorflow
import os
versions = [ int(x) for x in os.listdir('./resnet-classifier') ]
version_number = max(versions) + 1 if versions else 1
export_path = './resnet-classifier/{}'.format(version_number)
tf.saved_model.simple_save(sess, export_path,
inputs=dict(input_image=model.input),
outputs={t.name:t for t in model.outputs}
)

当我忘记规范化图像时,有时会遇到这种问题。我认为resnet接受0之间的浮点数格式的图像。和1。(或者可能是-1。to 1.(。我不知道preprocess_input函数的作用,但您可以检查它是否以预期格式返回数组。

最新更新