saved_model 来自 AutoML Vision Edge 的加载不正确

Question

我一直在使用 AutoML Vision Edge 执行一些图像分类任务，在以 TFLite 格式导出模型时取得了很好的效果。但是，我刚刚尝试使用 Tensorflow 2.0 导出 saved_model.pb 文件和运行它，似乎运行出现了一些问题。

代码片段：

import numpy as np
import tensorflow as tf
import cv2

from tensorflow import keras

my_model = tf.keras.models.load_model('saved_model')
print(my_model)
print(my_model.summary())

'saved_model' 是包含我下载的 saved_model.pb 文件的目录。这是我看到的：

2019-10-18 23:29:08.801647: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2019-10-18 23:29:08.829017: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7ffc2d717510 executing computations on platform Host. Devices: 2019-10-18 23:29:08.829038: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): Host, Default Version Traceback (most recent call last): File "classify_in_out_tf2.py", line 81, in print(my_model.summary()) AttributeError: 'AutoTrackable' object has no attribute 'summary'

我不确定这是我导出模型的方式的问题，还是我加载模型的代码的问题，或者这些模型是否与 Tensorflow 2.0 或某些组合不兼容。

如有任何帮助，我们将不胜感激！

Answer 1

我的 saved_model.pb 在 docker 容器之外工作（用于对象检测，而不是分类 - 但它们应该相似，更改输出，也许 [=14] 的输入=])，方法如下：

张量流 1.14.0:

图像编码为字节

import cv2
import tensorflow as tf
cv2.imread(filepath)
flag, bts = cv.imencode('.jpg', img)
inp = [bts[:,0].tobytes()]
with tf.Session(graph=tf.Graph()) as sess:
    tf.saved_model.loader.load(sess, ['serve'], 'directory_of_saved_model')
    graph = tf.get_default_graph()
    out = sess.run([sess.graph.get_tensor_by_name('num_detections:0'),
            sess.graph.get_tensor_by_name('detection_scores:0'),
            sess.graph.get_tensor_by_name('detection_boxes:0'),
            sess.graph.get_tensor_by_name('detection_classes:0')],
           feed_dict={'encoded_image_string_tensor:0': inp})

图像为 numpy 数组

import cv2
import tensorflow as tf
import numpy as np
with tf.Session(graph=tf.Graph()) as sess:
    tf.saved_model.loader.load(sess, ['serve'], 'directory_of_saved_model')
    graph = tf.get_default_graph()
    # Read and preprocess an image.
    img = cv2.imread(filepath)
    # Run the model
    out = sess.run([sess.graph.get_tensor_by_name('num_detections:0'),
                    sess.graph.get_tensor_by_name('detection_scores:0'),
                    sess.graph.get_tensor_by_name('detection_boxes:0'),
                    sess.graph.get_tensor_by_name('detection_classes:0')],
                   feed_dict={'map/TensorArrayStack/TensorArrayGatherV3:0': img[np.newaxis, :, :, :]})

我使用 netron 来查找我的输入。

张量流 2.0:

import cv2
import tensorflow as tf
img = cv2.imread('path_to_image_file')
flag, bts = cv2.imencode('.jpg', img)
inp = [bts[:,0].tobytes()]
loaded = tf.saved_model.load(export_dir='directory_of_saved_model')
infer = loaded.signatures["serving_default"]
out = infer(key=tf.constant('something_unique'), image_bytes=tf.constant(inp))

saved_model 来自 AutoML Vision Edge 的加载不正确

saved_model from AutoML Vision Edge not loading properly

python

tensorflow

google-cloud-automl

张量流 1.14.0:

图像编码为字节

图像为 numpy 数组

张量流 2.0: