我正在研究一个简单的Tensorflow mnist识别程序。目标是将包含手写数字的jpg / png图片上传到其中，并获得答案是多少。我的朋友写了一些模型，并用python脚本将其导出：
import tensorflow as tf
from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets
import time
iters_num = 1000
display_step = 10
batch = 100
tf.set_random_seed(0)
mnist = read_data_sets("MNISTdata", one_hot=True, reshape=False, validation_size=0)
# placeholders definition
X = tf.placeholder(tf.float32, [None, 28, 28, 1])
Y_ = tf.placeholder(tf.float32, [None, 10])
# probability of keeping a node during dropout = 1.0 at test time (no dropout) and 0.75 at training time(defined later on)
pkeep = tf.placeholder(tf.float32)
# layers with size (depth) definition
layer1 = 16
layer2 = 32
layer3 = 64
# fullyconnected layer (number of neurons)
full_layer4 = 512
# layers definitions
W1 = tf.Variable(tf.truncated_normal([10, 10, 1, layer1], stddev=0.1))
b1 = tf.Variable(tf.truncated_normal([layer1], stddev=0.1))
W2 = tf.Variable(tf.truncated_normal([6, 6, layer1, layer2], stddev=0.1))
b2 = tf.Variable(tf.truncated_normal([layer2], stddev=0.1))
W3 = tf.Variable(tf.truncated_normal([6, 6, layer2, layer3], stddev=0.1))
b3 = tf.Variable(tf.truncated_normal([layer3], stddev=0.1))
W4 = tf.Variable(tf.truncated_normal([7 * 7 * layer3, full_layer4], stddev=0.1))
b4 = tf.Variable(tf.truncated_normal([full_layer4], stddev=0.1))
# output softmax layer (10 labels (for 10 digits))
W5 = tf.Variable(tf.truncated_normal([full_layer4, 10], stddev=0.1))
b5 = tf.Variable(tf.truncated_normal([10], stddev=0.1))
XX = tf.reshape(X, [-1, 784])
# model definition
stride = 1 # output is 28x28 (no size changes)
Y1 = tf.nn.relu(tf.nn.conv2d(X, W1, strides=[1, stride, stride, 1], padding='SAME') + b1)
k = 2 # max pool filter size
Y2 = tf.nn.relu(tf.nn.conv2d(Y1, W2, strides=[1, stride, stride, 1], padding='SAME') + b2)
Y2 = tf.nn.max_pool(Y2, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME')
Y3 = tf.nn.relu(tf.nn.conv2d(Y2, W3, strides=[1, stride, stride, 1], padding='SAME') + b3)
Y3 = tf.nn.max_pool(Y3, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME')
# reshape the output from the third convolution for the fully connected layer
YY = tf.reshape(Y3, shape=[-1, 7 * 7 * layer3])
Y4 = tf.nn.relu(tf.matmul(YY, W4) + b4)
Ylogits = tf.matmul(Y4, W5) + b5
Y = tf.nn.softmax(Ylogits)
# loss function -> cross entropy
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=Ylogits, labels=Y_)
cross_entropy = tf.reduce_mean(cross_entropy) * 100
# accuracy of the trained model <0,1>
correct_prediction = tf.equal(tf.argmax(Y, 1), tf.argmax(Y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# training step definition with Adam optimalization algorithm
learning_rate = 0.003
train_step = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy)
# matplotlib visualization
allweights = tf.concat([tf.reshape(W1, [-1]), tf.reshape(W2, [-1]), tf.reshape(W3, [-1]), tf.reshape(W4, [-1]), tf.reshape(W5, [-1])], 0)
allbiases = tf.concat([tf.reshape(b1, [-1]), tf.reshape(b2, [-1]), tf.reshape(b3, [-1]), tf.reshape(b4, [-1]), tf.reshape(b5, [-1])], 0)
# initializing all variables(!!)
init = tf.global_variables_initializer()
# lists for training values
train_losses = list()
train_acc = list()
test_losses = list()
test_acc = list()
saver = tf.train.Saver()
time_start = time.clock()
export_dir = "D:/Optinav.Testowy/trunk/HandwriteRecognition/DigitsRecognitionCNN/23"
builder = tf.saved_model.builder.SavedModelBuilder(export_dir)
# launching computational graph
with tf.Session() as sess:
sess.run(init)
for i in range(iters_num + 1):
# training incoming on batches
batch_X, batch_Y = mnist.train.next_batch(batch)
if i % display_step == 0:
# compute training values for visualization of model steps
acc_trn, loss_trn, w, b = sess.run([accuracy, cross_entropy, allweights, allbiases], feed_dict={X: batch_X, Y_: batch_Y, pkeep: 1.0})
acc_tst, loss_tst = sess.run([accuracy, cross_entropy], feed_dict={X: mnist.test.images, Y_: mnist.test.labels, pkeep: 1.0})
print("Step#{} Train accuracy={} , Train loss={} Test accuracy={} , Test loss={}".format(i,acc_trn,loss_trn,acc_tst,loss_tst))
train_losses.append(loss_trn)
train_acc.append(acc_trn)
test_losses.append(loss_tst)
test_acc.append(acc_tst)
# the back-propagation training step (probability = 0.75)
sess.run(train_step, feed_dict={X: batch_X, Y_: batch_Y, pkeep: 0.75})
# save model
saver.save(sess, "D:/Optinav.Testowy/trunk/HandwriteRecognition/DigitsRecognitionCNN/model2.ckpt")
classification_inputs = tf.saved_model.utils.build_tensor_info(
X)
classification_outputs_classes = tf.saved_model.utils.build_tensor_info(
Y_)
classification_outputs_scores = tf.saved_model.utils.build_tensor_info(Y)
classification_signature = (
tf.saved_model.signature_def_utils.build_signature_def(
inputs={
tf.saved_model.signature_constants.CLASSIFY_INPUTS:
classification_inputs
},
outputs={
tf.saved_model.signature_constants.CLASSIFY_OUTPUT_CLASSES:
classification_outputs_classes,
tf.saved_model.signature_constants.CLASSIFY_OUTPUT_SCORES:
classification_outputs_scores
},
method_name=tf.saved_model.signature_constants.CLASSIFY_METHOD_NAME))
tensor_info_x = tf.saved_model.utils.build_tensor_info(X)
tensor_info_y = tf.saved_model.utils.build_tensor_info(Y)
prediction_signature = (
tf.saved_model.signature_def_utils.build_signature_def(
inputs={'images': tensor_info_x},
outputs={'scores': tensor_info_y},
method_name=tf.saved_model.signature_constants.PREDICT_METHOD_NAME))
builder.add_meta_graph_and_variables(
sess, [tf.saved_model.tag_constants.SERVING],
signature_def_map={
'predict_images':
prediction_signature,
tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
classification_signature,
},
main_op=tf.tables_initializer(),
strip_default_attrs=True)
builder.save()
print('Done exporting!')
# calculates learning time [s]
time_stop = time.clock()
time_run = time_stop - time_start
print("Learning time: %s" % time_run)
导出的模型放置在Azure的Ubuntu上运行的Docker容器中。 借助TensorFlow的示例（GitHub），我用python编写了一个客户端：
from __future__ import print_function
import grpc
import tensorflow as tf
import scipy.ndimage
import numpy
from tensorflow_serving.apis import predict_pb2
from tensorflow_serving.apis import prediction_service_pb2_grpc
tf.app.flags.DEFINE_string('server', '', 'PredictionService host:port')
tf.app.flags.DEFINE_string('image_filename', '', 'Name of image to test')
tf.app.flags.DEFINE_string('work_dir', '/tmp', 'Working directory. ')
FLAGS = tf.app.flags.FLAGS
class _ResultObj(object):
def __init__(self):
self._number = 99
def get_number(self):
return self._number
def set_number(self, val):
self._number = val
def myfunc(a):
if a > 125:
return 255
elif a > 70:
return a
else:
return 0
def _create_rpc_callback(resultobj):
def _callback(result_future):
exception = result_future.exception()
if exception:
print(exception)
else:
response = numpy.array(
result_future.result().outputs['scores'].float_val)
prediction = numpy.argmax(response)
resultobj.set_number(prediction)
return _callback
def do_inference(hostport, image_filename):
vfunc = numpy.vectorize(myfunc)
test_data_set = vfunc(numpy.ndarray.flatten(scipy.ndimage.imread(image_filename, flatten=True)).astype(int))
test_data_set = numpy.reshape(test_data_set, [28, 28, 1])
channel = grpc.insecure_channel(hostport)
stub = prediction_service_pb2_grpc.PredictionServiceStub(channel)
resultObj = _ResultObj()
request = predict_pb2.PredictRequest()
request.model_spec.name = 'ver2'
request.model_spec.signature_name = 'predict_images'
request.inputs['images'].CopyFrom(
tf.contrib.util.make_tensor_proto(test_data_set, shape=[1, test_data_set.size]))
result_future = stub.Predict.future(request, 5.0) # 5 seconds
result_future.add_done_callback(
_create_rpc_callback(resultObj))
return resultObj.get_number()
def main(_):
if not FLAGS.server:
print('please specify server host:port')
return
print(do_inference(FLAGS.server, FLAGS.image_filename))
if __name__ == '__main__':
tf.app.run()
我确信我朋友的模型可以识别图像。她告诉我将图像矢量化，然后再将其添加到请求中，但似乎无法正确连接模型。使用脚本时没有错误。当我写错了model_spec.name时，TensorFlow服务甚至都不在乎。 _callback从未使用过，我只得到ResultObj对象的初始值。
任何有关此问题的帮助将不胜感激。
谢谢。