[GRASS-SVN] r73132 - in grass-addons/grass7/imagery/i.ann.maskrcnn: i.ann.maskrcnn.train maskrcnnlib
svn_grass at osgeo.org
svn_grass at osgeo.org
Tue Aug 21 12:41:15 PDT 2018
Author: pesekon2
Date: 2018-08-21 12:41:15 -0700 (Tue, 21 Aug 2018)
New Revision: 73132
Modified:
grass-addons/grass7/imagery/i.ann.maskrcnn/i.ann.maskrcnn.train/i.ann.maskrcnn.train.py
grass-addons/grass7/imagery/i.ann.maskrcnn/maskrcnnlib/config.py
grass-addons/grass7/imagery/i.ann.maskrcnn/maskrcnnlib/model.py
grass-addons/grass7/imagery/i.ann.maskrcnn/maskrcnnlib/utils.py
Log:
allow modifying FPN size, parameters upgrades
Modified: grass-addons/grass7/imagery/i.ann.maskrcnn/i.ann.maskrcnn.train/i.ann.maskrcnn.train.py
===================================================================
--- grass-addons/grass7/imagery/i.ann.maskrcnn/i.ann.maskrcnn.train/i.ann.maskrcnn.train.py 2018-08-21 16:57:50 UTC (rev 73131)
+++ grass-addons/grass7/imagery/i.ann.maskrcnn/i.ann.maskrcnn.train/i.ann.maskrcnn.train.py 2018-08-21 19:41:15 UTC (rev 73132)
@@ -40,7 +40,7 @@
#% label: Path to the dataset with images and masks
#% required: yes
#%end
-#%option
+#%option G_OPT_F_INPUT
#% key: model
#% type: string
#% label: Path to the .h5 file to use as initial values
Modified: grass-addons/grass7/imagery/i.ann.maskrcnn/maskrcnnlib/config.py
===================================================================
--- grass-addons/grass7/imagery/i.ann.maskrcnn/maskrcnnlib/config.py 2018-08-21 16:57:50 UTC (rev 73131)
+++ grass-addons/grass7/imagery/i.ann.maskrcnn/maskrcnnlib/config.py 2018-08-21 19:41:15 UTC (rev 73132)
@@ -31,6 +31,12 @@
# are based on a Resnet101 backbone.
BACKBONE_STRIDES = [4, 8, 16, 32, 64]
+ # Size of the fully-connected layers in the classification graph
+ FPN_CLASSIF_FC_LAYERS_SIZE = 1024
+
+ # Size of the top-down layers used to build the feature pyramid
+ TOP_DOWN_PYRAMID_SIZE = 256
+
## RPN ##
# Length of square anchor side in pixels
RPN_ANCHOR_SCALES = (32, 64, 128, 256, 512)
@@ -183,11 +189,15 @@
self.BATCH_SIZE = self.IMAGES_PER_GPU * self.GPU_COUNT
# Set the backbone architecture
+ # Use a pedefined one or provide a callable that should have the
+ # signature of model.resnet_graph. If you do so, you need to supply
+ # a callable to COMPUTE_BACKBONE_SHAPE as well
self.BACKBONE = backbone
- # Input image size
- self.IMAGE_SHAPE = np.array(
- [self.IMAGE_MAX_DIM, self.IMAGE_MAX_DIM, 3])
+ # Only useful if you supply a callable to BACKBONE. Should compute
+ # the shape of each layer of the FPN Pyramid.
+ # See model.compute_backbone_shapes
+ COMPUTE_BACKBONE_SHAPE = None
# Compute backbone size from input image size
self.BACKBONE_SHAPES = np.array(
@@ -195,6 +205,10 @@
int(math.ceil(self.IMAGE_SHAPE[1] / stride))]
for stride in self.BACKBONE_STRIDES])
+ # Input image size
+ self.IMAGE_SHAPE = np.array(
+ [self.IMAGE_MAX_DIM, self.IMAGE_MAX_DIM, 3])
+
# Train or freeze batch normalization layers
# None: Train BN layers in a normal mode
# False: Freeze BN layers (recommended for small batch size)
Modified: grass-addons/grass7/imagery/i.ann.maskrcnn/maskrcnnlib/model.py
===================================================================
--- grass-addons/grass7/imagery/i.ann.maskrcnn/maskrcnnlib/model.py 2018-08-21 16:57:50 UTC (rev 73131)
+++ grass-addons/grass7/imagery/i.ann.maskrcnn/maskrcnnlib/model.py 2018-08-21 19:41:15 UTC (rev 73132)
@@ -78,6 +78,9 @@
Returns:
[N, (height, width)]. Where N is the number of stages
"""
+ if callable(config.BACKBONE):
+ return config.COMPUTE_BACKBONE_SHAPE(image_shape)
+
# Currently supports ResNet only
assert config.BACKBONE in ["resnet50", "resnet101"]
return np.array(
@@ -565,7 +568,11 @@
# Assign positive ROIs to GT boxes.
positive_overlaps = tf.gather(overlaps, positive_indices)
- roi_gt_box_assignment = tf.argmax(positive_overlaps, axis=1)
+ roi_gt_box_assignment = tf.cond(
+ tf.greater(tf.shape(positive_overlaps)[1], 0),
+ true_fn = lambda: tf.argmax(positive_overlaps, axis=1),
+ false_fn = lambda: tf.cast(tf.constant([]),tf.int64)
+ )
roi_gt_boxes = tf.gather(gt_boxes, roi_gt_box_assignment)
roi_gt_class_ids = tf.gather(gt_class_ids, roi_gt_box_assignment)
@@ -899,7 +906,8 @@
############################################################
def fpn_classifier_graph(rois, feature_maps, image_meta,
- pool_size, num_classes, train_bn=True):
+ pool_size, num_classes, train_bn=True,
+ fc_layers_size=1024):
"""Builds the computation graph of the feature pyramid network classifier
and regressor heads.
@@ -911,6 +919,7 @@
pool_size: The width of the square feature map generated from ROI Pooling.
num_classes: number of classes, which determines the depth of the results
train_bn: Boolean. Train or freeze Batch Norm layres
+ fc_layers_size: Size of the 2 FC layers
Returns:
logits: [N, NUM_CLASSES] classifier logits (before softmax)
@@ -924,11 +933,11 @@
name="roi_align_classifier")(
[rois, image_meta] + feature_maps)
# Two 1024 FC layers (implemented with Conv2D for consistency)
- x = KL.TimeDistributed(KL.Conv2D(1024, (pool_size, pool_size), padding="valid"),
+ x = KL.TimeDistributed(KL.Conv2D(fc_layers_size, (pool_size, pool_size), padding="valid"),
name="mrcnn_class_conv1")(x)
x = KL.TimeDistributed(BatchNorm(), name='mrcnn_class_bn1')(x, training=train_bn)
x = KL.Activation('relu')(x)
- x = KL.TimeDistributed(KL.Conv2D(1024, (1, 1)),
+ x = KL.TimeDistributed(KL.Conv2D(fc_layers_size, (1, 1)),
name="mrcnn_class_conv2")(x)
x = KL.TimeDistributed(BatchNorm(), name='mrcnn_class_bn2')(x, training=train_bn)
x = KL.Activation('relu')(x)
@@ -1903,25 +1912,29 @@
# Bottom-up Layers
# Returns a list of the last layers of each stage, 5 in total.
# Don't create the thead (stage 5), so we pick the 4th item in the list.
- _, C2, C3, C4, C5 = resnet_graph(input_image, config.BACKBONE,
- stage5=True, train_bn=config.TRAIN_BN)
+ if callable(config.BACKBONE):
+ _, C2, C3, C4, C5 = config.BACKBONE(input_image, stage5=True,
+ train_bn=config.TRAIN_BN)
+ else:
+ _, C2, C3, C4, C5 = resnet_graph(input_image, config.BACKBONE,
+ stage5=True, train_bn=config.TRAIN_BN)
# Top-down Layers
# TODO: add assert to varify feature map sizes match what's in config
- P5 = KL.Conv2D(256, (1, 1), name='fpn_c5p5')(C5)
+ P5 = KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (1, 1), name='fpn_c5p5')(C5)
P4 = KL.Add(name="fpn_p4add")([
KL.UpSampling2D(size=(2, 2), name="fpn_p5upsampled")(P5),
- KL.Conv2D(256, (1, 1), name='fpn_c4p4')(C4)])
+ KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (1, 1), name='fpn_c4p4')(C4)])
P3 = KL.Add(name="fpn_p3add")([
KL.UpSampling2D(size=(2, 2), name="fpn_p4upsampled")(P4),
- KL.Conv2D(256, (1, 1), name='fpn_c3p3')(C3)])
+ KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (1, 1), name='fpn_c3p3')(C3)])
P2 = KL.Add(name="fpn_p2add")([
KL.UpSampling2D(size=(2, 2), name="fpn_p3upsampled")(P3),
- KL.Conv2D(256, (1, 1), name='fpn_c2p2')(C2)])
+ KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (1, 1), name='fpn_c2p2')(C2)])
# Attach 3x3 conv to all P layers to get the final feature maps.
- P2 = KL.Conv2D(256, (3, 3), padding="SAME", name="fpn_p2")(P2)
- P3 = KL.Conv2D(256, (3, 3), padding="SAME", name="fpn_p3")(P3)
- P4 = KL.Conv2D(256, (3, 3), padding="SAME", name="fpn_p4")(P4)
- P5 = KL.Conv2D(256, (3, 3), padding="SAME", name="fpn_p5")(P5)
+ P2 = KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (3, 3), padding="SAME", name="fpn_p2")(P2)
+ P3 = KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (3, 3), padding="SAME", name="fpn_p3")(P3)
+ P4 = KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (3, 3), padding="SAME", name="fpn_p4")(P4)
+ P5 = KL.Conv2D(config.TOP_DOWN_PYRAMID_SIZE, (3, 3), padding="SAME", name="fpn_p5")(P5)
# P6 is used for the 5th anchor scale in RPN. Generated by
# subsampling from P5 with stride of 2.
P6 = KL.MaxPooling2D(pool_size=(1, 1), strides=2, name="fpn_p6")(P5)
@@ -1944,7 +1957,7 @@
# RPN Model
rpn = build_rpn_model(config.RPN_ANCHOR_STRIDE,
- len(config.RPN_ANCHOR_RATIOS), 256)
+ len(config.RPN_ANCHOR_RATIOS), config.TOP_DOWN_PYRAMID_SIZE)
# Loop through pyramid layers
layer_outputs = [] # list of lists
for p in rpn_feature_maps:
@@ -1999,15 +2012,12 @@
# Network Heads
# TODO: verify that this handles zero padded ROIs
mrcnn_class_logits, mrcnn_class, mrcnn_bbox =\
- fpn_classifier_graph(rois,
- mrcnn_feature_maps,
- input_image_meta,
- config.POOL_SIZE,
- config.NUM_CLASSES,
- train_bn=config.TRAIN_BN)
+ fpn_classifier_graph(rois, mrcnn_feature_maps, input_image_meta,
+ config.POOL_SIZE, config.NUM_CLASSES,
+ train_bn=config.TRAIN_BN,
+ fc_layers_size=config.FPN_CLASSIF_FC_LAYERS_SIZE)
- mrcnn_mask = build_fpn_mask_graph(rois,
- mrcnn_feature_maps,
+ mrcnn_mask = build_fpn_mask_graph(rois, mrcnn_feature_maps,
input_image_meta,
config.MASK_POOL_SIZE,
config.NUM_CLASSES,
@@ -2042,12 +2052,10 @@
# Network Heads
# Proposal classifier and BBox regressor heads
mrcnn_class_logits, mrcnn_class, mrcnn_bbox =\
- fpn_classifier_graph(rpn_rois,
- mrcnn_feature_maps,
- input_image_meta,
- config.POOL_SIZE,
- config.NUM_CLASSES,
- train_bn=config.TRAIN_BN)
+ fpn_classifier_graph(rpn_rois, mrcnn_feature_maps, input_image_meta,
+ config.POOL_SIZE, config.NUM_CLASSES,
+ train_bn=config.TRAIN_BN,
+ fc_layers_size=config.FPN_CLASSIF_FC_LAYERS_SIZE)
# Detections
# output is [batch, num_detections, (y1, x1, y2, x2, class_id, score)] in
@@ -2080,8 +2088,7 @@
"""Finds the last checkpoint file of the last trained model in the
model directory.
Returns:
- log_dir: The directory where events and weights are saved
- checkpoint_path: the path to the last checkpoint file
+ The path of the last checkpoint file
"""
# Get directory names. Each directory corresponds to a model
dir_names = next(os.walk(self.model_dir))[1]
@@ -2089,7 +2096,11 @@
dir_names = filter(lambda f: f.startswith(key), dir_names)
dir_names = sorted(dir_names)
if not dir_names:
- return None, None
+ import errno
+ raise FileNotFoundError(
+ errno.ENOENT,
+ "Could not find model directory under {}".format(
+ self.model_dir))
# Pick last directory
dir_name = os.path.join(self.model_dir, dir_names[-1])
# Find the last checkpoint
@@ -2097,9 +2108,13 @@
checkpoints = filter(lambda f: f.startswith("mask_rcnn"), checkpoints)
checkpoints = sorted(checkpoints)
if not checkpoints:
- return dir_name, None
+ import errno
+ raise FileNotFoundError(
+ errno.ENOENT,
+ "Could not find weight files in {}".format(
+ dir_name))
checkpoint = os.path.join(dir_name, checkpoints[-1])
- return dir_name, checkpoint
+ return checkpoint
def load_weights(self, filepath, by_name=False, exclude=None):
"""Modified version of the correspoding Keras function with
@@ -2255,7 +2270,7 @@
# Continue from we left of. Get epoch and date from the file name
# A sample model path might look like:
# /path/to/logs/coco20171029T2315/mask_rcnn_coco_0001.h5
- regex = r".*/\w+(\d{4})(\d{2})(\d{2})T(\d{2})(\d{2})/mask\_rcnn\_\w+(\d{4})\.h5"
+ regex = r".*/[\w-]+(\d{4})(\d{2})(\d{2})T(\d{2})(\d{2})/mask\_rcnn\_[\w-]+(\d{4})\.h5"
m = re.match(regex, model_path)
if m:
now = datetime.datetime(int(m.group(1)), int(m.group(2)), int(m.group(3)),
@@ -2263,11 +2278,16 @@
# Epoch number in file is 1-based, and in Keras code it's 0-based.
# So, adjust for that then increment by one to start from the next epoch
self.epoch = int(m.group(6))
+ print('Re-starting from epoch %d' % self.epoch)
# Directory for training logs
self.log_dir = os.path.join(self.model_dir, "{}{:%Y%m%dT%H%M}".format(
self.config.NAME.lower(), now))
+ # Create log_dir if not exists
+ if not os.path.exists(self.log_dir):
+ os.makedirs(self.log_dir)
+
# Path to save after each epoch. Include placeholders that get filled by Keras.
self.checkpoint_path = os.path.join(self.log_dir, "mask_rcnn_{}_*epoch*.h5".format(
self.config.NAME.lower()))
@@ -2286,7 +2306,7 @@
layers: Allows selecting wich layers to train. It can be:
- A regular expression to match layer names to train
- One of these predefined values:
- heaads: The RPN, classifier and mask heads of the network
+ heads: The RPN, classifier and mask heads of the network
all: All the layers
3+: Train Resnet stage 3 and up
4+: Train Resnet stage 4 and up
@@ -2463,7 +2483,7 @@
full_mask = utils.unmold_mask(masks[i], boxes[i], original_image_shape)
full_masks.append(full_mask)
full_masks = np.stack(full_masks, axis=-1)\
- if full_masks else np.empty(masks.shape[1:3] + (0,))
+ if full_masks else np.empty(original_image_shape[:2] + (0,))
return boxes, class_ids, scores, full_masks
Modified: grass-addons/grass7/imagery/i.ann.maskrcnn/maskrcnnlib/utils.py
===================================================================
--- grass-addons/grass7/imagery/i.ann.maskrcnn/maskrcnnlib/utils.py 2018-08-21 16:57:50 UTC (rev 73131)
+++ grass-addons/grass7/imagery/i.ann.maskrcnn/maskrcnnlib/utils.py 2018-08-21 19:41:15 UTC (rev 73132)
@@ -25,7 +25,7 @@
import warnings
# URL from which to download the latest COCO trained weights
-# https://github.com/matterport/Mask_RCNN/releases/download/v2.0/mask_rcnn_coco.h5
+# COCO_MODEL_URL = "https://github.com/matterport/Mask_RCNN/releases/download/v2.0/mask_rcnn_coco.h5"
############################################################
@@ -102,7 +102,11 @@
'''Computes IoU overlaps between two sets of masks.
masks1, masks2: [Height, Width, instances]
'''
- # flatten masks
+
+ # If either set of masks is empty return empty result
+ if masks1.shape[0] == 0 or masks2.shape[0] == 0:
+ return np.zeros((masks1.shape[0], masks2.shape[-1]))
+ # flatten masks and compute their areas
masks1 = np.reshape(masks1 > .5, (-1, masks1.shape[-1])).astype(np.float32)
masks2 = np.reshape(masks2 > .5, (-1, masks2.shape[-1])).astype(np.float32)
area1 = np.sum(masks1, axis=0)
More information about the grass-commit
mailing list