How to get predictions from a tf.estimator trained CNN - tensorflow

Question

I have trained a CNN using the tf.estimator API, but am having trouble getting predictions out in a way that is useful to me.
I need to feed images to my CNN in real time as they are received from a camera. In an older net design I made the Controller_tf class, which worked fine for doing that. So I have tried to adapt it to a new CNN trained using tf.estimator (as said earlier).
The estimator.predict interface seems to want to be invoked via a tf.app.run() call (would be glad to be proved wrong about that), which is why I am trying to run the CNN using tf.Session() (with if statements inside the model function to only run the relevant parts) but I'm currently getting the error:
ValueError: Fetch argument 'infer' cannot be interpreted as a Tensor. ("The name 'infer' refers to an Operation not in the graph.")
I can't quite see where I am going wrong. Is the trained model incompatable with the run in PREDICT mode? Any help will be very much appreciated. Any way here is the code:
class Controller_tf:
set_speed = None
def __init__(self, model, ckpt_path, set_speed_in):
self.set_speed = set_speed_in
self.x = tf.placeholder(tf.float32, shape = (None, 104, 160, 3))
self.y = model(self.x, None, tf.estimator.ModeKeys.PREDICT)
# make TF use memory growth method
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
self.sess = tf.Session(config=config)
saver = tf.train.Saver()
saver.restore(self.sess, ckpt_path)
def update(self, message):
# The current speed of the car
image = frame2numpy(message['frame'], (160,104))
image_array = np.asarray(image)
turn_logits = self.sess.run(self.y, {self.x: image_array[None, :, :, :]})
return turn_logits
model = cnn_model_fn3
ckpt = 'ckpts/stc_model3/model.ckpt-27621'
controller = Controller_tf(model, ckpt, 18)
image_file = 'G:/Datasets/ds072.001/ds072.001-fm-0008465.jpg'
#image_file = 'G:/Datasets/ds072.001/ds072.001-fm-0009156.jpg'
satnavimg = load_image(image_file)
satnavimg = np.asarray([satnavimg])
satnavimg = (satnavimg/127.5) - 1.0
print(np.shape(satnavimg))
msg = {'frame': satnavimg}
turn = controller.update(msg)
print(turn)
The model function is:
def cnn_model_fn3(features, labels, mode):
if mode == tf.estimator.ModeKeys.PREDICT:
input_layer = features
else:
input_layer = tf.reshape(features["image_data"], [-1, 104, 160, 3])
conv1 = tf.layers.conv2d(
inputs=input_layer,
filters=32,
kernel_size=[10, 10],
padding="same",
activation=tf.nn.relu,
name='Conv1')
... removed layer code for brevity ...
logits = tf.layers.dense(
inputs=dropout1,
units=3,
name='Dense3')
predictions = {
"classes": tf.argmax(input=logits, axis=1),
"probabilities": tf.nn.softmax(logits, name="softmax_tensor")
}
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)
# Calculate Loss (for both TRAIN and EVAL modes)
loss = tf.losses.sparse_softmax_cross_entropy(labels=labels, logits=logits)
# Configure the Training Op (for TRAIN mode)
if mode == tf.estimator.ModeKeys.TRAIN:
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001)
train_op = optimizer.minimize(
loss=loss,
global_step=tf.train.get_global_step())
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)
# Add evaluation metrics (for EVAL mode)
if mode == tf.estimator.ModeKeys.EVAL:
eval_metric_ops = {
"accuracy": tf.metrics.accuracy(
labels=labels, predictions=predictions["classes"])}
if mode == tf.estimator.ModeKeys.PREDICT:
return logits
return tf.estimator.EstimatorSpec(
mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)