How to properly maintain the object discovery model from the Tensorflow Object Discovery API?

I am using the Tensorflow Object Detection API (github.com/tensorflow/models/tree/master/object_detection) with one object detection task. Right now I have a problem servicing the discovery model that I trained with Tensorflow Serving (tensorflow.imtqy.com/serving/).

1. The first problem that I am facing is exporting the model to useable files. Detecting the api object kindly included exporting the script, so that I can convert the ckpt files to pb variable files. However, the output files will not contain content in the variable folder. I, although it was a mistake and reported this to Github, but it seems that they interned to convert variables to constants so that there are no variables. The detail can be found HERE .

The flags that I used when exporting the saved model are as follows:

    CUDA_VISIBLE_DEVICES=0 python export_inference_graph.py \
        --input_type image_tensor \
            --pipeline_config_path configs/rfcn_resnet50_car_Jul_20.config \
                --checkpoint_path resnet_ckpt/model.ckpt-17586 \
                    --inference_graph_path serving_model/1 \
                      --export_as_saved_model True

It works fine in python when I switch --export_as_saved_model to False.

But still, I have a problem servicing the model.

When I tried to run:

~/serving$ bazel-bin/tensorflow_serving/model_servers/tensorflow_model_server --port=9000 --model_name=gan --model_base_path=<my_model_path>

I got:

2017-07-27 16:11:53.222439: I external/org_tensorflow/tensorflow/cc/saved_model/loader.cc:155] Restoring SavedModel bundle.
2017-07-27 16:11:53.222497: I external/org_tensorflow/tensorflow/cc/saved_model/loader.cc:165] The specified SavedModel has no variables; no checkpoints were restored.
2017-07-27 16:11:53.222502: I external/org_tensorflow/tensorflow/cc/saved_model/loader.cc:190] Running LegacyInitOp on SavedModel bundle.
2017-07-27 16:11:53.229463: I external/org_tensorflow/tensorflow/cc/saved_model/loader.cc:284] Loading SavedModel: success. Took 281805 microseconds.
2017-07-27 16:11:53.229508: I tensorflow_serving/core/loader_harness.cc:86] Successfully loaded servable version {name: gan version: 1}
2017-07-27 16:11:53.244716: I tensorflow_serving/model_servers/main.cc:290] Running ModelServer at 0.0.0.0:9000 ...

, , " SavedModel , ".

, . .

2. .

:

from __future__ import print_function
from __future__ import absolute_import

# Communication to TensorFlow server via gRPC
from grpc.beta import implementations
import tensorflow as tf
import numpy as np
from PIL import Image
# TensorFlow serving stuff to send messages
from tensorflow_serving.apis import predict_pb2
from tensorflow_serving.apis import prediction_service_pb2


# Command line arguments
tf.app.flags.DEFINE_string('server', 'localhost:9000',
                       'PredictionService host:port')
tf.app.flags.DEFINE_string('image', '', 'path to image in JPEG format')
FLAGS = tf.app.flags.FLAGS


def load_image_into_numpy_array(image):
    (im_width, im_height) = image.size
    return np.array(image.getdata()).reshape(
    (im_height, im_width, 3)).astype(np.uint8)

def main(_):
    host, port = FLAGS.server.split(':')
    channel = implementations.insecure_channel(host, int(port))
    stub = prediction_service_pb2.beta_create_PredictionService_stub(channel)

    # Send request
    request = predict_pb2.PredictRequest()
    image = Image.open(FLAGS.image)
    image_np = load_image_into_numpy_array(image)
    image_np_expanded = np.expand_dims(image_np, axis=0)
    # Call GAN model to make prediction on the image
    request.model_spec.name = 'gan'
    request.model_spec.signature_name = 'predict_images'
    request.inputs['inputs'].CopyFrom(
    tf.contrib.util.make_tensor_proto(image_np_expanded))

    result = stub.Predict(request, 60.0)  # 60 secs timeout
    print(result)


if __name__ == '__main__':
    tf.app.run()

request.model_spec.signature_name = 'predict_images', exporter.py script api (github.com/tensorflow/models/blob/master/object_detection/exporter.py), 289:

          signature_def_map={
          signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
              detection_signature,
      },

To:

          signature_def_map={
          'predict_images': detection_signature,
          signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
              detection_signature,
      },

, .

:

bazel-bin/tensorflow_serving/example/client --server=localhost:9000 --image=<my_image_file>

:

    Traceback (most recent call last):
  File "/home/xinyao/serving/bazel-bin/tensorflow_serving/example/client.runfiles/tf_serving/tensorflow_serving/example/client.py", line 54, in <module>
    tf.app.run()
  File "/home/xinyao/serving/bazel-bin/tensorflow_serving/example/client.runfiles/org_tensorflow/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "/home/xinyao/serving/bazel-bin/tensorflow_serving/example/client.runfiles/tf_serving/tensorflow_serving/example/client.py", line 49, in main
    result = stub.Predict(request, 60.0)  # 60 secs timeout
  File "/usr/local/lib/python2.7/dist-packages/grpc/beta/_client_adaptations.py", line 324, in __call__
    self._request_serializer, self._response_deserializer)
  File "/usr/local/lib/python2.7/dist-packages/grpc/beta/_client_adaptations.py", line 210, in _blocking_unary_unary
    raise _abortion_error(rpc_error_call)
grpc.framework.interfaces.face.face.AbortionError: AbortionError(code=StatusCode.NOT_FOUND, details="FeedInputs: unable to find feed output ToFloat:0")

, .

, , , script , , , AbortionError github.com/tensorflow/tensorflow/blob/f488419cd6d9256b25ba25cbe736097dfeee79f9/tensorflow/core/graph/subgraph.cc. , . , .

, . , , , . , ? !

+4
4

. . . . , , Cloud ML Engine. . github issue, .

" SavedModel , ". , - , , . "FeedInputs: ToFloat: 0", , TF 1.2 .

+1

. SSDMobileNet-COCO Zoo API Tensorflow

, /,

cd serving/tf_models git pull origin master git checkout master

.

bazel build //tensorflow_serving/model_servers:tensorflow_model_server

,

0

grpc.framework.interfaces.face.face.AbortionError: AbortionError(code=StatusCode.NOT_FOUND, details="FeedInputs: unable to find feed output ToFloat:0"

tf_models .

. https://github.com/tensorflow/tensorflow/issues/11863

0
  • . .

  • The problem is that the input needs to be converted uint8to as the model expects. Here is a snippet of code that worked for me.

request = predict_pb2.PredictRequest()
request.model_spec.name = 'gan'
request.model_spec.signature_name = 
    signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY

image = Image.open('any.jpg')
image_np = load_image_into_numpy_array(image)
image_np_expanded = np.expand_dims(image_np, axis=0)

request.inputs['inputs'].CopyFrom(
    tf.contrib.util.make_tensor_proto(image_np_expanded, 
        shape=image_np_expanded.shape, dtype='uint8'))

This part is important to you shape = image_np_expanded.shape, dtype = 'uint8' and don't forget to download the latest update for maintenance.

0
source

Source: https://habr.com/ru/post/1682456/


All Articles