def model(this, inputs, is_training):
'''
define the model, we use slim's implemention of resnet
'''
with tf.variable_scope(this.vscope):
base_network = nets_factory.get_network_fn(
this.network_name,
num_classes=2,
weight_decay=this.weight_decay,
is_training=is_training)
logits, end_points = base_network(inputs[0])
f = [
end_points['pool5'], end_points['pool4'], end_points['pool3'],
end_points['pool2']
]
values = None
#end_points.value;
# with slim.arg_scope(resnet_v1.resnet_arg_scope(weight_decay=weight_decay)):
# logits, end_points = resnet_v1.resnet_v1_50(images, is_training=is_training, scope='resnet_v1_50')
g = welf_slime_unpool().model(f,
is_training,
values=values,
weight_decay=this.weight_decay)
return welf_slime_east_parser().model(
g,
is_training,
values=values,
weight_decay=this.weight_decay,
text_scale=this.text_scale)
def testGetNetworkFnSecondHalf(self):
batch_size = 5
num_classes = 1000
for net in nets_factory.networks_map.keys()[10:]:
with tf.Graph().as_default() as g, self.test_session(g):
net_fn = nets_factory.get_network_fn(net, num_classes)
# Most networks use 224 as their default_image_size
image_size = getattr(net_fn, 'default_image_size', 224)
inputs = tf.random_uniform(
(batch_size, image_size, image_size, 3))
logits, end_points = net_fn(inputs)
self.assertTrue(isinstance(logits, tf.Tensor))
self.assertTrue(isinstance(end_points, dict))
self.assertEqual(logits.get_shape().as_list()[0], batch_size)
self.assertEqual(logits.get_shape().as_list()[-1], num_classes)