I am writing a client python file that uses flask framework and running
this inside a docker machine. So this take an input file and produces
output of it. But it throws error that it cant convert to tensor.
tf.app.flags.DEFINE_string('server', 'localhost:9000', 'PredictionService
host:port')
FLAGS = tf.app.flags.FLAGS
app = Flask(__name__)
class mainSessRunning():
def __init__(self):
host, port = FLAGS.server.split(':')
channel = implementations.insecure_channel(host, int(port))
self.stub =
prediction_service_pb2.beta_create_PredictionService_stub(channel)
self.request = predict_pb2.PredictRequest()
self.request.model_spec.name = 'modelX'
self.request.model_spec.signature_name = 'prediction'
def inference(self, val_x):
data = val_x
self.request.inputs['input'].CopyFrom(tf.contrib.util.make_tensor_proto(data))
result = self.stub.Predict(self.request, 5.0)
return result
run = mainSessRunning()
# Define a route for the default URL, which loads the form@app.route('/pred',
methods=['POST'])def pred():
request_data = request.files['file']
result = run.inference(request_data)
rs = json_format.MessageToJson(result)
return jsonify({'result':rs})
So when i send an input text file, it throws error:
TypeError: Failed to convert object of type
(class'werkzeug.datastructures.File.Storage') to tensor. Contents:
(Filestorage: u'File.txt' ('text/plain')). Consider casting elements to a
supported type
This line produces the error :
*self.request.inputs['input'].CopyFrom(tf.contrib.util.make_tensor_proto(data))*
I don't know how to deal with it. Any help is appreciated.
--
You received this message because you are subscribed to the Google Groups
"pocoo-libs" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to pocoo-libs+unsubscr...@googlegroups.com.
To post to this group, send email to pocoo-libs@googlegroups.com.
Visit this group at https://groups.google.com/group/pocoo-libs.
For more options, visit https://groups.google.com/d/optout.
