Bienqq
/
car-detection-bayes
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

updates

This commit is contained in:
glenn-jocher 2019-07-04 22:10:46 +02:00
parent d0eace6cec
commit abf59f1565
2 changed files with 13 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
train.py
View File

@ -18,8 +18,8 @@ hyp = {'giou': 1.008, # giou loss gain
'wh': 0.1845, # wh loss gain 'wh': 0.1845, # wh loss gain
'cls': 16.94, # cls loss gain 'cls': 16.94, # cls loss gain
'cls_pw': 6.215, # cls BCELoss positive_weight 'cls_pw': 6.215, # cls BCELoss positive_weight
'conf': 10.61, # conf loss gain 'obj': 10.61, # obj loss gain
'conf_pw': 4.272, # conf BCELoss positive_weight 'obj_pw': 4.272, # obj BCELoss positive_weight
'iou_t': 0.251, # iou target-anchor training threshold 'iou_t': 0.251, # iou target-anchor training threshold
'lr0': 0.001, # initial learning rate 'lr0': 0.001, # initial learning rate
'lrf': -4., # final learning rate = lr0 * (10 ** lrf) 'lrf': -4., # final learning rate = lr0 * (10 ** lrf)
@ -34,8 +34,8 @@ hyp = {'giou': 1.008, # giou loss gain
# 'wh': 0.10, # wh loss gain # 'wh': 0.10, # wh loss gain
# 'cls': 0.035, # cls loss gain # 'cls': 0.035, # cls loss gain
# 'cls_pw': 79.0, # cls BCELoss positive_weight # 'cls_pw': 79.0, # cls BCELoss positive_weight
# 'conf': 1.61, # conf loss gain # 'obj': 1.61, # obj loss gain
# 'conf_pw': 3.53, # conf BCELoss positive_weight # 'obj_pw': 3.53, # obj BCELoss positive_weight
# 'iou_t': 0.29, # iou target-anchor training threshold # 'iou_t': 0.29, # iou target-anchor training threshold
# 'lr0': 0.001, # initial learning rate # 'lr0': 0.001, # initial learning rate
# 'lrf': -4., # final learning rate = lr0 * (10 ** lrf) # 'lrf': -4., # final learning rate = lr0 * (10 ** lrf)
@ -174,7 +174,7 @@ def train(
for epoch in range(start_epoch, epochs): for epoch in range(start_epoch, epochs):
model.train() model.train()
print(('\n%8s%12s' + '%10s' * 7) % print(('\n%8s%12s' + '%10s' * 7) %
('Epoch', 'Batch', 'xy', 'wh', 'conf', 'cls', 'total', 'targets', 'img_size')) ('Epoch', 'Batch', 'xy', 'wh', 'obj', 'cls', 'total', 'targets', 'img_size'))
# Update scheduler # Update scheduler
scheduler.step() scheduler.step()

16
utils/utils.py
View File

@ -273,27 +273,27 @@ def wh_iou(box1, box2):
def compute_loss(p, targets, model, giou_loss=False): # predictions, targets, model def compute_loss(p, targets, model, giou_loss=False): # predictions, targets, model
ft = torch.cuda.FloatTensor if p[0].is_cuda else torch.Tensor ft = torch.cuda.FloatTensor if p[0].is_cuda else torch.Tensor
lxy, lwh, lcls, lconf = ft([0]), ft([0]), ft([0]), ft([0]) lxy, lwh, lcls, lobj = ft([0]), ft([0]), ft([0]), ft([0])
txy, twh, tcls, tbox, indices, anchor_vec = build_targets(model, targets) txy, twh, tcls, tbox, indices, anchor_vec = build_targets(model, targets)
h = model.hyp # hyperparameters h = model.hyp # hyperparameters
# Define criteria # Define criteria
MSE = nn.MSELoss() MSE = nn.MSELoss()
CE = nn.CrossEntropyLoss() # (weight=model.class_weights)
BCEcls = nn.BCEWithLogitsLoss(pos_weight=ft([h['cls_pw']])) BCEcls = nn.BCEWithLogitsLoss(pos_weight=ft([h['cls_pw']]))
BCEconf = nn.BCEWithLogitsLoss(pos_weight=ft([h['conf_pw']])) BCEobj = nn.BCEWithLogitsLoss(pos_weight=ft([h['obj_pw']]))
# CE = nn.CrossEntropyLoss() # (weight=model.class_weights)
# Compute losses # Compute losses
bs = p[0].shape[0] # batch size bs = p[0].shape[0] # batch size
k = bs / 64 # loss gain k = bs / 64 # loss gain
for i, pi0 in enumerate(p): # layer i predictions, i for i, pi0 in enumerate(p): # layer i predictions, i
b, a, gj, gi = indices[i] # image, anchor, gridy, gridx b, a, gj, gi = indices[i] # image, anchor, gridy, gridx
tconf = torch.zeros_like(pi0[..., 0]) # conf tobj = torch.zeros_like(pi0[..., 0]) # target obj
# Compute losses # Compute losses
if len(b): # number of targets if len(b): # number of targets
pi = pi0[b, a, gj, gi] # predictions closest to anchors pi = pi0[b, a, gj, gi] # predictions closest to anchors
tconf[b, a, gj, gi] = 1.0 # conf tobj[b, a, gj, gi] = 1.0 # obj
# pi[..., 2:4] = torch.sigmoid(pi[..., 2:4]) # wh power loss (uncomment) # pi[..., 2:4] = torch.sigmoid(pi[..., 2:4]) # wh power loss (uncomment)
if giou_loss: if giou_loss:
@ -313,10 +313,10 @@ def compute_loss(p, targets, model, giou_loss=False): # predictions, targets, m
# with open('targets.txt', 'a') as file: # with open('targets.txt', 'a') as file:
# [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)] # [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)]
lconf += (k * h['conf']) * BCEconf(pi0[..., 4], tconf) # obj_conf loss lobj += (k * h['obj']) * BCEobj(pi0[..., 4], tobj) # obj loss
loss = lxy + lwh + lconf + lcls loss = lxy + lwh + lobj + lcls
return loss, torch.cat((lxy, lwh, lconf, lcls, loss)).detach() return loss, torch.cat((lxy, lwh, lobj, lcls, loss)).detach()
def build_targets(model, targets): def build_targets(model, targets):