使用方法参考这位大佬:https://blog.csdn.net/qq_35874169/article/details/116203228
这里补充一些细节:
将 model.py 中的 data_generator() 方法注释掉
新加上一个 DataGenerator 类,内容如下:
class DataGenerator(keras.utils.Sequence):
"""A generator that returns images and corresponding target class ids,
bounding box deltas, and masks.
dataset: The Dataset object to pick data from
config: The model config object
shuffle: If True, shuffles the samples before every epoch
augment: (deprecated. Use augmentation instead). If true, apply random
image augmentation. Currently, only horizontal flipping is offered.
augmentation: Optional. An imgaug (https://github.com/aleju/imgaug) augmentation.
For example, passing imgaug.augmenters.Fliplr(0.5) flips images
right/left 50% of the time.
random_rois: If > 0 then generate proposals to be used to train the
network classifier and mask heads. Useful if training
the Mask RCNN part without the RPN.
batch_size: How many images to return in each call
detection_targets: If True, generate detection targets (class IDs, bbox
deltas, and masks). Typically for debugging or visualizations because
in trainig detection targets are generated by DetectionTargetLayer.
no_augmentation_sources: Optional. List of sources to exclude for
augmentation. A source is string that identifies a dataset and is
defined in the Dataset class.
Returns a Python generator. Upon calling next() on it, the
generator returns two lists, inputs and outputs. The contents
of the lists differs depending on the received arguments:
inputs list:
- images: [batch, H, W, C]
- image_meta: [batch, (meta data)] Image details. See compose_image_meta()
- rpn_match: [batch, N] Integer (1=positive anchor, -1=negative, 0=neutral)
- rpn_bbox: [batch, N, (dy, dx, log(dh), log(dw))] Anchor bbox deltas.
- gt_class_ids: [batch, MAX_GT_INSTANCES] Integer class IDs
- gt_boxes: [batch, MAX_GT_INSTANCES, (y1, x1, y2, x2)]
- gt_masks: [batch, height, width, MAX_GT_INSTANCES]. The height and width
are those of the image unless use_mini_mask is True, in which
case they are defined in MINI_MASK_SHAPE.
outputs list: Usually empty in regular training. But if detection_targets
is True then the outputs list contains target class_ids, bbox deltas,
and masks.
"""
def __init__(self, dataset, config, shuffle=True, augment=False, augmentation=None,
random_rois=0, batch_size=1, detection_targets=False,
no_augmentation_sources=None):
self.image_ids = np.copy(dataset.image_ids)
self.dataset = dataset
self.config = config
self.error_count = 0
# Anchors
# [anchor_count, (y1, x1, y2, x2)]
self.backbone_shapes = compute_backbone_shapes(config, config.IMAGE_SHAPE)
self.anchors = utils.generate_pyramid_anchors(config.RPN_ANCHOR_SCALES,
config.RPN_ANCHOR_RATIOS,
self.backbone_shapes,
config.BACKBONE_STRIDES,
config.RPN_ANCHOR_STRIDE)
self.shuffle = shuffle
self.augment = augment
self.augmentation = augmentation
self.random_rois = random_rois
self.batch_size = batch_size
self.detection_targets = detection_targets
self.no_augmentation_sources = no_augmentation_sources or []
def __len__(self):
return int(np.ceil(len(self.image_ids) / float(self.batch_size)))
def __getitem__(self, idx):
return self.data_generator(self.image_ids[idx * self.batch_size:(idx + 1) * self.batch_size])
def data_generator(self, image_ids):
b = 0
while b < self.batch_size:
try:
# Get GT bounding boxes and masks for image.
image_id = image_ids[b]
# If the image source is not to be augmented pass None as augmentation
if self.dataset.image_info[image_id]['source'] in self.no_augmentation_sources:
image, image_meta, gt_class_ids, gt_boxes, gt_masks = \
load_image_gt(self.dataset, self.config, image_id, augment=self.augment,
augmentation=None,
use_mini_mask=self.config.USE_MINI_MASK)
else:
image, image_meta, gt_class_ids, gt_boxes, gt_masks = \
load_image_gt(self.dataset, self.config, image_id, augment=self.augment,
augmentation=self.augmentation,
use_mini_mask=self.config.USE_MINI_MASK)
# Skip images that have no instances. This can happen in cases
# where we train on a subset of classes and the image doesn't
# have any of the classes we care about.
if not np.any(gt_class_ids > 0):
continue
# RPN Targets
rpn_match, rpn_bbox = build_rpn_targets(image.shape, self.anchors,
gt_class_ids, gt_boxes, self.config)
# Mask R-CNN Targets
if self.random_rois:
rpn_rois = generate_random_rois(
image.shape, self.random_rois, gt_class_ids, gt_boxes)
if self.detection_targets:
rois, mrcnn_class_ids, mrcnn_bbox, mrcnn_mask = \
build_detection_targets(
rpn_rois, gt_class_ids, gt_boxes, gt_masks, self.config)
# Init batch arrays
if b == 0:
batch_image_meta = np.zeros(
(self.batch_size,) + image_meta.shape, dtype=image_meta.dtype)
batch_rpn_match = np.zeros(
[self.batch_size, self.anchors.shape[0], 1], dtype=rpn_match.dtype)
batch_rpn_bbox = np.zeros(
[self.batch_size, self.config.RPN_TRAIN_ANCHORS_PER_IMAGE, 4], dtype=rpn_bbox.dtype)
batch_images = np.zeros(
(self.batch_size,) + image.shape, dtype=np.float32)
batch_gt_class_ids = np.zeros(
(self.batch_size, self.config.MAX_GT_INSTANCES), dtype=np.int32)
batch_gt_boxes = np.zeros(
(self.batch_size, self.config.MAX_GT_INSTANCES, 4), dtype=np.int32)
batch_gt_masks = np.zeros(
(self.batch_size, gt_masks.shape[0], gt_masks.shape[1],
self.config.MAX_GT_INSTANCES), dtype=gt_masks.dtype)
if self.random_rois:
batch_rpn_rois = np.zeros(
(self.batch_size, rpn_rois.shape[0], 4), dtype=rpn_rois.dtype)
if self.detection_targets:
batch_rois = np.zeros(
(self.batch_size,) + rois.shape, dtype=rois.dtype)
batch_mrcnn_class_ids = np.zeros(
(self.batch_size,) + mrcnn_class_ids.shape, dtype=mrcnn_class_ids.dtype)
batch_mrcnn_bbox = np.zeros(
(self.batch_size,) + mrcnn_bbox.shape, dtype=mrcnn_bbox.dtype)
batch_mrcnn_mask = np.zeros(
(self.batch_size,) + mrcnn_mask.shape, dtype=mrcnn_mask.dtype)
# If more instances than fits in the array, sub-sample from them.
if gt_boxes.shape[0] > self.config.MAX_GT_INSTANCES:
ids = np.random.choice(
np.arange(gt_boxes.shape[0]), self.config.MAX_GT_INSTANCES, replace=False)
gt_class_ids = gt_class_ids[ids]
gt_boxes = gt_boxes[ids]
gt_masks = gt_masks[:, :, ids]
# Add to batch
batch_image_meta[b] = image_meta
batch_rpn_match[b] = rpn_match[:, np.newaxis]
batch_rpn_bbox[b] = rpn_bbox
batch_images[b] = mold_image(image.astype(np.float32), self.config)
batch_gt_class_ids[b, :gt_class_ids.shape[0]] = gt_class_ids
batch_gt_boxes[b, :gt_boxes.shape[0]] = gt_boxes
batch_gt_masks[b, :, :, :gt_masks.shape[-1]] = gt_masks
if self.random_rois:
batch_rpn_rois[b] = rpn_rois
if self.detection_targets:
batch_rois[b] = rois
batch_mrcnn_class_ids[b] = mrcnn_class_ids
batch_mrcnn_bbox[b] = mrcnn_bbox
batch_mrcnn_mask[b] = mrcnn_mask
b += 1
# Batch full?
if b >= self.batch_size:
inputs = [batch_images, batch_image_meta, batch_rpn_match, batch_rpn_bbox,
batch_gt_class_ids, batch_gt_boxes, batch_gt_masks]
outputs = []
if self.random_rois:
inputs.extend([batch_rpn_rois])
if self.detection_targets:
inputs.extend([batch_rois])
# Keras requires that output and targets have the same number of dimensions
batch_mrcnn_class_ids = np.expand_dims(
batch_mrcnn_class_ids, -1)
outputs.extend(
[batch_mrcnn_class_ids, batch_mrcnn_bbox, batch_mrcnn_mask])
return inputs, outputs
except (GeneratorExit, KeyboardInterrupt):
raise
except:
# Log it and skip the image
logging.exception("Error processing image {}".format(
self.dataset.image_info[image_id]))
self.error_count += 1
if self.error_count > 5:
raise
def on_epoch_end(self):
if self.shuffle:
np.random.shuffle(self.image_ids)
再将 model.py 中用到 data_generator() 原方法的地方换为 DataGenerator() 即可,如图:
修改完成运行就不会有这个提示,亲测 : D