def __init__(self, phase, size, Basenet, Neck, Head, cfg):
super(SSD, self).__init__()
self.phase = phase
self.cfg = cfg
self.priorbox = PriorBox(self.cfg)
self.priors = self.priorbox.forward()
self.size = size
# SSD network
self.basenet = Basenet
self.neck = Neck
self.head = Head
self.num_classes = cfg['num_classes']
self.softmax = nn.Softmax(dim=-1)
self.detect = Detect(self.num_classes, 0, 200, 0.01, 0.45,
variance=cfg['variance'], nms_kind=cfg['nms_kind'], beta1=cfg['beta1'])
def __init__(self):
super().__init__()
self.backbone = darknet53
# Compute mask_dim here and add it back to the config. Make sure Yolact's constructor is called early!
self.num_grids = 0
self.proto_src = 0
in_channels = 256
in_channels += self.num_grids
mask_proto_net = [(256, 3, {
'padding': 1
}), (256, 3, {
'padding': 1
}), (256, 3, {
'padding': 1
}), (None, -2, {}), (256, 3, {
'padding': 1
}), (32, 1, {})]
# The include_last_relu=false here is because we might want to change it to another function
self.proto_net, mask_dim = make_net(in_channels,
mask_proto_net,
include_last_relu=False)
self.selected_layers = [2, 3, 4]
src_channels = self.backbone.channels
# Some hacky rewiring to accomodate the FPN
self.fpn = FPN([src_channels[i] for i in self.selected_layers])
self.selected_layers = list(range(len(self.selected_layers) + 2))
src_channels = [256] * len(self.selected_layers)
self.prediction_layers = nn.ModuleList()
pred_aspect_ratios = [[[1, 1 / 2, 2]]] * 5
pred_scales = [[24], [48], [96], [192], [384]]
for idx, layer_idx in enumerate(self.selected_layers):
# If we're sharing prediction module weights, have every module's parent be the first one
parent = None
if idx > 0: parent = self.prediction_layers[0]
pred = PredictionModule(src_channels[layer_idx],
src_channels[layer_idx],
aspect_ratios=pred_aspect_ratios[idx],
scales=pred_scales[idx],
parent=parent)
self.prediction_layers.append(pred)
self.semantic_seg_conv = nn.Conv2d(src_channels[0], 80, kernel_size=1)
self.detect = Detect(81,
bkg_label=0,
top_k=200,
conf_thresh=0.05,
nms_thresh=0.5)
def __init__(self, phase, size, base, extras, head, num_classes):
super(SSD, self).__init__()
self.phase = phase # 'train'或'test'
self.size = size # 输入尺寸=300
self.num_classes = num_classes # 类别数
self.cfg = VOC # 配置信息
self.priorbox = PriorBox(self.cfg) # 产生先验框
with torch.no_grad(): # 不使用梯度
self.priors = self.priorbox.forward()
self.vgg = nn.ModuleList(base) # 根据'base'建立nn.ModuleList对象
self.L2Norm = L2Norm(512, 20) # conv4_3后使用L2正则化
self.extras = nn.ModuleList(extras) # VGG-16后额外添加的四层
self.loc = nn.ModuleList(head[0]) # 位置预测
self.conf = nn.ModuleList(head[1]) # 置信度预测
if phase == 'test': # 测试阶段需要不同处理
self.softmax = nn.Softmax(dim=-1)
self.detect = Detect(num_classes, 200, 0.01, 0.45)
class SSD(nn.Module):
"""Single Shot Multibox Architecture
The network is composed of a base VGG network followed by the
added multibox conv layers. Each multibox layer branches into
1) conv2d for class conf scores
2) conv2d for localization predictions
3) associated priorbox layer to produce default bounding
boxes specific to the layer's feature map size.
See: https://arxiv.org/pdf/1512.02325.pdf for more details.
Args:
phase: (string) Can be "test" or "train"
size: input image size
base: VGG16 layers for input, size of either 300 or 500
extras: extra layers that feed to multibox loc and conf layers
head: "multibox head" consists of loc and conf conv layers
"""
def __init__(self, phase, size, Basenet, Neck, Head, cfg):
super(SSD, self).__init__()
self.phase = phase
self.cfg = cfg
self.priorbox = PriorBox(self.cfg)
self.priors = self.priorbox.forward()
self.size = size
# SSD network
self.basenet = Basenet
self.neck = Neck
self.head = Head
self.num_classes = cfg['num_classes']
self.softmax = nn.Softmax(dim=-1)
self.detect = Detect(self.num_classes, 0, 200, 0.01, 0.45,
variance=cfg['variance'], nms_kind=cfg['nms_kind'], beta1=cfg['beta1'])
def forward(self, x, phase):
"""Applies network layers and ops on input image(s) x.
Args:
x: input image or batch of images. Shape: [batch,3,300,300].
Return:
Depending on phase:
test:
Variable(tensor) of output class label predictions,
confidence score, and corresponding location predictions for
each object detected. Shape: [batch,topk,7]
train:
list of concat outputs from:
1: confidence layers, Shape: [batch*num_priors,num_classes]
2: localization layers, Shape: [batch,num_priors*4]
3: priorbox layers, Shape: [2,num_priors*4]
"""
x = self.basenet(x)
if self.neck is not None:
x = self.neck(x)
conf, loc = self.head(x)
loc = torch.cat([o.view(o.size(0), -1) for o in loc], 1)
conf = torch.cat([o.view(o.size(0), -1) for o in conf], 1)
if phase == "test":
output = self.detect.trans(
loc.view(loc.size(0), -1, 4), # loc preds
self.softmax(conf.view(conf.size(0), -1,
self.num_classes)), # conf preds
#self.priors.type(type(x.data)) # default boxes
self.priors
)
else:
output = (
loc.view(loc.size(0), -1, 4),
conf.view(conf.size(0), -1, self.num_classes),
self.priors
)
return output
def load_weights(self, base_file):
other, ext = os.path.splitext(base_file)
if ext == '.pkl' or '.pth':
print('Loading weights into state dict...')
self.load_state_dict(torch.load(base_file,
map_location=lambda storage, loc: storage))
print('Finished!')
else:
print('Sorry only .pth and .pkl files supported.')
print('Epoch {}, iter {}, lr {:.6f}, loss {:.2f}, time {:.2f}s, eta {:.2f}h'.format(
epoch,
iteration,
optimizer.param_groups[0]['lr'],
loss.item(),
load_time,
load_time * (max_iter - iteration) / 3600,
))
timer.clear()
save_weights(model)
print('Start Evaluation...')
thresh=0.005
max_per_image=300
model.eval()
detector = Detect(num_classes)
transform = BaseTransform(args.size)
num_images = len(testset)
all_boxes = [[[] for _ in range(num_images)] for _ in range(num_classes)]
rgbs = dict()
os.makedirs("draw/", exist_ok=True)
os.makedirs("draw/{}/".format(args.dataset), exist_ok=True)
_t = {'im_detect': Timer(), 'im_nms': Timer()}
for i in range(num_images):
img = testset.pull_image(i)
scale = torch.Tensor([img.shape[1], img.shape[0], img.shape[1], img.shape[0]])
with torch.no_grad():
x = transform(img).unsqueeze(0)
(x, scale) = (x.cuda(), scale.cuda())
_t['im_detect'].tic()
def eval_model(
model,
num_classes,
testset,
priors,
thresh=0.005,
max_per_image=300,
):
# Testing after training
print('Start Evaluation...')
model.eval()
detector = Detect(num_classes)
transform = BaseTransform(args.size, (104, 117, 123), (2, 0, 1))
num_images = len(testset)
all_boxes = [[[] for _ in range(num_images)] for _ in range(num_classes)]
rgbs = dict()
_t = {'im_detect': Timer(), 'im_nms': Timer()}
for i in range(num_images):
img = testset.pull_image(i)
scale = torch.Tensor(
[img.shape[1], img.shape[0], img.shape[1], img.shape[0]])
with torch.no_grad():
x = transform(img).unsqueeze(0)
(x, scale) = (x.cuda(), scale.cuda())
_t['im_detect'].tic()
out = model(x) # forward pass
(boxes, scores) = detector.forward(out, priors)
detect_time = _t['im_detect'].toc()
boxes *= scale # scale each detection back up to the image
boxes = boxes.cpu().numpy()
scores = scores.cpu().numpy()
_t['im_nms'].tic()
for j in range(1, num_classes):
inds = np.where(scores[:, j - 1] > thresh)[0]
if len(inds) == 0:
all_boxes[j][i] = np.empty([0, 5], dtype=np.float32)
continue
c_bboxes = boxes[inds]
c_scores = scores[inds, j - 1]
c_dets = np.hstack(
(c_bboxes, c_scores[:, np.newaxis])).astype(np.float32,
copy=False)
keep = nms(c_dets,
thresh=args.nms_thresh) # non maximum suppression
c_dets = c_dets[keep, :]
all_boxes[j][i] = c_dets
if max_per_image > 0:
image_scores = np.hstack(
[all_boxes[j][i][:, -1] for j in range(1, num_classes)])
if len(image_scores) > max_per_image:
image_thresh = np.sort(image_scores)[-max_per_image]
for j in range(1, num_classes):
keep = np.where(all_boxes[j][i][:, -1] >= image_thresh)[0]
all_boxes[j][i] = all_boxes[j][i][keep, :]
nms_time = _t['im_nms'].toc()
if i == 10:
_t['im_detect'].clear()
_t['im_nms'].clear()
if i % math.floor(num_images / 10) == 0 and i > 0:
print('[{}/{}]Time results: detect={:.2f}ms,nms={:.2f}ms,'.format(
i, num_images, detect_time * 1000, nms_time * 1000))
testset.evaluate_detections(all_boxes, 'eval/{}/'.format(args.dataset))
model.train()