def create_model(num_classes):
backbone = MobileNetV2().features
backbone.out_channels = 1280
anchor_generator = AnchorsGenerator(sizes=((32, 64, 128, 256, 512),),
aspect_ratios=((0.5, 1.0, 2.0),))
roi_pooler = torchvision.ops.MultiScaleRoIAlign(featmap_names=['0'], # 在哪些特征层上进行roi pooling
output_size=[7, 7], # roi_pooling输出特征矩阵尺寸
sampling_ratio=2) # 采样率
model = FasterRCNN(backbone=backbone,
num_classes=num_classes,
rpn_anchor_generator=anchor_generator,
box_roi_pool=roi_pooler)
return model
def create_model(num_classes):
backbone = torchvision.models.vgg16(pretrained=True).features
backbone.out_channels = 512
anchor_generator = AnchorsGenerator(sizes=((32, 64, 128, 256, 512), ),
aspect_ratios=((0.5, 1.0, 2.0), ))
roi_pooler = torchvision.ops.MultiScaleRoIAlign(featmap_names=['0'],
output_size=[7, 7],
sampling_ratio=2)
model = FasterRCNN(backbone=backbone,
num_classes=num_classes,
rpn_anchor_generator=anchor_generator,
box_roi_pool=roi_pooler)
return model
def create_model(num_classes):
# https://download.pytorch.org/models/mobilenet_v2-b0353104.pth
backbone = MobileNetV2(weights_path="./backbone/mobilenet_v2.pth").features
backbone.out_channels = 1280
anchor_generator = AnchorsGenerator(sizes=((32, 64, 128, 256, 512),),
aspect_ratios=((0.5, 1.0, 2.0),))
roi_pooler = torchvision.ops.MultiScaleRoIAlign(featmap_names=['0'], # 在哪些特征层上进行roi pooling
output_size=[7, 7], # roi_pooling输出特征矩阵尺寸
sampling_ratio=2) # 采样率
model = FasterRCNN(backbone=backbone,
num_classes=num_classes,
rpn_anchor_generator=anchor_generator,
box_roi_pool=roi_pooler)
return model
def create_model(num_classes):
# mobileNetv2+faster_RCNN
backbone = MobileNetV2().features
backbone.out_channels = 1280
anchor_generator = AnchorsGenerator(sizes=((32, 64, 128, 256, 512), ),
aspect_ratios=((0.5, 1.0, 2.0), ))
roi_pooler = torchvision.ops.MultiScaleRoIAlign(featmap_names=['0'],
output_size=[7, 7],
sampling_ratio=2)
model = FasterRCNN(backbone=backbone,
num_classes=num_classes,
rpn_anchor_generator=anchor_generator,
box_roi_pool=roi_pooler)
# # resNet50+fpn+faster_RCNN
# backbone = resnet50_fpn_backbone()
# model = FasterRCNN(backbone=backbone, num_classes=num_classes)
return model
def __init__(
self,
backbone,
num_classes=None,
# transform parameter
min_size=800,
max_size=1000, # 预处理resize时限制的最小尺寸与最大尺寸
image_mean=None,
image_std=None, # 预处理normalize时使用的均值和方差
# RPN parameters
rpn_anchor_generator=None,
rpn_head=None,
rpn_pre_nms_top_n_train=2000,
rpn_pre_nms_top_n_test=1000, # rpn中在nms处理前保留的proposal数(根据score)
rpn_post_nms_top_n_train=2000,
rpn_post_nms_top_n_test=1000, # rpn中在nms处理后保留的proposal数
rpn_nms_thresh=0.7, # rpn中进行nms处理时使用的iou阈值
rpn_fg_iou_thresh=0.7,
rpn_bg_iou_thresh=0.3, # rpn计算损失时，采集正负样本设置的阈值
rpn_batch_size_per_image=256,
rpn_positive_fraction=0.5, # rpn计算损失时采样的样本数，以及正样本占总样本的比例
# Box parameters
box_roi_pool=None,
box_head=None,
box_predictor=None,
# 移除低目标概率 fast rcnn中进行nms处理的阈值 对预测结果根据score排序取前100个目标
box_score_thresh=0.05,
box_nms_thresh=0.5,
box_detections_per_img=100,
box_fg_iou_thresh=0.5,
box_bg_iou_thresh=0.5, # fast rcnn计算误差时，采集正负样本设置的阈值
box_batch_size_per_image=512,
box_positive_fraction=0.25, # fast rcnn计算误差时采样的样本数，以及正样本占所有样本的比例
bbox_reg_weights=None):
if not hasattr(backbone, "out_channels"):
raise ValueError(
"backbone should contain an attribute out_channels"
"specifying the number of output channels (assumed to be the"
"same for all the levels")
assert isinstance(rpn_anchor_generator, (AnchorsGenerator, type(None)))
assert isinstance(box_roi_pool, (MultiScaleRoIAlign, type(None)))
if num_classes is not None:
if box_predictor is not None:
raise ValueError(
"num_classes should be None when box_predictor "
"is specified")
else:
if box_predictor is None:
raise ValueError(
"num_classes should not be None when box_predictor "
"is not specified")
# 预测特征层的channels
out_channels = backbone.out_channels
# 若anchor生成器为空，则自动生成针对resnet50_fpn的anchor生成器
if rpn_anchor_generator is None:
anchor_sizes = ((32, ), (64, ), (128, ), (256, ), (512, ))
aspect_ratios = ((0.5, 1.0, 2.0), ) * len(anchor_sizes)
rpn_anchor_generator = AnchorsGenerator(anchor_sizes,
aspect_ratios)
# 生成RPN通过滑动窗口预测网络部分
if rpn_head is None:
rpn_head = RPNHead(
out_channels,
rpn_anchor_generator.num_anchors_per_location()[0])
# 默认rpn_pre_nms_top_n_train = 2000, rpn_pre_nms_top_n_test = 1000,
# 默认rpn_post_nms_top_n_train = 2000, rpn_post_nms_top_n_test = 1000,
rpn_pre_nms_top_n = dict(training=rpn_pre_nms_top_n_train,
testing=rpn_pre_nms_top_n_test)
rpn_post_nms_top_n = dict(training=rpn_post_nms_top_n_train,
testing=rpn_post_nms_top_n_test)
# 定义整个RPN框架
rpn = RegionProposalNetwork(rpn_anchor_generator, rpn_head,
rpn_fg_iou_thresh, rpn_bg_iou_thresh,
rpn_batch_size_per_image,
rpn_positive_fraction, rpn_pre_nms_top_n,
rpn_post_nms_top_n, rpn_nms_thresh)
# Multi-scale RoIAlign pooling
if box_roi_pool is None:
box_roi_pool = MultiScaleRoIAlign(
featmap_names=['0', '1', '2', '3'], # 在哪些特征层进行roi pooling
output_size=[7, 7],
sampling_ratio=2)
# fast RCNN中roi pooling后的展平处理两个全连接层部分
if box_head is None:
resolution = box_roi_pool.output_size[0] # 默认等于7
representation_size = 1024
box_head = TwoMLPHead(out_channels * resolution**2,
representation_size)
# 在box_head的输出上预测部分
if box_predictor is None:
representation_size = 1024
box_predictor = FastRCNNPredictor(representation_size, num_classes)
# 将roi pooling, box_head以及box_predictor结合在一起
roi_heads = RoIHeads(
# box
box_roi_pool,
box_head,
box_predictor,
box_fg_iou_thresh,
box_bg_iou_thresh, # 0.5 0.5
box_batch_size_per_image,
box_positive_fraction, # 512 0.25
bbox_reg_weights,
box_score_thresh,
box_nms_thresh,
box_detections_per_img) # 0.05 0.5 100
if image_mean is None:
image_mean = [0.485, 0.456, 0.406]
if image_std is None:
image_std = [0.229, 0.224, 0.225]
# 对数据进行标准化，缩放，打包成batch等处理部分
transform = GeneralizedRCNNTransform(min_size, max_size, image_mean,
image_std)
super(FasterRCNN, self).__init__(backbone, rpn, roi_heads, transform)
def __init__(self, backbone, num_classes=None,
# transform parameter
min_size=800, max_size=1333,
image_mean=None, image_std=None,
# RPN parameters
rpn_anchor_generator=None, rpn_head=None,
rpn_pre_nms_top_n_train=2000, rpn_pre_nms_top_n_test=1000,
rpn_post_nms_top_n_train=2000, rpn_post_nms_top_n_test=1000,
rpn_nms_thresh=0.7,
rpn_fg_iou_thresh=0.7, rpn_bg_iou_thresh=0.3,
rpn_batch_size_per_image=256, rpn_positive_fraction=0.5,
# Bpx parameters
box_roi_pool=None, box_head=None, box_predictor=None,
box_score_thresh=0.05, box_nms_thresh=0.5, box_detections_per_img=100,
box_fg_iou_thresh=0.5, box_bg_iou_thresh=0.5,
box_batch_size_per_image=512, box_positive_fraction=0.25,
bbox_reg_weights=None):
if not hasattr(backbone, "out_channels"):
raise ValueError(
"backbone should contain an attribute out_channels"
"specifying the number of output channels (assumed to be the"
"same for all the levels"
)
assert isinstance(rpn_anchor_generator, (AnchorsGenerator, type(None)))
assert isinstance(box_roi_pool, (MultiScaleRoIAlign, type(None)))
if num_classes is not None:
if box_predictor is not None:
raise ValueError("num_classes should be None when box_predictor "
"is specified")
else:
if box_predictor is None:
raise ValueError("num_classes should not be None when box_predictor "
"is not specified")
# The channels of prediction layer
out_channels = backbone.out_channels
# if anchor is None, automatically using anchor_generator for resnet50_fpn
if rpn_anchor_generator is None:
anchor_sizes = ((32,), (64,), (128,), (256,), (512,))
aspect_ratios = ((0.5, 1.0, 2.0),) * len(anchor_sizes)
rpn_anchor_generator = AnchorsGenerator(
anchor_sizes, aspect_ratios
)
# 生成RPN通过滑动窗口预测网络部分
if rpn_head is None:
rpn_head = RPNHead(
out_channels, rpn_anchor_generator.num_anchors_per_location()[0]
)
# 默认rpn_pre_nms_top_n_train = 2000, rpn_pre_nms_top_n_test = 1000,
# 默认rpn_post_nms_top_n_train = 2000, rpn_post_nms_top_n_test = 1000,
rpn_pre_nms_top_n = dict(training=rpn_pre_nms_top_n_train, testing=rpn_pre_nms_top_n_test)
rpn_post_nms_top_n = dict(training=rpn_post_nms_top_n_train, testing=rpn_post_nms_top_n_test)
# 定义整个RPN框架
rpn = RegionProposalNetwork(
rpn_anchor_generator, rpn_head,
rpn_fg_iou_thresh, rpn_bg_iou_thresh,
rpn_batch_size_per_image, rpn_positive_fraction,
rpn_pre_nms_top_n, rpn_post_nms_top_n, rpn_nms_thresh)
# Multi-scale RoIAlign pooling
if box_roi_pool is None:
box_roi_pool = MultiScaleRoIAlign(
featmap_names=['0', '1', '2', '3'], # 在哪些特征层进行预测
output_size=[7, 7],
sampling_ratio=2)
# fast RCNN中roi pooling后的两个全连接层部分
if box_head is None:
resolution = box_roi_pool.output_size[0] # 默认等于7
representation_size = 1024
box_head = TwoMLPHead(
out_channels * resolution ** 2,
representation_size
)
# 在box_head的输出上预测部分
if box_predictor is None:
representation_size = 1024
box_predictor = FastRCNNPredictor(
representation_size,
num_classes)
# 将roi pooling, box_head以及box_predictor结合在一起
roi_heads = RoIHeads(
# box
box_roi_pool, box_head, box_predictor,
box_fg_iou_thresh, box_bg_iou_thresh,
box_batch_size_per_image, box_positive_fraction,
bbox_reg_weights,
box_score_thresh, box_nms_thresh, box_detections_per_img)
if image_mean is None:
image_mean = [0.485, 0.456, 0.406]
if image_std is None:
image_std = [0.229, 0.224, 0.225]
# 对数据进行标准化，缩放，打包成batch等处理部分
transform = GeneralizedRCNNTransform(min_size, max_size, image_mean, image_std)
super(FasterRCNN, self).__init__(backbone, rpn, roi_heads, transform)
