gemfield commented 3 years ago

IoU 金榜

test9: 91.5%
test5: 90.9%
test6: 90.5%
test7: 90.5%
test3: 87.2%
test2: 86.9%
test4: 86.3%
test1: 85.7%
test8: 85.6%

1icas commented 3 years ago

test1

IoU

label: 85.7%
label_no_mix: ??

特别超参

训练集：HumanSeg-Mapillary
config.input_w = 224
config.input_h = 384
config.core.optimizer = torch.optim.SGD(config.core.net.parameters(), 0.01, momentum=0.9)
config.core.scheduler = optim.lr_scheduler.MultiStepLR(config.core.optimizer, milestones=[4, 8, 12, 15], gamma=0.1)

基本超参

config.core.cls_num = 2
config.core.batch_size = 64
config.core.mean = config.data['mean']
config.core.std = config.data['std']
config.core.model_path = "/opt/public/pretrain/ESPNetv2/imagenet/espnetv2_s_2.0.pth"
config.core.criterion = torch.nn.CrossEntropyLoss(weight)
AugFactory('SpeckleAug@0.1 => GaussianAug@0.1 => HorlineAug@0.1 => VerlineAug@0.1 => LRmotionAug@0.1 =>UDmotionAug@0.1 => NoisyAug@0.1 => DarkAug@0.1 => ColorJitterAug@0.15 => BrightnessJitterAug@0.15 =>ContrastJitterAug@0.15 => ImageWithMasksRandomRotateAug@0.6 => ImageWithMasksNormalizeAug =>ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => ImageWithMasksHFlipAug@0.5 =>ImageWithMasksToTensorAug', deepvac_config)

1icas commented 3 years ago

test2

IoU

label: 86.9%
label_no_mix: ??

特别超参

训练集：HumanSeg-Mapillary + 1倍HumanSeg-Mapillary 背景替换
config.input_w = 224
config.input_h = 384
config.core.optimizer = torch.optim.SGD(config.core.net.parameters(), 0.01, momentum=0.9)
config.core.scheduler = optim.lr_scheduler.MultiStepLR(config.core.optimizer, milestones=[4, 8, 12, 15], gamma=0.1)

基本超参

  config.core.cls_num = 2
  config.core.batch_size = 64
  config.core.mean = config.data['mean']
  config.core.std = config.data['std']
  config.core.model_path = "/opt/public/pretrain/ESPNetv2/imagenet/espnetv2_s_2.0.pth"
  config.core.criterion = torch.nn.CrossEntropyLoss(weight)
  AugFactory('SpeckleAug@0.1 => GaussianAug@0.1 => HorlineAug@0.1 => VerlineAug@0.1 => LRmotionAug@0.1 =>UDmotionAug@0.1 => NoisyAug@0.1 => DarkAug@0.1 => ColorJitterAug@0.15 => BrightnessJitterAug@0.15 =>ContrastJitterAug@0.15 => ImageWithMasksRandomRotateAug@0.6 => ImageWithMasksNormalizeAug =>ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => ImageWithMasksHFlipAug@0.5 =>ImageWithMasksToTensorAug', deepvac_config)

1icas commented 3 years ago

test3

IoU

label: 87.2%
label_no_mix: ??

特别超参

训练集：HumanSeg-Mapillary + 4倍HumanSeg-Mapillary 背景替换
config.input_w = 224
config.input_h = 384
config.core.optimizer = torch.optim.SGD(config.core.net.parameters(), 0.01, momentum=0.9)
config.core.scheduler = optim.lr_scheduler.MultiStepLR(config.core.optimizer, milestones=[4, 8, 12, 15], gamma=0.1)

基本超参

  config.core.cls_num = 2
  config.core.batch_size = 64
  config.core.mean = config.data['mean']
  config.core.std = config.data['std']
  config.core.model_path = "/opt/public/pretrain/ESPNetv2/imagenet/espnetv2_s_2.0.pth"
  config.core.criterion = torch.nn.CrossEntropyLoss(weight)
  AugFactory('SpeckleAug@0.1 => GaussianAug@0.1 => HorlineAug@0.1 => VerlineAug@0.1 => LRmotionAug@0.1 =>UDmotionAug@0.1 => NoisyAug@0.1 => DarkAug@0.1 => ColorJitterAug@0.15 => BrightnessJitterAug@0.15 =>ContrastJitterAug@0.15 => ImageWithMasksRandomRotateAug@0.6 => ImageWithMasksNormalizeAug =>ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => ImageWithMasksHFlipAug@0.5 =>ImageWithMasksToTensorAug', deepvac_config)

1icas commented 3 years ago

test4

IoU

label: 86.3%
label_no_mix: ??

特别超参

训练集：HumanSeg-Mapillary + 4倍HumanSeg-Mapillary 背景替换 + 2w张纯背景
config.input_w = 224
config.input_h = 384
config.core.optimizer = torch.optim.SGD(config.core.net.parameters(), 0.01, momentum=0.9)
config.core.scheduler = optim.lr_scheduler.MultiStepLR(config.core.optimizer, milestones=[4, 8, 12, 15], gamma=0.1)

基本超参

  config.core.cls_num = 2
  config.core.batch_size = 64
  config.core.mean = config.data['mean']
  config.core.std = config.data['std']
  config.core.model_path = "/opt/public/pretrain/ESPNetv2/imagenet/espnetv2_s_2.0.pth"
  config.core.criterion = torch.nn.CrossEntropyLoss(weight)
  AugFactory('SpeckleAug@0.1 => GaussianAug@0.1 => HorlineAug@0.1 => VerlineAug@0.1 => LRmotionAug@0.1 =>UDmotionAug@0.1 => NoisyAug@0.1 => DarkAug@0.1 => ColorJitterAug@0.15 => BrightnessJitterAug@0.15 =>ContrastJitterAug@0.15 => ImageWithMasksRandomRotateAug@0.6 => ImageWithMasksNormalizeAug =>ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => ImageWithMasksHFlipAug@0.5 =>ImageWithMasksToTensorAug', deepvac_config)

1icas commented 3 years ago

test5

IoU

label: 90.9%
label_no_mix:90.8%

特别超参

训练集：HumanSeg-Mapillary + CoCo + 2.5w张纯背景
config.core.optimizer = torch.optim.SGD(config.core.net.parameters(), 0.01, momentum=0.9, weight_decay=1e-5)
config.core.scheduler = optim.lr_scheduler.MultiStepLR(config.core.optimizer, milestones=[6, 12, 15, 18], gamma=0.1)

模型修改

去掉了网络中所有的nn.Dropout2d

基本超参

config.input_w = 384
config.input_h = 384
config.core.cls_num = 2
config.core.batch_size = 16
config.core.mean = config.data['mean']
config.core.std = config.data['std']
config.core.model_path = "/opt/public/pretrain/ESPNetv2/imagenet/espnetv2_s_2.0.pth"
config.core.criterion = torch.nn.CrossEntropyLoss(weight)
AugFactory('SpeckleAug@0.1 => GaussianAug@0.1 => HorlineAug@0.1 => VerlineAug@0.1 => LRmotionAug@0.1 =>UDmotionAug@0.1 => NoisyAug@0.1 => DarkAug@0.1 => ColorJitterAug@0.15 => BrightnessJitterAug@0.15 =>ContrastJitterAug@0.15 => ImageWithMasksRandomRotateAug@0.6 => ImageWithMasksNormalizeAug =>ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => ImageWithMasksHFlipAug@0.5 =>ImageWithMasksToTensorAug', deepvac_config)

MHGL commented 3 years ago

test6

IoU

epoch: 93
labels: 90.5%
labels_no_mix: 90.1%
特别超参
训练集： deepvac-chengdu(1526 no mix) + deepvac-waibao(1589 no mix)
config.input_w = 384
config.input_h = 384

config.core.criterion = torch.nn.CrossEntropyLoss(weight)

基本超参

config.core.epoch_num = 100
config.core.cls_num = 2
config.core.batch_size = 16
config.core.mean = config.data['mean']
config.core.std = config.data['std']
config.core.optimizer = torch.optim.Adam(config.core.net.parameters(), 3e-4, (0.9, 0.999), eps=1e-08, weight_decay=5e-4)
lambda_lr = lambda epoch: round ((1 - epoch/config.core.epoch_num) ** 0.9, 8)
config.core.scheduler = optim.lr_scheduler.LambdaLR(config.core.optimizer, lr_lambda=lambda_lr)
config.core.model_path = "/opt/public/pretrain/ESPNetv2/imagenet/espnetv2_s_2.0.pth"
AugFactory('SpeckleAug@0.1 => GaussianAug@0.1 => HorlineAug@0.1 => VerlineAug@0.1 => LRmotionAug@0.1 =>UDmotionAug@0.1 => NoisyAug@0.1 => DarkAug@0.1 => ColorJitterAug@0.15 => BrightnessJitterAug@0.15 =>ContrastJitterAug@0.15 => ImageWithMasksRandomRotateAug@0.6 => ImageWithMasksNormalizeAug =>ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => ImageWithMasksHFlipAug@0.5 =>ImageWithMasksToTensorAug', deepvac_config)

MHGL commented 3 years ago

test7

IoU

epoch: 95
labels: 90.5%
labels_no_mix: 90.3%
特别超参
训练集： deepvac-chengdu(1526 no mix) + deepvac-waibao(1589 no mix)
config.input_w = 384
config.input_h = 384

config.core.criterion = bce_loss + dice_loss

基本超参

config.core.epoch_num = 100
config.core.cls_num = 2
config.core.batch_size = 16
config.core.mean = config.data['mean']
config.core.std = config.data['std']
config.core.optimizer = torch.optim.Adam(config.core.net.parameters(), 3e-4, (0.9, 0.999), eps=1e-08, weight_decay=5e-4)
lambda_lr = lambda epoch: round ((1 - epoch/config.core.epoch_num) ** 0.9, 8)
config.core.scheduler = optim.lr_scheduler.LambdaLR(config.core.optimizer, lr_lambda=lambda_lr)
config.core.model_path = "/opt/public/pretrain/ESPNetv2/imagenet/espnetv2_s_2.0.pth"
AugFactory('SpeckleAug@0.1 => GaussianAug@0.1 => HorlineAug@0.1 => VerlineAug@0.1 => LRmotionAug@0.1 =>UDmotionAug@0.1 => NoisyAug@0.1 => DarkAug@0.1 => ColorJitterAug@0.15 => BrightnessJitterAug@0.15 =>ContrastJitterAug@0.15 => ImageWithMasksRandomRotateAug@0.6 => ImageWithMasksNormalizeAug =>ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => ImageWithMasksHFlipAug@0.5 =>ImageWithMasksToTensorAug', deepvac_config)

MHGL commented 3 years ago

test8

IoU

前sota模型
labels: 85.6%
labels_no_mix: 85.5%
特别超参
训练集： deepvac-chengdu(1526 no mix) + supervisely(5711)
config.input_w = 384
config.input_h = 384

config.core.criterion = bce_loss + dice_loss

基本超参

config.core.epoch_num = 100
config.core.cls_num = 2
config.core.batch_size = 16
config.core.mean = config.data['mean']
config.core.std = config.data['std']
config.core.optimizer = torch.optim.Adam(config.core.net.parameters(), 3e-4, (0.9, 0.999), eps=1e-08, weight_decay=5e-4)
lambda_lr = lambda epoch: round ((1 - epoch/config.core.epoch_num) ** 0.9, 8)
config.core.scheduler = optim.lr_scheduler.LambdaLR(config.core.optimizer, lr_lambda=lambda_lr)
config.core.model_path = "/opt/public/pretrain/ESPNetv2/imagenet/espnetv2_s_2.0.pth"

MHGL commented 3 years ago

test9

IoU

epoch: 71
labels: 91.5%
labels_no_mix: 91.4%
特别超参
训练集： deepvac-chengdu(1646 no mix) + deepvac-waibao(4399 no mix) + onlyBG(1000)
config.input_w = 384
config.input_h = 384

config.core.criterion = CrossEntropyLoss

基本超参

config.core.epoch_num = 100
config.core.cls_num = 2
config.core.batch_size = 16
config.core.mean = config.data['mean']
config.core.std = config.data['std']
config.core.optimizer = torch.optim.Adam(config.core.net.parameters(), 3e-4, (0.9, 0.999), eps=1e-08, weight_decay=5e-4)
lambda_lr = lambda epoch: round ((1 - epoch/config.core.epoch_num) ** 0.9, 8)
config.core.scheduler = optim.lr_scheduler.LambdaLR(config.core.optimizer, lr_lambda=lambda_lr)
config.core.model_path = "/opt/public/pretrain/ESPNetv2/imagenet/espnetv2_s_2.0.pth"
AugFactory('SpeckleAug@0.1 => GaussianAug@0.1 => HorlineAug@0.1 => VerlineAug@0.1 => LRmotionAug@0.1 =>UDmotionAug@0.1 => NoisyAug@0.1 => DarkAug@0.1 => ColorJitterAug@0.15 => BrightnessJitterAug@0.15 =>ContrastJitterAug@0.15 => ImageWithMasksRandomRotateAug@0.6 => ImageWithMasksNormalizeAug =>ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => ImageWithMasksHFlipAug@0.5 =>ImageWithMasksToTensorAug', deepvac_config)

DeepVAC / ESPNet

deepvac_human_accept600 SOTA #15

IoU 金榜

test1

IoU

特别超参

基本超参

test2

IoU

特别超参

基本超参

test3

IoU

特别超参

基本超参

test4

IoU

特别超参

基本超参

test5

IoU

特别超参

模型修改

基本超参

test6

IoU

特别超参

基本超参

test7

IoU

特别超参

基本超参

test8

IoU

特别超参

基本超参

test9

IoU

特别超参

基本超参