def tower_loss(scope):
images, labels = read_and_decode()
if net == 'vgg_16':
with slim.arg_scope(vgg.vgg_arg_scope()):
logits, end_points = vgg.vgg_16(images, num_classes=FLAGS.num_classes)
elif net == 'vgg_19':
with slim.arg_scope(vgg.vgg_arg_scope()):
logits, end_points = vgg.vgg_19(images, num_classes=FLAGS.num_classes)
elif net == 'resnet_v1_101':
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
logits, end_points = resnet_v1.resnet_v1_101(images, num_classes=FLAGS.num_classes)
logits = tf.reshape(logits, [FLAGS.batch_size, FLAGS.num_classes])
elif net == 'resnet_v1_50':
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
logits, end_points = resnet_v1.resnet_v1_50(images, num_classes=FLAGS.num_classes)
logits = tf.reshape(logits, [FLAGS.batch_size, FLAGS.num_classes])
elif net == 'resnet_v2_50':
with slim.arg_scope(resnet_v2.resnet_arg_scope()):
logits, end_points = resnet_v2.resnet_v2_50(images, num_classes=FLAGS.num_classes)
logits = tf.reshape(logits, [FLAGS.batch_size, FLAGS.num_classes])
else:
raise Exception('No network matched with net %s.' % net)
assert logits.shape == (FLAGS.batch_size, FLAGS.num_classes)
_ = cal_loss(logits, labels)
losses = tf.get_collection('losses', scope)
total_loss = tf.add_n(losses, name='total_loss')
for l in losses + [total_loss]:
loss_name = re.sub('%s_[0-9]*/' % TOWER_NAME, '', l.op.name)
tf.summary.scalar(loss_name, l)
return total_loss
def main(args):
start = time()
print('Start')
splits = get_splits(args.image_dir)
img_size = 224
# TF graph creation
images_placeholder = tf.placeholder(tf.float32, [None, None, None, 3],
name='image')
proc_image_op = tf.image.resize_image_with_crop_or_pad(images_placeholder,
target_height=224,
target_width=224)
_, end_points = vgg.vgg_16(proc_image_op,
is_training=False,
dropout_keep_prob=1.0)
ft_name = os.path.join("vgg_16", "fc8")
ft_output = end_points[ft_name]
####
for split in splits:
extract_features(images_placeholder=images_placeholder,
image_dir=os.path.join(args.image_dir, split),
ft_output=ft_output,
out_dir=args.output_dir,
split=split,
network_ckpt=args.model_ckpt)
print('Image Features extracted.')
print('Time taken: ', time() - start)
def testEndPoints(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
for is_training in [True, False]:
with ops.Graph().as_default():
inputs = random_ops.random_uniform(
(batch_size, height, width, 3))
_, end_points = vgg.vgg_16(inputs,
num_classes,
is_training=is_training)
expected_names = [
'vgg_16/conv1/conv1_1', 'vgg_16/conv1/conv1_2',
'vgg_16/pool1', 'vgg_16/conv2/conv2_1',
'vgg_16/conv2/conv2_2', 'vgg_16/pool2',
'vgg_16/conv3/conv3_1', 'vgg_16/conv3/conv3_2',
'vgg_16/conv3/conv3_3', 'vgg_16/pool3',
'vgg_16/conv4/conv4_1', 'vgg_16/conv4/conv4_2',
'vgg_16/conv4/conv4_3', 'vgg_16/pool4',
'vgg_16/conv5/conv5_1', 'vgg_16/conv5/conv5_2',
'vgg_16/conv5/conv5_3', 'vgg_16/pool5', 'vgg_16/fc6',
'vgg_16/fc7', 'vgg_16/fc8'
]
self.assertSetEqual(set(end_points.keys()),
set(expected_names))
def testEndPoints(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = vgg.vgg_16(inputs, num_classes)
expected_names = ['vgg_16/conv1/conv1_1',
'vgg_16/conv1/conv1_2',
'vgg_16/pool1',
'vgg_16/conv2/conv2_1',
'vgg_16/conv2/conv2_2',
'vgg_16/pool2',
'vgg_16/conv3/conv3_1',
'vgg_16/conv3/conv3_2',
'vgg_16/conv3/conv3_3',
'vgg_16/pool3',
'vgg_16/conv4/conv4_1',
'vgg_16/conv4/conv4_2',
'vgg_16/conv4/conv4_3',
'vgg_16/pool4',
'vgg_16/conv5/conv5_1',
'vgg_16/conv5/conv5_2',
'vgg_16/conv5/conv5_3',
'vgg_16/pool5',
'vgg_16/fc6',
'vgg_16/fc7',
'vgg_16/fc8'
]
print(end_points.keys())
self.assertSetEqual(set(end_points.keys()), set(expected_names))
def top_feature_net(input, anchors, inds_inside, num_bases):
stride=8
# arg_scope = resnet_v1.resnet_arg_scope(weight_decay=0.0)
# with slim.arg_scope(arg_scope) :
with slim.arg_scope(vgg.vgg_arg_scope()):
# net, end_points = resnet_v1.resnet_v1_50(input, None, global_pool=False, output_stride=8)
block5, end_points = vgg.vgg_16(input)
block3 = end_points['conv3/conv3_3']
# block = conv2d_bn_relu(block, num_kernels=512, kernel_size=(1,1), stride=[1,1,1,1], padding='SAME', name='2')
tf.summary.histogram('rpn_top_block', block)
# tf.summary.histogram('rpn_top_block_weights', tf.get_collection('2/conv_weight')[0])
with tf.variable_scope('top') as scope:
#up = upsample2d(block, factor = 2, has_bias=True, trainable=True, name='1')
#up = block
up = conv2d_bn_relu(block, num_kernels=128, kernel_size=(3,3), stride=[1,1,1,1], padding='SAME', name='2')
scores = conv2d(up, num_kernels=2*num_bases, kernel_size=(1,1), stride=[1,1,1,1], padding='SAME', name='score')
probs = tf.nn.softmax( tf.reshape(scores,[-1,2]), name='prob')
deltas = conv2d(up, num_kernels=4*num_bases, kernel_size=(1,1), stride=[1,1,1,1], padding='SAME', name='delta')
#<todo> flip to train and test mode nms (e.g. different nms_pre_topn values): use tf.cond
with tf.variable_scope('top-nms') as scope: #non-max
batch_size, img_height, img_width, img_channel = input.get_shape().as_list()
img_scale = 1
# pdb.set_trace()
rois, roi_scores = tf_rpn_nms( probs, deltas, anchors, inds_inside,
stride, img_width, img_height, img_scale,
nms_thresh=0.7, min_size=stride, nms_pre_topn=nms_pre_topn_, nms_post_topn=nms_post_topn_,
name ='nms')
#<todo> feature = upsample2d(block, factor = 4, ...)
feature = block
def VGG_16(input_image):
arg_scope = vgg.vgg_arg_scope()
with slim.arg_scope(arg_scope):
features, _ = vgg.vgg_16(input_image)
# feature flatten
features = tf.reshape(features, shape=[1, -1])
features = tf.squeeze(features)
return features
def testModelVariables(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
with self.test_session():
inputs = random_ops.random_uniform((batch_size, height, width, 3))
vgg.vgg_16(inputs, num_classes)
expected_names = [
'vgg_16/conv1/conv1_1/weights',
'vgg_16/conv1/conv1_1/biases',
'vgg_16/conv1/conv1_2/weights',
'vgg_16/conv1/conv1_2/biases',
'vgg_16/conv2/conv2_1/weights',
'vgg_16/conv2/conv2_1/biases',
'vgg_16/conv2/conv2_2/weights',
'vgg_16/conv2/conv2_2/biases',
'vgg_16/conv3/conv3_1/weights',
'vgg_16/conv3/conv3_1/biases',
'vgg_16/conv3/conv3_2/weights',
'vgg_16/conv3/conv3_2/biases',
'vgg_16/conv3/conv3_3/weights',
'vgg_16/conv3/conv3_3/biases',
'vgg_16/conv4/conv4_1/weights',
'vgg_16/conv4/conv4_1/biases',
'vgg_16/conv4/conv4_2/weights',
'vgg_16/conv4/conv4_2/biases',
'vgg_16/conv4/conv4_3/weights',
'vgg_16/conv4/conv4_3/biases',
'vgg_16/conv5/conv5_1/weights',
'vgg_16/conv5/conv5_1/biases',
'vgg_16/conv5/conv5_2/weights',
'vgg_16/conv5/conv5_2/biases',
'vgg_16/conv5/conv5_3/weights',
'vgg_16/conv5/conv5_3/biases',
'vgg_16/fc6/weights',
'vgg_16/fc6/biases',
'vgg_16/fc7/weights',
'vgg_16/fc7/biases',
'vgg_16/fc8/weights',
'vgg_16/fc8/biases',
]
model_variables = [
v.op.name for v in variables_lib.get_model_variables()
]
self.assertSetEqual(set(model_variables), set(expected_names))
def testForward(self):
batch_size = 1
height, width = 224, 224
with self.test_session() as sess:
inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_16(inputs)
sess.run(variables.global_variables_initializer())
output = sess.run(logits)
self.assertTrue(output.any())
def testForward(self):
batch_size = 1
height, width = 224, 224
with self.test_session() as sess:
inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_16(inputs)
sess.run(variables.global_variables_initializer())
output = sess.run(logits)
self.assertTrue(output.any())
def encoder_vgg(x,
enc_final_size,
reuse=False,
scope_prefix='',
hparams=None,
is_training=True):
"""VGG network to use as encoder without the top few layers.
Can be pretrained.
Args:
x: The image to encode. In the range 0 to 1.
enc_final_size: The desired size of the encoding.
reuse: To reuse in variable scope or not.
scope_prefix: The prefix before the scope name.
hparams: The python hparams.
is_training: boolean value indicating if training is happening.
Returns:
The generated image.
"""
with tf.variable_scope(scope_prefix + 'encoder', reuse=reuse):
# Preprocess input
x *= 256
x = x - COLOR_NORMALIZATION_VECTOR
with arg_scope(vgg.vgg_arg_scope()):
# Padding because vgg_16 accepts images of size at least VGG_IMAGE_SIZE.
x = tf.pad(x, [[0, 0], [0, VGG_IMAGE_SIZE - IMG_WIDTH],
[0, VGG_IMAGE_SIZE - IMG_HEIGHT], [0, 0]])
_, end_points = vgg.vgg_16(x,
num_classes=enc_final_size,
is_training=is_training)
pool5_key = [key for key in end_points.keys() if 'pool5' in key]
assert len(pool5_key) == 1
enc = end_points[pool5_key[0]]
# Undoing padding.
enc = tf.slice(enc, [0, 0, 0, 0], [-1, 2, 2, -1])
enc_shape = enc.get_shape().as_list()
enc_shape[0] = -1
enc_size = enc_shape[1] * enc_shape[2] * enc_shape[3]
enc_flat = tf.reshape(enc, (-1, enc_size))
enc_flat = tf.nn.dropout(enc_flat, hparams.enc_keep_prob)
enc_flat = tf.layers.dense(
enc_flat,
enc_final_size,
kernel_initializer=tf.truncated_normal_initializer(stddev=1e-4, ))
if hparams.enc_pred_use_l2norm:
enc_flat = tf.nn.l2_normalize(enc_flat, 1)
return enc_flat
def testBuild(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
with self.test_session():
inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_16(inputs, num_classes)
self.assertEquals(logits.op.name, 'vgg_16/fc8/squeezed')
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
def testFullyConvolutional(self):
batch_size = 1
height, width = 256, 256
num_classes = 1000
with self.test_session():
inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_16(inputs, num_classes, spatial_squeeze=False)
self.assertEquals(logits.op.name, 'vgg_16/fc8/BiasAdd')
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, 2, 2, num_classes])
def testModelVariables(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
with self.test_session():
inputs = random_ops.random_uniform((batch_size, height, width, 3))
vgg.vgg_16(inputs, num_classes)
expected_names = [
'vgg_16/conv1/conv1_1/weights',
'vgg_16/conv1/conv1_1/biases',
'vgg_16/conv1/conv1_2/weights',
'vgg_16/conv1/conv1_2/biases',
'vgg_16/conv2/conv2_1/weights',
'vgg_16/conv2/conv2_1/biases',
'vgg_16/conv2/conv2_2/weights',
'vgg_16/conv2/conv2_2/biases',
'vgg_16/conv3/conv3_1/weights',
'vgg_16/conv3/conv3_1/biases',
'vgg_16/conv3/conv3_2/weights',
'vgg_16/conv3/conv3_2/biases',
'vgg_16/conv3/conv3_3/weights',
'vgg_16/conv3/conv3_3/biases',
'vgg_16/conv4/conv4_1/weights',
'vgg_16/conv4/conv4_1/biases',
'vgg_16/conv4/conv4_2/weights',
'vgg_16/conv4/conv4_2/biases',
'vgg_16/conv4/conv4_3/weights',
'vgg_16/conv4/conv4_3/biases',
'vgg_16/conv5/conv5_1/weights',
'vgg_16/conv5/conv5_1/biases',
'vgg_16/conv5/conv5_2/weights',
'vgg_16/conv5/conv5_2/biases',
'vgg_16/conv5/conv5_3/weights',
'vgg_16/conv5/conv5_3/biases',
'vgg_16/fc6/weights',
'vgg_16/fc6/biases',
'vgg_16/fc7/weights',
'vgg_16/fc7/biases',
'vgg_16/fc8/weights',
'vgg_16/fc8/biases',
]
model_variables = [v.op.name for v in variables_lib.get_model_variables()]
self.assertSetEqual(set(model_variables), set(expected_names))
def testFullyConvolutional(self):
batch_size = 1
height, width = 256, 256
num_classes = 1000
with self.test_session():
inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_16(inputs, num_classes, spatial_squeeze=False)
self.assertEquals(logits.op.name, 'vgg_16/fc8/BiasAdd')
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, 2, 2, num_classes])
def testBuild(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
with self.test_session():
inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_16(inputs, num_classes)
self.assertEquals(logits.op.name, 'vgg_16/fc8/squeezed')
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
def testEvaluation(self):
batch_size = 2
height, width = 224, 224
num_classes = 1000
with self.test_session():
eval_inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_16(eval_inputs, is_training=False)
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
predictions = math_ops.argmax(logits, 1)
self.assertListEqual(predictions.get_shape().as_list(), [batch_size])
def testEvaluation(self):
batch_size = 2
height, width = 224, 224
num_classes = 1000
with self.test_session():
eval_inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_16(eval_inputs, is_training=False)
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
predictions = tf.argmax(logits, 1)
self.assertListEqual(predictions.get_shape().as_list(), [batch_size])
def encoder_vgg(x, enc_final_size, reuse=False, scope_prefix='', hparams=None,
is_training=True):
"""VGG network to use as encoder without the top few layers.
Can be pretrained.
Args:
x: The image to encode. In the range 0 to 1.
enc_final_size: The desired size of the encoding.
reuse: To reuse in variable scope or not.
scope_prefix: The prefix before the scope name.
hparams: The python hparams.
is_training: boolean value indicating if training is happening.
Returns:
The generated image.
"""
with tf.variable_scope(scope_prefix + 'encoder', reuse=reuse):
# Preprocess input
x *= 256
x = x - COLOR_NORMALIZATION_VECTOR
with arg_scope(vgg.vgg_arg_scope()):
# Padding because vgg_16 accepts images of size at least VGG_IMAGE_SIZE.
x = tf.pad(x, [[0, 0], [0, VGG_IMAGE_SIZE - IMG_WIDTH],
[0, VGG_IMAGE_SIZE - IMG_HEIGHT], [0, 0]])
_, end_points = vgg.vgg_16(
x,
num_classes=enc_final_size,
is_training=is_training)
pool5_key = [key for key in end_points.keys() if 'pool5' in key]
assert len(pool5_key) == 1
enc = end_points[pool5_key[0]]
# Undoing padding.
enc = tf.slice(enc, [0, 0, 0, 0], [-1, 2, 2, -1])
enc_shape = enc.get_shape().as_list()
enc_shape[0] = -1
enc_size = enc_shape[1] * enc_shape[2] * enc_shape[3]
enc_flat = tf.reshape(enc, (-1, enc_size))
enc_flat = tf.nn.dropout(enc_flat, hparams.enc_keep_prob)
enc_flat = tf.layers.dense(
enc_flat,
enc_final_size,
kernel_initializer=tf.truncated_normal_initializer(stddev=1e-4,))
if hparams.enc_pred_use_l2norm:
enc_flat = tf.nn.l2_normalize(enc_flat, 1)
return enc_flat
def testTrainEvalWithReuse(self):
train_batch_size = 2
eval_batch_size = 1
train_height, train_width = 224, 224
eval_height, eval_width = 256, 256
num_classes = 1000
with self.test_session():
train_inputs = tf.random_uniform(
(train_batch_size, train_height, train_width, 3))
logits, _ = vgg.vgg_16(train_inputs)
self.assertListEqual(logits.get_shape().as_list(),
[train_batch_size, num_classes])
tf.get_variable_scope().reuse_variables()
eval_inputs = tf.random_uniform(
(eval_batch_size, eval_height, eval_width, 3))
logits, _ = vgg.vgg_16(eval_inputs, is_training=False,
spatial_squeeze=False)
self.assertListEqual(logits.get_shape().as_list(),
[eval_batch_size, 2, 2, num_classes])
logits = tf.reduce_mean(logits, [1, 2])
predictions = tf.argmax(logits, 1)
self.assertEquals(predictions.get_shape().as_list(), [eval_batch_size])
def get_logits_prob(self, batch_input):
"""
Prediction from the model on a single batch.
:param batch_input: the input batch. Must be from size [?, 224, 224, 3]
:return: the logits and probabilities for the batch
"""
with slim.arg_scope(vgg.vgg_arg_scope()):
logits, _ = vgg.vgg_16(batch_input,
num_classes=1000,
is_training=False)
probs = tf.squeeze(tf.nn.softmax(logits))[1:]
return logits, probs
def testTrainEvalWithReuse(self):
train_batch_size = 2
eval_batch_size = 1
train_height, train_width = 224, 224
eval_height, eval_width = 256, 256
num_classes = 1000
with self.test_session():
train_inputs = random_ops.random_uniform(
(train_batch_size, train_height, train_width, 3))
logits, _ = vgg.vgg_16(train_inputs)
self.assertListEqual(logits.get_shape().as_list(),
[train_batch_size, num_classes])
variable_scope.get_variable_scope().reuse_variables()
eval_inputs = random_ops.random_uniform(
(eval_batch_size, eval_height, eval_width, 3))
logits, _ = vgg.vgg_16(
eval_inputs, is_training=False, spatial_squeeze=False)
self.assertListEqual(logits.get_shape().as_list(),
[eval_batch_size, 2, 2, num_classes])
logits = math_ops.reduce_mean(logits, [1, 2])
predictions = math_ops.argmax(logits, 1)
self.assertEquals(predictions.get_shape().as_list(), [eval_batch_size])
def rgb_feature_net(input):
# with tf.variable_scope("rgb_base"):
# arg_scope = resnet_v1.resnet_arg_scope(weight_decay=0.0)
# with slim.arg_scope(arg_scope):
with slim.arg_scope(vgg.vgg_arg_scope()):
# net, end_points = resnet_v1.resnet_v1_50(input, None, global_pool=False, output_stride=8)
# block=end_points['resnet_v1_50/block4']
# block = conv2d_bn_relu(block, num_kernels=512, kernel_size=(1,1), stride=[1,1,1,1], padding='SAME', name='2')
block, _ = vgg.vgg_16(input)
#<todo> feature = upsample2d(block, factor = 4, ...)
tf.summary.histogram('rgb_top_block', block)
feature = block
return feature
def build_model(self, is_training=True, dropout_keep_prob=0.5):
self.inputs = tf.placeholder(real_type(self.FLAGS),
[self.FLAGS.batch_size, 224, 224, 3])
self.targets = tf.placeholder(tf.int32, [self.FLAGS.batch_size])
with slim.arg_scope(vgg_arg_scope()):
logits, endpoints = vgg.vgg_16(self.inputs,
num_classes=self.FLAGS.num_classes)
loss = tf.nn.sparse_softmax_cross_entropy_with_logits(
logits=logits, labels=self.targets)
self.cost = tf.reduce_sum(loss)
self.global_step = tf.contrib.framework.get_or_create_global_step()
self.train_op = tf.train.AdagradOptimizer(0.01).minimize(
self.cost, global_step=self.global_step)
def __init__(self):
self.holder = tf.placeholder(
tf.float32, [None, IMAGE_SIZE, IMAGE_SIZE,
len(CHANNEL_MEAN)],
name='image')
_, self.end_points = vgg.vgg_16(self.holder,
is_training=False,
dropout_keep_prob=1.0)
tf_config = tf.ConfigProto(log_device_placement=False)
tf_config.gpu_options.allow_growth = True
self.sess = tf.Session(config=tf_config)
rospy.on_shutdown(self.sess.close)
saver = tf.train.Saver()
saver.restore(self.sess, VGG16_NTW_PATH)
def __init__(self,
tensor,
keep_prob=1.0,
num_classes=1000,
retrain_layer=[],
weights_path='./weights/vgg_16.ckpt'):
# Call the parent class
Model.__init__(self, tensor, keep_prob, num_classes, retrain_layer,
weights_path)
# TODO This implementation has a problem while validation (is still set to training)
is_training = True if retrain_layer else False
with slim.arg_scope(vgg_arg_scope()):
self.final, self.endpoints = vgg_16(self.tensor,
num_classes=self.num_classes,
is_training=is_training,
dropout_keep_prob=keep_prob)
def build(self):
# Input
self.input = tf.placeholder(
dtype=tf.float32,
shape=[None, self.img_size[0], self.img_size[1], self.img_size[2]])
self.input_mean = tfutils.mean_value(self.input, self.img_mean)
if self.base_net == 'vgg16':
with slim.arg_scope(vgg.vgg_arg_scope()):
outputs, end_points = vgg.vgg_16(self.input_mean,
self.num_classes)
self.prob = tf.nn.softmax(outputs, -1)
self.logits = outputs
elif self.base_net == 'res50':
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
net, end_points = resnet_v1.resnet_v1_50(
self.input_mean,
self.num_classes,
is_training=self.is_train)
self.prob = tf.nn.softmax(net[:, 0, 0, :], -1)
self.logits = net[:, 0, 0, :]
elif self.base_net == 'res101':
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
net, end_points = resnet_v1.resnet_v1_101(
self.input_mean,
self.num_classes,
is_training=self.is_train)
self.prob = tf.nn.softmax(net[:, 0, 0, :], -1)
self.logits = net[:, 0, 0, :]
elif self.base_net == 'res152':
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
net, end_points = resnet_v1.resnet_v1_152(
self.input_mean,
self.num_classes,
is_training=self.is_train)
self.prob = tf.nn.softmax(net[:, 0, 0, :], -1)
self.logits = net[:, 0, 0, :]
else:
raise ValueError(
'base network should be vgg16, res50, -101, -152...')
self.gt = tf.placeholder(dtype=tf.int32, shape=[None])
# self.var_list = tf.trainable_variables()
if self.is_train:
self.loss()
def vgg_encode(inputs,
trainable=False,
is_training=False,
dropout_keep_prob=0.8,
add_summaries=True):
fine_tune = is_training & trainable
net, end_points = vgg_16(inputs,
is_training=fine_tune,
dropout_keep_prob=dropout_keep_prob,
spatial_squeeze=True,
scope='vgg_16')
# Add summaries
if add_summaries:
for v in end_points.values():
tf.contrib.layers.summaries.summarize_activation(v)
return net, end_points
def testEndPoints(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
for is_training in [True, False]:
with ops.Graph().as_default():
inputs = random_ops.random_uniform((batch_size, height, width, 3))
_, end_points = vgg.vgg_16(inputs, num_classes, is_training=is_training)
expected_names = [
'vgg_16/conv1/conv1_1', 'vgg_16/conv1/conv1_2', 'vgg_16/pool1',
'vgg_16/conv2/conv2_1', 'vgg_16/conv2/conv2_2', 'vgg_16/pool2',
'vgg_16/conv3/conv3_1', 'vgg_16/conv3/conv3_2',
'vgg_16/conv3/conv3_3', 'vgg_16/pool3', 'vgg_16/conv4/conv4_1',
'vgg_16/conv4/conv4_2', 'vgg_16/conv4/conv4_3', 'vgg_16/pool4',
'vgg_16/conv5/conv5_1', 'vgg_16/conv5/conv5_2',
'vgg_16/conv5/conv5_3', 'vgg_16/pool5', 'vgg_16/fc6', 'vgg_16/fc7',
'vgg_16/fc8'
]
self.assertSetEqual(set(end_points.keys()), set(expected_names))
def build_model(self):
is_train = self.FLAGS.is_train
dropout_keep_prob = 1.0
if is_train:
dropout_keep_prob = 0.5
images_placeholder = tf.image.resize_images(self.input_placeholder, (224, 224))
with slim.arg_scope(vgg.vgg_arg_scope()):
logits, end_points = vgg.vgg_16(images_placeholder, is_training=is_train, dropout_keep_prob=dropout_keep_prob)
image_features = end_points['vgg_16/fc8']
scene_logits = slim.fully_connected(image_features, 100, activation_fn=None, scope='scene_pred', trainable=True)
multi_hot_logits = slim.fully_connected(image_features, 175, activation_fn=None, scope='multi_hot_logits', trainable=True)
word_embedding_logits = slim.fully_connected(image_features, 300, activation_fn=None, scope='word_embedding_pred', trainable=True)
obj_embedding_size = 40
object_embedding_logits = slim.fully_connected(image_features, obj_embedding_size, activation_fn=None, scope='object_embedding_pred', trainable=True)
outputs = [scene_logits, multi_hot_logits, word_embedding_logits, object_embedding_logits]
return outputs
def get_featuremap(net_name, input, num_classes=None):
'''
#tensorlayer
input = tl.layers.InputLayer(input)
if net_name == 'resnet_v1_50':
with slim.arg_scope(resnet_v1.resnet_arg_scope(weight_decay=cfg.FEATURE_WEIGHT_DECAY)):
featuremap = tl.layers.SlimNetsLayer(prev_layer=input,
slim_layer=resnet_v1.resnet_v1_50,
slim_args={
'num_classes': num_classes,
'is_training': True,
'global_pool': False
},
name='resnet_v1_50'
)
sv = tf.train.Supervisor()
with sv.managed_session() as sess:
a = sess.run(featuremap.all_layers)
print(a)
feature_w_loss = tf.reduce_sum(slim.losses.get_regularization_losses())
return featuremap.outputs, feature_w_loss, featuremap.all_params
if net_name == 'resnet_v1_101':
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
featuremap = tl.layers.SlimNetsLayer(prev_layer=input,
slim_layer=resnet_v1.resnet_v1_101,
slim_args={
'num_classes': num_classes,
'is_training': True,
'global_pool': False
},
name='resnet_v1_101'
)
feature_w_loss = tf.reduce_sum(slim.losses.get_regularization_losses())
return featuremap.outputs, feature_w_loss, featuremap.all_params
if net_name == 'resnet_v1_152':
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
featuremap = tl.layers.SlimNetsLayer(prev_layer=input,
slim_layer=resnet_v1.resnet_v1_152,
slim_args={
'num_classes': num_classes,
'is_training': True,
'global_pool': False
},
name='resnet_v1_152'
)
feature_w_loss = tf.reduce_sum(slim.losses.get_regularization_losses())
return featuremap.outputs, feature_w_loss, featuremap.all_params
if net_name == 'vgg16':
with slim.arg_scope(vgg.vgg_arg_scope()):
featuremap = tl.layers.SlimNetsLayer(prev_layer=input,
slim_layer=vgg.vgg_16,
slim_args={
'num_classes': num_classes,
'is_training': True,
'spatial_squeeze': False
},
name='vgg_16'
)
feature_w_loss = tf.reduce_sum(slim.losses.get_regularization_losses())
return featuremap.outputs, feature_w_loss, featuremap.all_params
'''
#slim
if net_name == 'resnet_v1_50':
with slim.arg_scope(
resnet_v1.resnet_arg_scope(
weight_decay=cfg.FEATURE_WEIGHT_DECAY)):
featuremap, layer_dic = resnet_v1.resnet_v1_50(
inputs=input,
num_classes=num_classes,
is_training=False,
global_pool=False)
if cfg.USE_FPN:
feature_maps_dict = {
'C2': layer_dic[
'resnet_v1_50/block1/unit_2/bottleneck_v1'], # [56, 56]
'C3': layer_dic[
'resnet_v1_50/block2/unit_3/bottleneck_v1'], # [28, 28]
'C4': layer_dic[
'resnet_v1_50/block3/unit_5/bottleneck_v1'], # [14, 14]
'C5': layer_dic['resnet_v1_50/block4'] # [7, 7]
}
return feature_maps_dict
return layer_dic['resnet_v1_50/block3/unit_5/bottleneck_v1']
#return featuremap
if net_name == 'resnet_v1_101':
with slim.arg_scope(
resnet_v1.resnet_arg_scope(
weight_decay=cfg.FEATURE_WEIGHT_DECAY)):
featuremap, layer_dic = resnet_v1.resnet_v1_101(
inputs=input,
num_classes=num_classes,
is_training=True,
global_pool=False)
if cfg.USE_FPN:
feature_maps_dict = {
'C2': layer_dic[
'resnet_v1_101/block1/unit_2/bottleneck_v1'], # [56, 56]
'C3': layer_dic[
'resnet_v1_101/block2/unit_3/bottleneck_v1'], # [28, 28]
'C4': layer_dic[
'resnet_v1_101/block3/unit_22/bottleneck_v1'], # [14, 14]
'C5': layer_dic['resnet_v1_101/block4']
}
return feature_maps_dict
return featuremap
if net_name == 'vgg_16':
with slim.arg_scope(
resnet_v1.resnet_arg_scope(
weight_decay=cfg.FEATURE_WEIGHT_DECAY)):
featuremap, layer_dic = vgg.vgg_16(
inputs=input,
num_classes=7,
is_training=False,
spatial_squeeze=False,
)
return layer_dic['vgg_16/conv5/conv5_3']
def network_vgg_16():
input_shape = [1, 224, 224, 3]
input_ = tf.placeholder(dtype=tf.float32, name='input', shape=input_shape)
net, _end_points = vgg_16(input_, num_classes=1000, is_training=False)
return net
if args.network == "resnet":
# create network
with slim.arg_scope(slim_utils.resnet_arg_scope(is_training=False)):
_, end_points = resnet_v1.resnet_v1_152(images, 1000) # 1000 is the number of softmax class
# define the feature name according slim standard
feature_name = os.path.join("resnet_v1_152", args.feature_name)
# create the output directory
out_dir = os.path.join(args.data_dir, out_file)
if not os.path.exists(out_dir):
os.makedirs(out_dir)
elif args.network == "vgg":
_, end_points = vgg.vgg_16(images)
out_dir = os.path.join(args.data_dir, out_file + ".pkl")
feature_name = os.path.join("vgg_16", args.feature_name)
else:
assert False, "Incorrect Network"
# check that the feature name is correct
assert feature_name in end_points, \
"Invalid Feature name ({}), Must be on of the following {}"\
.format({feature_name}, end_points.keys())
# CPU/GPU option
cpu_pool = Pool(args.no_thread, maxtasksperchild=1000)
def run_training():
config = tf.ConfigProto(allow_soft_placement=True)
sess = tf.Session(config=config)
# sess = tf.Session() # config=tf.ConfigProto(log_device_placement=True))
# create input path and labels np.array from csv annotations
df_annos = pd.read_csv(ANNOS_CSV, index_col=0)
df_annos = df_annos.sample(frac=1).reset_index(
drop=True) # shuffle the whole datasets
if DATA == 'l8':
path_col = ['l8_vis_jpg']
elif DATA == 's1':
path_col = ['s1_vis_jpg']
elif DATA == 'l8s1':
path_col = ['l8_vis_jpg', 's1_vis_jpg']
input_files_train = JPG_DIR + df_annos.loc[df_annos.partition == 'train',
path_col].values
input_labels_train = df_annos.loc[df_annos.partition == 'train',
'pop_density_log2'].values
input_files_val = JPG_DIR + df_annos.loc[df_annos.partition == 'val',
path_col].values
input_labels_val = df_annos.loc[df_annos.partition == 'val',
'pop_density_log2'].values
input_id_train = df_annos.loc[df_annos.partition == 'train',
'village_id'].values
input_id_val = df_annos.loc[df_annos.partition == 'val',
'village_id'].values
print('input_files_train shape:', input_files_train.shape)
train_set_size = len(input_labels_train)
# data input
with tf.device('/cpu:0'):
train_images_batch, train_labels_batch, _ = \
dataset.input_batches(FLAGS.batch_size, FLAGS.output_size, input_files_train, input_labels_train, input_id_train,
IMAGE_HEIGHT, IMAGE_WIDTH, IMAGE_CHANNEL, regression=True, augmentation=True, normalization=True)
val_images_batch, val_labels_batch, _ = \
dataset.input_batches(FLAGS.batch_size, FLAGS.output_size, input_files_val, input_labels_val, input_id_val,
IMAGE_HEIGHT, IMAGE_WIDTH, IMAGE_CHANNEL, regression=True, augmentation=False, normalization=True)
images_placeholder = tf.placeholder(
tf.float32, shape=[None, IMAGE_HEIGHT, IMAGE_WIDTH, IMAGE_CHANNEL])
labels_placeholder = tf.placeholder(tf.float32, shape=[
None,
])
print('finish data input')
TRAIN_BATCHES_PER_EPOCH = int(
train_set_size /
FLAGS.batch_size) # number of training batches/steps in each epoch
MAX_STEPS = TRAIN_BATCHES_PER_EPOCH * FLAGS.max_epoch # total number of training batches/steps
# CNN forward reference
if MODEL == 'vgg':
with slim.arg_scope(
vgg.vgg_arg_scope(weight_decay=FLAGS.weight_decay)):
outputs, _ = vgg.vgg_16(images_placeholder,
num_classes=FLAGS.output_size,
dropout_keep_prob=FLAGS.dropout_keep,
is_training=True)
outputs = tf.squeeze(
outputs
) # change shape from (B,1) to (B,), same as label input
if MODEL == 'resnet':
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
outputs, _ = resnet_v1.resnet_v1_152(images_placeholder,
num_classes=FLAGS.output_size,
is_training=True)
outputs = tf.squeeze(
outputs
) # change shape from (B,1) to (B,), same as label input
# loss
labels_real = tf.pow(2.0, labels_placeholder)
outputs_real = tf.pow(2.0, outputs)
# only loss_log2_mse are used for gradient calculate, model minimize this value
loss_log2_mse = tf.reduce_mean(tf.squared_difference(
labels_placeholder, outputs),
name='loss_log2_mse')
loss_real_rmse = tf.sqrt(tf.reduce_mean(
tf.squared_difference(labels_real, outputs_real)),
name='loss_real_rmse')
loss_real_mae = tf.losses.absolute_difference(labels_real, outputs_real)
tf.summary.scalar('loss_log2_mse', loss_log2_mse)
tf.summary.scalar('loss_real_rmse', loss_real_rmse)
tf.summary.scalar('loss_real_mae', loss_real_mae)
# accuracy (R2)
def r_sqaured(labels, outputs):
sst = tf.reduce_sum(
tf.squared_difference(labels, tf.reduce_mean(labels)))
sse = tf.reduce_sum(tf.squared_difference(labels, outputs))
return (1.0 - tf.div(sse, sst))
r2_log2 = r_sqaured(labels_placeholder, outputs)
r2_real = r_sqaured(labels_real, outputs_real)
tf.summary.scalar('r2_log2', r2_log2)
tf.summary.scalar('r2_real', r2_real)
# determine the model vairables to restore from pre-trained checkpoint
if MODEL == 'vgg':
if DATA == 'l8s1':
model_variables = slim.get_variables_to_restore(
exclude=['vgg_16/fc8', 'vgg_16/conv1'])
else:
model_variables = slim.get_variables_to_restore(
exclude=['vgg_16/fc8'])
if MODEL == 'resnet':
model_variables = slim.get_variables_to_restore(
exclude=['resnet_v1_152/logits', 'resnet_v1_152/conv1'])
# training step and learning rate
global_step = tf.Variable(0, name='global_step',
trainable=False) #, dtype=tf.int64)
learning_rate = tf.train.exponential_decay(
FLAGS.learning_rate, # initial learning rate
global_step=global_step, # current step
decay_steps=MAX_STEPS, # total numbers step to decay
decay_rate=FLAGS.lr_decay_rate
) # final learning rate = FLAGS.learning_rate * decay_rate
tf.summary.scalar('learning_rate', learning_rate)
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
# optimizer = tf.train.RMSPropOptimizer(learning_rate=learning_rate)
# optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate)
# to only update gradient in first and last layer
# vars_update = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, 'vgg_16/(conv1|fc8)')
# print('variables to update in traing: ', vars_update)
train_op = optimizer.minimize(
loss_log2_mse, global_step=global_step) #, var_list = vars_update)
# summary output in tensorboard
summary = tf.summary.merge_all()
summary_writer_train = tf.summary.FileWriter(
os.path.join(LOG_DIR, 'log_train'), sess.graph)
summary_writer_val = tf.summary.FileWriter(
os.path.join(LOG_DIR, 'log_val'), sess.graph)
# variable initialize
init = tf.global_variables_initializer()
sess.run(init)
# restore the model from pre-trained checkpoint
restorer = tf.train.Saver(model_variables)
restorer.restore(sess, PRETRAIN_WEIGHTS)
print('loaded pre-trained weights: ', PRETRAIN_WEIGHTS)
# saver object to save checkpoint during training
saver = tf.train.Saver(tf.global_variables(), max_to_keep=10)
print('start training...')
epoch = 0
best_r2 = -float('inf')
for step in xrange(MAX_STEPS):
if step % TRAIN_BATCHES_PER_EPOCH == 0:
epoch += 1
start_time = time.time() # record the time used for each batch
images_out, labels_out = sess.run(
[train_images_batch,
train_labels_batch]) # inputs of this batch, numpy array format
duration_batch = time.time() - start_time
if step == 0:
print("finished reading batch data")
print("images_out shape:", images_out.shape)
feed_dict = {
images_placeholder: images_out,
labels_placeholder: labels_out
}
_, train_loss, train_accuracy, train_outputs, lr = \
sess.run([train_op, loss_log2_mse, r2_log2, outputs, learning_rate], feed_dict=feed_dict)
duration = time.time() - start_time
if step % 10 == 0 or (
step + 1) == MAX_STEPS: # print traing loss every 10 batches
print('Step %d epoch %d lr %.3e: log2 MSE loss = %.4f log2 R2 = %.4f (%.3f sec, %.3f sec(each batch))' \
% (step, epoch, lr, train_loss, train_accuracy, duration*10, duration_batch))
summary_str = sess.run(summary, feed_dict=feed_dict)
summary_writer_train.add_summary(summary_str, step)
summary_writer_train.flush()
if step % 50 == 0 or (
step + 1
) == MAX_STEPS: # calculate and print validation loss every 50 batches
images_out, labels_out = sess.run(
[val_images_batch, val_labels_batch])
feed_dict = {
images_placeholder: images_out,
labels_placeholder: labels_out
}
val_loss, val_accuracy = sess.run([loss_log2_mse, r2_log2],
feed_dict=feed_dict)
print('Step %d epoch %d: val log2 MSE = %.4f val log2 R2 = %.4f ' %
(step, epoch, val_loss, val_accuracy))
summary_str = sess.run(summary, feed_dict=feed_dict)
summary_writer_val.add_summary(summary_str, step)
summary_writer_val.flush()
# in each epoch, if the validation R2 is higher than best R2, save the checkpoint
if step % (TRAIN_BATCHES_PER_EPOCH -
TRAIN_BATCHES_PER_EPOCH % 50) == 0:
if val_accuracy > best_r2:
best_r2 = val_accuracy
checkpoint_file = os.path.join(LOG_DIR, 'model.ckpt')
saver.save(sess,
checkpoint_file,
global_step=step,
write_state=True)
def main(argv=None):
# 加载处理好的数据
processed_data = np.load(INPUT_DATA)
training_images = processed_data[0]
n_training_examples = len(training_images)
training_labels = processed_data[1]
validation_images = processed_data[2]
validation_labels = processed_data[3]
testing_images = processed_data[4]
testing_labels = processed_data[5]
print('%d training, %d validation, %d testing' %
(n_training_examples, len(validation_labels), len(testing_labels)))
# 定义vgg16的输入
images = tf.placeholder(tf.float32, [None, 224, 224, 3],
name='input_image')
labels = tf.placeholder(tf.int64, [None], name='labels')
# 定义vgg16模型
with slim.arg_scope(vgg.vgg_arg_scope()):
logits, _ = vgg.vgg_16(images, num_classes=N_CLASSES)
# 损失函数
loss_fun = tf.losses.softmax_cross_entropy(tf.one_hot(labels, N_CLASSES),
logits)
# 训练
# train_step = tf.train.RMSPropOptimizer(LEARNING_RATE).minimize(tf.losses.get_total_loss())
# 只训练最后一层
train_step = tf.train.RMSPropOptimizer(LEARNING_RATE).minimize(
tf.losses.get_total_loss(), var_list=get_trainable_variables())
# 正确率
with tf.variable_scope('evaluation'):
correct_prediction = tf.equal(tf.argmax(logits, 1), labels)
evaluation_step = tf.reduce_mean(
tf.cast(correct_prediction, tf.float32))
ckpt = tf.train.get_checkpoint_state(SAVE_PATH)
if ckpt and ckpt.model_checkpoint_path:
# 加载之前训练的参数继续训练
variables_to_restore = slim.get_model_variables()
print('continue training from %s' % ckpt)
step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
step = int(step)
ckpt = ckpt.model_checkpoint_path
else:
# 没有训练数据，就先迁移一部分训练好的
ckpt = TRAINED_CKPT_FILE
variables_to_restore = get_tuned_variable()
print('loading tuned variables from %s' % TRAINED_CKPT_FILE)
step = 0
load_fn = slim.assign_from_checkpoint_fn(ckpt,
variables_to_restore,
ignore_missing_vars=True)
# 开启会话训练
saver = tf.train.Saver()
with tf.Session() as sess:
# 初始化所有参数
init = tf.global_variables_initializer()
sess.run(init)
load_fn(sess)
start = 0
end = BATCH
for i in range(step + 1, step + 1 + STEPS):
start_time = time.time()
# 运行训练,不会更新所有参数
_, loss_val = sess.run(
[train_step, loss_fun],
feed_dict={
images: training_images[start:end],
labels: training_labels[start:end]
})
duration = time.time() - start_time
#print('current train step duration %.3f' % duration)
if i % 10 == 0:
print('after %d train step, loss value is: %.4f' %
(i, loss_val))
# 输出日志
if i % 100 == 0:
saver.save(sess, TRAIN_FILE, global_step=i)
validation_accuracy = sess.run(evaluation_step,
feed_dict={
images: validation_images,
labels: validation_labels
})
print('Step %d Validation accuracy = %.1f%%' %
(i, validation_accuracy * 100.0))
start = end
if start == n_training_examples:
start = 0
end = start + BATCH
if end > n_training_examples:
end = n_training_examples
# 在测试集上测试正确率
test_accuracy = sess.run(evaluation_step,
feed_dict={
images: testing_images,
labels: testing_labels
})
print('Final test accuracy = %.1f%%' % (test_accuracy * 100.0))
def network():
input = tf.placeholder(dtype=tf.float32, name='input', shape=input_shape)
net, end_points = vgg_16(input, spatial_squeeze = False, num_classes=1000, is_training=False)
return net
mode=args.mode, network=args.network, feature_name=args.feature_name, size=args.img_size)
print("Create networks...")
if args.network == "resnet":
ft_output = resnet.create_resnet(images,
resnet_out=args.feature_name,
resnet_version=args.resnet_version,
is_training=False)
# create network
with slim.arg_scope(slim_utils.resnet_arg_scope(is_training=False)):
_, end_points = resnet_v1.resnet_v1_152(images, 1000) # 1000 is the number of softmax class
elif args.network == "vgg":
_, end_points = vgg.vgg_16(images, is_training=False, dropout_keep_prob=1.0)
ft_name = os.path.join("vgg_16", args.feature_name)
ft_output = end_points[ft_name]
else:
assert False, "Incorrect Network"
extract_features(
img_input = images,
ft_output = ft_output,
dataset_cstor = dataset_cstor,
dataset_args = {"folder": args.data_dir, "image_builder":image_builder, "crop_builder":crop_builder, "dataset_name": args.dataset_name},
batchifier_cstor = OracleBatchifier,
out_dir = args.out_dir,
set_type = args.set_type,
network_ckpt=args.ckpt,
def get_model(ref_dict, num_point, is_training, bn=False, bn_decay=None, img_size = (137,137), wd=1e-5, FLAGS=None):
ref_img = ref_dict['imgs']
ref_pc = ref_dict['pc']
ref_sample_pc = ref_dict['sample_pc']
ref_sample_pc_rot = ref_dict['sample_pc_rot']
trans_mat = ref_dict['trans_mat']
K = ref_dict['K']
RT = ref_dict['RT']
gt_xyshift = ref_dict['shifts']
batch_size = ref_img.get_shape()[0].value
# endpoints
end_points = {}
end_points['ref_pc'] = ref_pc
end_points['RT'] = RT
end_points['K'] = K
end_points['gt_xyshift'] = gt_xyshift
end_points['trans_mat'] = trans_mat
end_points['sample_pc'] = ref_sample_pc #* 10
# Image extract features
if ref_img.shape[1] != 224 or ref_img.shape[2] != 224:
ref_img = tf.image.resize_bilinear(ref_img, [224, 224])
end_points['ref_img'] = ref_img
# vgg.vgg_16.default_image_size = (224, 224)
with slim.arg_scope([slim.conv2d],
weights_regularizer=slim.l2_regularizer(wd)):
ref_feats_embedding, vgg_end_points = vgg.vgg_16(ref_img, num_classes=1024, is_training=False, scope='vgg_16', spatial_squeeze=False)
ref_feats_embedding_cnn = tf.squeeze(ref_feats_embedding, axis = [1,2])
end_points['embedding'] = ref_feats_embedding_cnn
print(vgg_end_points.keys())
with tf.variable_scope("cameraprediction") as scope:
if FLAGS.shift:
pred_rotation, pred_translation, pred_RT, pred_xyshift = posenet.get_cam_mat_shft(ref_feats_embedding_cnn, is_training, batch_size, bn, bn_decay, wd)
end_points['pred_rotation'] = pred_rotation
end_points['pred_translation'] = pred_translation
end_points['pred_RT'] = pred_RT
end_points['pred_xyshift'] = pred_xyshift
else:
pred_rotation, pred_translation, pred_RT = posenet.get_cam_mat(ref_feats_embedding_cnn, is_training, batch_size, bn, bn_decay, wd)
end_points['pred_rotation'] = pred_rotation
end_points['pred_translation'] = pred_translation
end_points['pred_RT'] = pred_RT
end_points['pred_xyshift'] = None
pred_xyshift = None
print('trans_mat', trans_mat.shape)
sample_img_points, gt_xy = get_img_points(ref_sample_pc, trans_mat, gt_xyshift, FLAGS)
end_points['sample_img_points'] = sample_img_points
end_points['gt_xy'] = gt_xy
K_transpose = tf.transpose(K, perm=[0, 2, 1])
pred_trans_mat = tf.matmul(pred_RT, K_transpose)
pred_sample_img_points, pred_xy = get_img_points(ref_sample_pc, pred_trans_mat, pred_xyshift, FLAGS)
end_points['pred_sample_img_points'] = pred_sample_img_points
end_points['pred_trans_mat'] = pred_trans_mat
end_points['pred_xy'] = pred_xy
print("gt_xy, pred_xy", gt_xy.get_shape(), pred_xy.get_shape())
return end_points
def get_model(input_pls,
is_training,
bn=False,
bn_decay=None,
img_size=224,
FLAGS=None):
if FLAGS.act == "relu":
activation_fn = tf.nn.relu
elif FLAGS.act == "elu":
activation_fn = tf.nn.elu
input_imgs = input_pls['imgs']
input_pnts = input_pls['pnts']
input_gvfs = input_pls['gvfs']
input_onedge = input_pls['onedge']
input_trans_mat = input_pls['trans_mats']
input_obj_rot_mats = input_pls['obj_rot_mats']
batch_size = input_imgs.get_shape()[0].value
# endpoints
end_points = {}
end_points['pnts'] = input_pnts
if FLAGS.rot:
end_points['gt_gvfs_xyz'] = tf.matmul(input_gvfs, input_obj_rot_mats)
end_points['pnts_rot'] = tf.matmul(input_pnts, input_obj_rot_mats)
else:
end_points['gt_gvfs_xyz'] = input_gvfs #* 10
end_points['pnts_rot'] = input_pnts
if FLAGS.edgeweight != 1.0:
end_points['onedge'] = input_onedge
input_pnts_rot = end_points['pnts_rot']
end_points['imgs'] = input_imgs # B*H*W*3|4
# Image extract features
if input_imgs.shape[1] != img_size or input_imgs.shape[2] != img_size:
if FLAGS.alpha:
ref_img_rgb = tf.compat.v1.image.resize_bilinear(
input_imgs[:, :, :, :3], [img_size, img_size])
ref_img_alpha = tf.image.resize_nearest_neighbor(
tf.expand_dims(input_imgs[:, :, :, 3], axis=-1),
[img_size, img_size])
ref_img = tf.concat([ref_img_rgb, ref_img_alpha], axis=-1)
else:
ref_img = tf.compat.v1.image.resize_bilinear(
input_imgs, [img_size, img_size])
else:
ref_img = input_imgs
end_points['resized_ref_img'] = ref_img
if FLAGS.encoder[:6] == "vgg_16":
vgg.vgg_16.default_image_size = img_size
with slim.arg_scope([slim.conv2d],
weights_regularizer=slim.l2_regularizer(FLAGS.wd)):
ref_feats_embedding, encdr_end_points = vgg.vgg_16(
ref_img,
num_classes=FLAGS.num_classes,
is_training=False,
scope='vgg_16',
spatial_squeeze=False)
elif FLAGS.encoder == "sim_res":
ref_feats_embedding, encdr_end_points = res_sim_encoder.res_sim_encoder(
ref_img,
FLAGS.batch_size,
is_training=is_training,
activation_fn=activation_fn,
bn=bn,
bn_decay=bn_decay,
wd=FLAGS.wd)
elif FLAGS.encoder == "resnet_v1_50":
resnet_v1.default_image_size = img_size
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
ref_feats_embedding, encdr_end_points = resnet_v1.resnet_v1_50(
ref_img,
FLAGS.num_classes,
is_training=is_training,
scope='resnet_v1_50')
scopelst = [
"resnet_v1_50/block1", "resnet_v1_50/block2",
"resnet_v1_50/block3", 'resnet_v1_50/block4'
]
elif FLAGS.encoder == "resnet_v1_101":
resnet_v1.default_image_size = img_size
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
ref_feats_embedding, encdr_end_points = resnet_v1.resnet_v1_101(
ref_img,
FLAGS.num_classes,
is_training=is_training,
scope='resnet_v1_101')
scopelst = [
"resnet_v1_101/block1", "resnet_v1_101/block2",
"resnet_v1_101/block3", 'resnet_v1_101/block4'
]
elif FLAGS.encoder == "resnet_v2_50":
resnet_v2.default_image_size = img_size
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
ref_feats_embedding, encdr_end_points = resnet_v2.resnet_v2_50(
ref_img,
FLAGS.num_classes,
is_training=is_training,
scope='resnet_v2_50')
scopelst = [
"resnet_v2_50/block1", "resnet_v2_50/block2",
"resnet_v2_50/block3", 'resnet_v2_50/block4'
]
elif FLAGS.encoder == "resnet_v2_101":
resnet_v2.default_image_size = img_size
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
ref_feats_embedding, encdr_end_points = resnet_v2.resnet_v2_101(
ref_img,
FLAGS.num_classes,
is_training=is_training,
scope='resnet_v2_101')
scopelst = [
"resnet_v2_101/block1", "resnet_v2_101/block2",
"resnet_v2_101/block3", 'resnet_v2_101/block4'
]
end_points['img_embedding'] = ref_feats_embedding
point_img_feat = None
gvfs_feat = None
sample_img_points = get_img_points(input_pnts,
input_trans_mat) # B * N * 2
if FLAGS.img_feat_onestream:
with tf.compat.v1.variable_scope("sdfimgfeat") as scope:
if FLAGS.encoder[:3] == "vgg":
conv1 = tf.compat.v1.image.resize_bilinear(
encdr_end_points['vgg_16/conv1/conv1_2'],
(FLAGS.img_h, FLAGS.img_w))
point_conv1 = tf.contrib.resampler.resampler(
conv1, sample_img_points)
conv2 = tf.compat.v1.image.resize_bilinear(
encdr_end_points['vgg_16/conv2/conv2_2'],
(FLAGS.img_h, FLAGS.img_w))
point_conv2 = tf.contrib.resampler.resampler(
conv2, sample_img_points)
conv3 = tf.compat.v1.image.resize_bilinear(
encdr_end_points['vgg_16/conv3/conv3_3'],
(FLAGS.img_h, FLAGS.img_w))
point_conv3 = tf.contrib.resampler.resampler(
conv3, sample_img_points)
if FLAGS.encoder[-7:] != "smaller":
conv4 = tf.compat.v1.image.resize_bilinear(
encdr_end_points['vgg_16/conv4/conv4_3'],
(FLAGS.img_h, FLAGS.img_w))
point_conv4 = tf.contrib.resampler.resampler(
conv4, sample_img_points)
point_img_feat = tf.concat(axis=2,
values=[
point_conv1, point_conv2,
point_conv3, point_conv4
]) # small
else:
print("smaller vgg")
point_img_feat = tf.concat(
axis=2, values=[point_conv1, point_conv2,
point_conv3]) # small
elif FLAGS.encoder[:3] == "res":
# print(encdr_end_points.keys())
conv1 = tf.compat.v1.image.resize_bilinear(
encdr_end_points[scopelst[0]], (FLAGS.img_h, FLAGS.img_w))
point_conv1 = tf.contrib.resampler.resampler(
conv1, sample_img_points)
conv2 = tf.compat.v1.image.resize_bilinear(
encdr_end_points[scopelst[1]], (FLAGS.img_h, FLAGS.img_w))
point_conv2 = tf.contrib.resampler.resampler(
conv2, sample_img_points)
conv3 = tf.compat.v1.image.resize_bilinear(
encdr_end_points[scopelst[2]], (FLAGS.img_h, FLAGS.img_w))
point_conv3 = tf.contrib.resampler.resampler(
conv3, sample_img_points)
# conv4 = tf.compat.v1.image.resize_bilinear(encdr_end_points[scopelst[3]], (FLAGS.img_h, FLAGS.img_w))
# point_conv4 = tf.contrib.resampler.resampler(conv4, sample_img_points)
point_img_feat = tf.concat(
axis=2, values=[point_conv1, point_conv2, point_conv3])
else:
conv1 = tf.compat.v1.image.resize_bilinear(
encdr_end_points[0], (FLAGS.img_h, FLAGS.img_w))
point_conv1 = tf.contrib.resampler.resampler(
conv1, sample_img_points)
conv2 = tf.compat.v1.image.resize_bilinear(
encdr_end_points[1], (FLAGS.img_h, FLAGS.img_w))
point_conv2 = tf.contrib.resampler.resampler(
conv2, sample_img_points)
conv3 = tf.compat.v1.image.resize_bilinear(
encdr_end_points[2], (FLAGS.img_h, FLAGS.img_w))
point_conv3 = tf.contrib.resampler.resampler(
conv3, sample_img_points)
# conv4 = tf.compat.v1.image.resize_bilinear(encdr_end_points[scopelst[3]], (FLAGS.img_h, FLAGS.img_w))
# point_conv4 = tf.contrib.resampler.resampler(conv4, sample_img_points)
point_img_feat = tf.concat(
axis=2, values=[point_conv1, point_conv2, point_conv3])
print("point_img_feat.shape", point_img_feat.get_shape())
point_img_feat = tf.expand_dims(point_img_feat, axis=2)
if FLAGS.decoder == "att":
gvfs_feat = gvfnet.get_gvf_att_imgfeat(
input_pnts_rot,
ref_feats_embedding,
point_img_feat,
is_training,
batch_size,
bn,
bn_decay,
wd=FLAGS.wd,
activation_fn=activation_fn)
elif FLAGS.decoder == "skip":
gvfs_feat = gvfnet.get_gvf_basic_imgfeat_onestream_skip(
input_pnts_rot,
ref_feats_embedding,
point_img_feat,
is_training,
batch_size,
bn,
bn_decay,
wd=FLAGS.wd,
activation_fn=activation_fn)
else:
gvfs_feat = gvfnet.get_gvf_basic_imgfeat_onestream(
input_pnts_rot,
ref_feats_embedding,
point_img_feat,
is_training,
batch_size,
bn,
bn_decay,
wd=FLAGS.wd,
activation_fn=activation_fn)
else:
if not FLAGS.multi_view:
with tf.compat.v1.variable_scope("sdfprediction") as scope:
gvfs_feat = gvfnet.get_gvf_basic(input_pnts_rot,
ref_feats_embedding,
is_training,
batch_size,
bn,
bn_decay,
wd=FLAGS.wd,
activation_fn=activation_fn)
end_points['pred_gvfs_xyz'], end_points['pred_gvfs_dist'], end_points[
'pred_gvfs_direction'] = None, None, None
if FLAGS.XYZ:
end_points['pred_gvfs_xyz'] = gvfnet.xyz_gvfhead(
gvfs_feat, batch_size, wd=FLAGS.wd, activation_fn=activation_fn)
end_points['pred_gvfs_dist'] = tf.sqrt(
tf.reduce_sum(tf.square(end_points['pred_gvfs_xyz']),
axis=2,
keepdims=True))
end_points[
'pred_gvfs_direction'] = end_points['pred_gvfs_xyz'] / tf.maximum(
end_points['pred_gvfs_dist'], 1e-6)
else:
end_points['pred_gvfs_dist'], end_points[
'pred_gvfs_direction'] = gvfnet.dist_direct_gvfhead(
gvfs_feat,
batch_size,
wd=FLAGS.wd,
activation_fn=activation_fn)
end_points['pred_gvfs_xyz'] = end_points[
'pred_gvfs_direction'] * end_points['pred_gvfs_dist']
end_points["sample_img_points"] = sample_img_points
# end_points["ref_feats_embedding"] = ref_feats_embedding
end_points["point_img_feat"] = point_img_feat
return end_points
def get_model(ref_dict,
num_point,
is_training,
bn=False,
bn_decay=None,
img_size=(137, 137),
wd=1e-5,
FLAGS=None):
ref_img = ref_dict['imgs']
ref_pc = ref_dict['pc']
ref_sample_pc = ref_dict['sample_pc']
ref_sample_pc_rot = ref_dict['sample_pc_rot']
trans_mat = ref_dict['trans_mat']
K = ref_dict['K']
norm_params = ref_dict['norm_params']
rot_mat_inv = ref_dict['rot_mat_inv']
regress_mat = ref_dict['regress_mat']
gt_xyshift = ref_dict['shifts']
batch_size = ref_img.get_shape()[0].value
norm_mat_inv = get_inverse_norm_matrix(norm_params, batch_size)
# endpoints
end_points = {}
end_points['ref_pc'] = ref_pc
end_points['regress_mat'] = regress_mat
end_points['K'] = K
end_points['gt_xyshift'] = gt_xyshift
end_points['trans_mat'] = trans_mat
end_points['sample_pc'] = ref_sample_pc #* 10
# Image extract features
if ref_img.shape[1] != 224 or ref_img.shape[2] != 224:
ref_img = tf.image.resize_bilinear(ref_img, [224, 224])
else:
print("image size:", img_size)
end_points['ref_img'] = ref_img
# vgg.vgg_16.default_image_size = (224, 224)
with slim.arg_scope([slim.conv2d],
weights_regularizer=slim.l2_regularizer(wd)):
ref_feats_embedding, vgg_end_points = vgg.vgg_16(ref_img,
num_classes=1024,
is_training=False,
scope='vgg_16',
spatial_squeeze=False)
ref_feats_embedding_cnn = tf.squeeze(ref_feats_embedding, axis=[1, 2])
end_points['embedding'] = ref_feats_embedding_cnn
print(vgg_end_points.keys())
with tf.variable_scope("cameraprediction") as scope:
if FLAGS.shift:
pred_rotation, pred_translation, pred_RT, pred_xyshift = posenet.get_cam_mat_shft(
ref_feats_embedding_cnn, is_training, batch_size, bn, bn_decay,
wd)
end_points['pred_rotation'] = pred_rotation
end_points['pred_translation'] = pred_translation
end_points['pred_RT'] = pred_RT
end_points['pred_xyshift'] = pred_xyshift
elif FLAGS.space_shift:
pred_rotation, pred_translation, pred_RT, predxyzshift = posenet.get_cam_mat_spaceshft(
ref_feats_embedding_cnn, is_training, batch_size, bn, bn_decay,
wd)
end_points['pred_rotation'] = pred_rotation
end_points['pred_translation'] = pred_translation
end_points['pred_RT'] = pred_RT
end_points['pred_xyshift'] = None
pred_xyshift = None
else:
pred_rotation, pred_translation, pred_RT = posenet.get_cam_mat(
ref_feats_embedding_cnn, is_training, batch_size, bn, bn_decay,
wd)
end_points['pred_rotation'] = pred_rotation
end_points['pred_translation'] = pred_translation
end_points['pred_RT'] = pred_RT
end_points['pred_xyshift'] = None
pred_xyshift = None
print('trans_mat', trans_mat.shape)
sample_img_points, gt_xy = get_img_points(ref_sample_pc,
trans_mat,
gt_xyshift,
FLAGS,
img_size=img_size)
end_points['sample_img_points'] = sample_img_points
end_points['gt_xy'] = gt_xy
# K, RT, rot_mat, W2O_mat, norm_mat, pred_transmat = inverse norm_mat * inverse W2O_mat * inverse rot_mat * pred_RT * K inverse
if FLAGS.space_shift:
pred_regress_mat = norm_mat_inv @ predxyzshift @ rot_mat_inv @ pred_RT
else:
pred_regress_mat = norm_mat_inv @ rot_mat_inv @ pred_RT
pred_trans_mat = pred_regress_mat @ K
pred_sample_img_points, pred_xy = get_img_points(ref_sample_pc,
pred_trans_mat,
pred_xyshift,
FLAGS,
img_size=img_size)
end_points['pred_sample_img_points'] = pred_sample_img_points
end_points['pred_trans_mat'] = pred_trans_mat
end_points['pred_regress_mat'] = pred_regress_mat
end_points['pred_xy'] = pred_xy
print("gt_xy, pred_xy", gt_xy.get_shape(), pred_xy.get_shape())
return end_points
