def pack_loss(labels, logits,
#num_classes=81,
num_classes=91,
base_anchors=9,
loss_weights=[0.2, 0.2, 1.0, 0.2, 1.0],
**kwargs
):
#'targets': ['height', 'width', 'num_objects', 'labels', 'segmentation_masks', 'bboxes'],
#print(labels)
ih = labels[0]
iw = labels[1]
num_instances = labels[2]
gt_boxes = labels[5]
#labels_s = labels[3]
#gt_boxes = tf.concat([gt_boxes, tf.cast(labels_s, tf.float64)], 1)
#gt_boxes = tf.Print(gt_boxes, [tf.shape(gt_boxes)], message = 'Box shape loss', summarize = 4)
gt_masks = labels[4]
#gt_masks = tf.Print(gt_masks, [tf.shape(gt_masks)], message = 'Mask shape loss', summarize = 4)
loss, losses, batch_info = pyramid_network.build_losses(logits['pyramid'], logits['outputs'],
gt_boxes, gt_masks,
num_classes=num_classes, base_anchors=base_anchors,
rpn_box_lw=loss_weights[0], rpn_cls_lw=loss_weights[1],
refined_box_lw=loss_weights[2], refined_cls_lw=loss_weights[3],
mask_lw=loss_weights[4])
#outputs['losses'] = losses
#outputs['total_loss'] = loss
#outputs['batch_info'] = batch_info
losses = tf.get_collection(tf.GraphKeys.LOSSES)
regular_losses = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
regular_loss = tf.add_n(regular_losses)
out_loss = tf.add_n(losses)
total_loss = tf.add_n(losses + regular_losses)
return total_loss
outputs = pyramid_network.build_heads(pyramid,
ih,
iw,
num_classes=81,
base_anchors=9,
is_training=True,
gt_boxes=gt_boxes)
## losses
loss, losses, batch_info = pyramid_network.build_losses(
pyramid,
outputs,
gt_boxes,
gt_masks,
num_classes=81,
base_anchors=9,
rpn_box_lw=0.1,
rpn_cls_lw=0.2,
refined_box_lw=2.0,
refined_cls_lw=0.1,
mask_lw=0.2)
## optimization
learning_rate = _configure_learning_rate(82783, global_step)
optimizer = _configure_optimizer(learning_rate)
summaries.add(tf.summary.scalar('learning_rate', learning_rate))
for loss in tf.get_collection(tf.GraphKeys.LOSSES):
summaries.add(tf.summary.scalar('losses/%s' % loss.op.name, loss))
loss = tf.get_collection(tf.GraphKeys.LOSSES)
regular_loss = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
#!/usr/bin/env python
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import functools
import tensorflow as tf
import tensorflow.contrib.slim as slim
from libs.logs.log import LOG
import libs.nets.resnet_v1 as resnet_v1
resnet50 = resnet_v1.resnet_v1_50
images = tf.placeholder(tf.float32, [16, 224, 224, 3], name='image')
logits, end_points = resnet50(images, 1000, is_training=False)
end_points['inputs'] = images
for x in sorted(end_points.keys()):
print (x, end_points[x].name, end_points[x].shape)
import libs.nets.pyramid_network as pyramid_network
pyramid = pyramid_network.build_pyramid('resnet50', end_points)
for p in pyramid:
print (p, pyramid[p])
outputs = pyramid_network.build_heads(pyramid, num_classes=81, base_anchors=15, is_training=True)
outputs = pyramid_network.build_losses(pyramid, outputs)
is_training=True)
if DEBUG:
gt_boxes = np.random.randint(0, 200, (32, 2))
shape = np.random.randint(10, 30, (32, 2))
classes = np.random.randint(0, 81, (32, ))
gt_boxes = np.hstack((gt_boxes, gt_boxes + shape, classes[:,
np.newaxis]))
gt_boxes = gt_boxes.astype(np.float32)
gt_masks = np.zeros((32, 224, 224), np.int32)
gt_masks[:, 100:150, 100:150] = 1
## losses
outputs = pyramid_network.build_losses(pyramid,
outputs,
gt_boxes,
gt_masks,
num_classes=81,
base_anchors=15)
## optimization
learning_rate = _configure_learning_rate(82783, global_step)
optimizer = _configure_optimizer(learning_rate)
summaries.add(tf.summary.scalar('learning_rate', learning_rate))
for loss in tf.get_collection(tf.GraphKeys.LOSSES):
summaries.add(tf.summary.scalar('losses/%s' % loss.op.name, loss))
learning_rate = _configure_learning_rate(82783, global_step)
optimizer = _configure_optimizer(learning_rate)
loss = tf.get_collection(tf.GraphKeys.LOSSES)
regular_loss = tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)
total_loss = tf.add_n(loss + regular_loss)
import tensorflow as tf
import tensorflow.contrib.slim as slim
from libs.logs.log import LOG
import libs.nets.resnet_v1 as resnet_v1
resnet50 = resnet_v1.resnet_v1_50
images = tf.placeholder(tf.float32, [1, 224, 224, 3], name='image')
logits, end_points = resnet50(images, 1000, is_training=False)
end_points['inputs'] = images
for x in sorted(end_points.keys()):
print (x, end_points[x].name, end_points[x].shape)
import libs.nets.pyramid_network as pyramid_network
pyramid = pyramid_network.build_pyramid('resnet50', end_points)
for p in pyramid:
print (p, pyramid[p])
outputs = pyramid_network.build_heads(pyramid, num_classes=81, base_anchors=15, is_training=True)
gt_boxes = np.random.randint(0, 200, (32, 2))
shape = np.random.randint(10, 30, (32, 2))
classes = np.random.randint(0, 81, (32,))
gt_boxes = np.hstack((gt_boxes, gt_boxes + shape, classes[:, np.newaxis]))
gt_masks = np.zeros((32, 224, 224), np.int32)
gt_masks[:, 100:150, 100:150 ] = 1
outputs = pyramid_network.build_losses(pyramid, outputs,
gt_boxes.astype(np.float32), gt_masks.astype(np.float32),
num_classes=81, base_anchors=15)