def __init__(self, classes, class_agnostic):
super(_HierRCNN, self).__init__()
with h5py.File('data/pretrained_model/label_vec_vrd.h5', 'r') as f:
self.label_vecs = np.array(f['label_vec'])
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
self.order_embedding = nn.Sequential(
nn.ReLU(inplace=True), nn.Dropout(), nn.Linear(4096, 4096),
nn.ReLU(inplace=True), nn.Dropout(),
nn.Linear(4096, cfg.HIER.EMBEDDING_LENGTH))
self.order_score = _OrderSimilarity(cfg.HIER.ORDER_DISTANCE_NORM)
def __init__(self, classes, class_agnostic):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0/16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE, 1.0/16.0)
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE# = 7*2 =14
'''
# Size of the pooled region after RoI pooling
__C.POOLING_SIZE = 7 roi pooling 之后得到的特征的尺寸
CROP_RESIZE_WITH_MAX_POOL = True
'''
self.RCNN_roi_crop = _RoICrop()
def __init__(self, phase, cfg, size, base, extras, head, num_classes):
super(test_association, self).__init__()
self.phase = phase
self.num_classes = num_classes
self.cfg = vid
self.priorbox = PriorBox(self.cfg)
self.priors = Variable(self.priorbox.forward(), volatile=True)
self.size = size
# SSD network
self.vgg = nn.ModuleList(base)
# Layer learns to scale the l2 normalized features from conv4_3
self.L2Norm = L2Norm(512, 20)
self.extras = nn.ModuleList(extras)
self.loc = nn.ModuleList(head[0])
self.conf = nn.ModuleList(head[1])
self.roi_pool = _RoIPooling(self.cfg['POOLING_SIZE'], self.cfg['POOLING_SIZE'], 1.0 / 16.0)
self.roi_align = RoIAlignAvg(self.cfg['POOLING_SIZE'], self.cfg['POOLING_SIZE'], 1.0 / 16.0)
self.grid_size = self.cfg['POOLING_SIZE'] * 2 if self.cfg['CROP_RESIZE_WITH_MAX_POOL'] else self.cfg['POOLING_SIZE']
self.roi_crop = _RoICrop()
self.img_shape = (self.cfg['min_dim'],self.cfg['min_dim'])
if phase == 'vid_test':
self.softmax = nn.Softmax(dim=-1)
self.detect = test_target(num_classes, 200, 0.5, 0.01, 0.45)
def __init__(self, classes, class_agnostic):
super(_fasterRCNN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
def __init__(self, phase, cfg, size, base, extras, head, num_classes):
super(association_lstm, self).__init__()
self.phase = phase
self.num_classes = num_classes
self.cfg = vid
self.priorbox = PriorBox(self.cfg)
self.priors = Variable(self.priorbox.forward(), volatile=True)
self.size = size
# SSD network
self.vgg = nn.ModuleList(base)
# Layer learns to scale the l2 normalized features from conv4_3
self.L2Norm = L2Norm(512, 20)
self.extras = nn.ModuleList(extras)
self.loc = nn.ModuleList(head[0])
self.conf = nn.ModuleList(head[1])
self.roi_pool = _RoIPooling(self.cfg['POOLING_SIZE'],
self.cfg['POOLING_SIZE'], 1.0 / 16.0)
self.roi_align = RoIAlignAvg(self.cfg['POOLING_SIZE'],
self.cfg['POOLING_SIZE'], 1.0 / 16.0)
self.grid_size = self.cfg['POOLING_SIZE'] * 2 if self.cfg[
'CROP_RESIZE_WITH_MAX_POOL'] else self.cfg['POOLING_SIZE']
self.roi_crop = _RoICrop()
self.img_shape = (self.cfg['min_dim'], self.cfg['min_dim'])
self.tensor_len = 4 + self.num_classes + 49
self.bnlstm1 = BNLSTM(input_size=84,
hidden_size=150,
batch_first=False,
bidirectional=False)
self.bnlstm2 = BNLSTM(input_size=150,
hidden_size=300,
batch_first=False,
bidirectional=False)
self.cls_pred = nn.Linear(300, self.num_classes)
self.bbox_pred = nn.Linear(300, 4)
self.association_pred = nn.Linear(300, 49)
self.MultiProjectLoss = MultiProjectLoss(self.num_classes, 0, True, 3,
0.5)
if phase == 'vid_train':
self.softmax = nn.Softmax(dim=-1)
#self.detect = Trnsform_target(num_classes, 200, 0.5, 0.01, 0.45)
self.detect = train_target(num_classes, 200, 0.5, 0.01, 0.45)
def __init__(self, out_size, phase, in_im_sz, fm_use):
"""Initializes RoI_layer module."""
super(RoI_layer, self).__init__()
self.phase = phase # in order to get the RoI reigon
self.out_size = out_size
self.in_img_sz = in_im_sz
self.tm_scale = 8
self.fm_ROI = int(fm_use / 4)
self.Dense_scale = int(self.tm_scale / 2)
if phase == 'train':
data_index_file = './data/Charades_train.pkl'
elif phase == 'eval':
data_index_file = './data/Charades_Val_Video.pkl'
else:
assert 0, 'The data can not find'
self.bx_dir = '/VIDEO_DATA/BBOX/'
self.data_index = pickle.load(open(
data_index_file, 'rb')) # in order to get the bbox (RPN)
# define rpn
self.ROI_Align = RoIAlignAvg(out_size, out_size,
1 / 16.0) # scale need to change
self.ROI_Pool = _RoIPooling(out_size, out_size,
1 / 16.0) # scale need to change
self.Ptorch_ROI = Torch_ROI(feature_scal=(self.in_img_sz / 16))
self.Scene_Roi = np.array(
[[i, 0, 0, self.in_img_sz - 32, self.in_img_sz - 32]
for i in range(self.fm_ROI)])
# 32 = scale * 2 = 16*2 for ROI Align
self.Scens_Full = np.array(
[[i, 0, 0, self.in_img_sz - 16, self.in_img_sz - 16]
for i in range(self.fm_ROI)])
self.Scens_Pytorch = np.array(
[[i, 0, 0, self.in_img_sz, self.in_img_sz]
for i in range(self.fm_ROI)])
self.Scens_Sparse = np.array(
[[i, 0, 0, self.in_img_sz, self.in_img_sz]
for i in range(1, self.fm_ROI, 2)])
def __init__(self, classes, class_agnostic):
super(_FPN, self).__init__()
self.classes = classes
self.n_classes = len(classes)
self.class_agnostic = class_agnostic
# loss
self.RCNN_loss_cls = 0
self.RCNN_loss_bbox = 0
# define rpn
self.RCNN_rpn = _RPN_FPN(self.dout_base_model)
self.RCNN_proposal_target = _ProposalTargetLayer(self.n_classes)
# NOTE: the original paper used pool_size = 7 for cls branch, and 14 for mask branch, to save the
# computation time, we first use 14 as the pool_size, and then do stride=2 pooling for cls branch.
self.RCNN_roi_pool = _RoIPooling(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.RCNN_roi_align = RoIAlignAvg(cfg.POOLING_SIZE, cfg.POOLING_SIZE,
1.0 / 16.0)
self.grid_size = cfg.POOLING_SIZE * 2 if cfg.CROP_RESIZE_WITH_MAX_POOL else cfg.POOLING_SIZE
self.RCNN_roi_crop = _RoICrop()
def __init__(self, phase, base, extras, head, extras_lstd, num_classes):
super(SSD, self).__init__()
self.phase = phase
self.num_classes = num_classes
# TODO: implement __call__ in PriorBox
self.priorbox = PriorBox(v2)
self.priors = Variable(self.priorbox.forward(), volatile=True)
self.size = 300
# SSD network
self.vgg = nn.ModuleList(base)
# Layer learns to scale the l2 normalized features from conv4_3
self.L2Norm = L2Norm(512, 20)
self.extras = nn.ModuleList(extras)
self.loc = nn.ModuleList(head[0])
self.conf = nn.ModuleList(head[1])
'''
self.extras_lstd = nn.ModuleList(extras_lstd)
self.classifier = nn.ModuleList([nn.Linear(256*3*3, 21)])
'''
self.classifier = nn.ModuleList([
nn.Linear(1024 * 5 * 5, 4096),
nn.ReLU(True),
nn.Dropout(p=0.5),
nn.Linear(4096, 4096),
nn.ReLU(True),
nn.Dropout(0.5),
nn.Linear(4096, 21)
])
self.softmax = nn.Softmax(dim=-1)
self.post_rois = Post_rois(num_classes, 0, 100, 0, 0.65)
self.detect = Detect(num_classes, 0, 100, 0, 0.65)
#self.ROI_POOL = RoIPoolFunction(5, 5, 1.0/19.0)
#self.roi_pooling = _roi_pooling
self.roi_pool = _RoIPooling(5, 5, 1.0 / 16.0)
if __name__ == '__main__':
import torch
import numpy as np
from torch.autograd import Variable
from lib.model.roi_pooling.modules.roi_pool import _RoIPooling
input = torch.randn(2, 21 * 7 * 7, 50, 72)
rois = torch.from_numpy(
np.array([
[0.0000, 350.6689, 211.0240, 779.0886, 777.7496],
[0.0000, 744.0627, 277.4919, 988.4307, 602.7589],
[1.0000, 350.6689, 211.0240, 779.0886, 777.7496],
[1.0000, 744.0627, 277.4919, 988.4307, 602.7589],
])).float()
pool = PSRoIPool(7, 7, 1 / 16.0, 7, 21)
input = Variable(input.cuda())
rois = Variable(rois.cuda())
print(rois.size(), input.size())
print(input)
out = pool(input, rois)
print(out)
print(out.size())
print('============================')
roi_pool = _RoIPooling(7, 7, 1 / 16.0)
out = roi_pool(input, rois.view(-1, 5))
print(out)
print(out.size())