Comments (6)
buptlihang
commented on August 29, 2024
test1
model
model_esp_epoch_248_miou_0.7251.pth
IOU
- images: 0.536
- images_no_dress: 0.571
- val data: 0.7251
特别超参
- 训练集：std2.1
- 网络：original ESPNetV2
- config.input_w = 384
- config.input_h = 384
- config.core.optimizer = torch.optim.SGD(config.core.net.parameters(), 5e-3, momentum=0.9)
config.core.scheduler = optim.lr_scheduler.MultiStepLR(config.core.optimizer, milestones=[20,40,55,70,80,90,100,110,120,130,140,150,160], gamma=0.27030)
基本超参
- config.core.cls_num = 4
- 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)
- BorderTargetAugFactory('[email protected] => [email protected] => [email protected] => [email protected] => [email protected] => [email protected]
=> [email protected] => [email protected] => [email protected] => [email protected] => [email protected] =>
[email protected] => ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => [email protected] =>
ImageWithMasksNormalizeAug => BorderTargetAug => ImageWithTwoMasksToTensorAug', deepvac_config)
from espnet.
buptlihang
commented on August 29, 2024
test2
model
gemfield_epoch_186.pth
IOU
- images: 0.572
- images_no_dress: 0.615
- val data: 0.73?
特别超参
- 训练集：std2.1
- 网络：original ESPNetV2
- config.input_w = 384
- config.input_h = 384
- config.core.optimizer = torch.optim.Adam(config.core.net.parameters(), 5e-4, (0.9, 0.999))
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)
基本超参
- config.core.cls_num = 4
- 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)
- BorderTargetAugFactory('[email protected] => [email protected] => [email protected] => [email protected] => [email protected] => [email protected]
=> [email protected] => [email protected] => [email protected] => [email protected] => [email protected] =>
[email protected] => ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => [email protected] =>
ImageWithMasksNormalizeAug => BorderTargetAug => ImageWithTwoMasksToTensorAug', deepvac_config)
from espnet.
buptlihang
commented on August 29, 2024
test3
model
model_fusion_0.7428.pth
IOU
- images：0.574
- images_no_dress: 0.615
- val data: 0.7428
特别超参
- 训练集：std2.1
- 网络：semantic+detail+fusion
- config.input_w = 384
- config.input_h = 384
- config.core.optimizer = torch.optim.SGD(config.core.net.parameters(), 5e-3, momentum=0.9)
- config.core.scheduler = optim.lr_scheduler.MultiStepLR(config.core.optimizer, milestones=[20,40,55,70,80,90,100,110,120,130,140,150,160], gamma=0.27030)
基本超参
- config.core.cls_num = 4
- 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)
- BorderTargetAugFactory('[email protected] => [email protected] => [email protected] => [email protected] => [email protected] => [email protected]
=> [email protected] => [email protected] => [email protected] => [email protected] => [email protected] =>
[email protected] => ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => [email protected] =>
ImageWithMasksNormalizeAug => BorderTargetAug => ImageWithTwoMasksToTensorAug', deepvac_config)
from espnet.
buptlihang
commented on August 29, 2024
test4
model
model_fusion_0.7473.pth
IOU
- images: 0.578
- images_no_dress: 0.624
- val data: 0.7473
特别超参
- 训练集：std2.1
- 网络：semantic+detail+fusion
- config.input_w = 384
- config.input_h = 384
- config.core.optimizer = torch.optim.Adam(config.core.net.parameters(), 5e-4, (0.9, 0.999))
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)
基本超参
- config.core.cls_num = 4
- 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)
- BorderTargetAugFactory('[email protected] => [email protected] => [email protected] => [email protected] => [email protected] => [email protected]
=> [email protected] => [email protected] => [email protected] => [email protected] => [email protected] =>
[email protected] => ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => [email protected] =>
ImageWithMasksNormalizeAug => BorderTargetAug => ImageWithTwoMasksToTensorAug', deepvac_config)
from espnet.
buptlihang
commented on August 29, 2024
test5
model
model_synthesis_epoch_155_0.7394.pth
IOU
- images: 0.586
- images_no_dress: 0.626
- val data: 0.7394
特别超参
- 训练集：std2.1+synthesis(2800+5700)
- 网络：original ESPNetV2
- config.input_w = 384
- config.input_h = 384
- config.core.optimizer = torch.optim.SGD(config.core.net.parameters(), 5e-3, momentum=0.9)
config.core.scheduler = optim.lr_scheduler.MultiStepLR(config.core.optimizer, milestones=[20,40,55,70,80,90,100,110,120,130,140,150,160], gamma=0.27030)
基本超参
- config.core.cls_num = 4
- 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)
- BorderTargetAugFactory('[email protected] => [email protected] => [email protected] => [email protected] => [email protected] => [email protected]
=> [email protected] => [email protected] => [email protected] => [email protected] => [email protected] =>
[email protected] => ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => [email protected] =>
ImageWithMasksNormalizeAug => BorderTargetAug => ImageWithTwoMasksToTensorAug', deepvac_config)
from espnet.
buptlihang
commented on August 29, 2024
test6
model
model_synthesis_bg_0.7405.pth
IOU
- images: 0.584
- images_no_dress: 0.627
- val data: 0.7405
特别超参
- 训练集：std2.1+Synthesis+bg(2800+5700+2000)
- 网络：original ESPNetV2
- config.input_w = 384
- config.input_h = 384
- config.core.optimizer = torch.optim.SGD(config.core.net.parameters(), 5e-3, momentum=0.9)
config.core.scheduler = optim.lr_scheduler.MultiStepLR(config.core.optimizer, milestones=[20,40,55,70,80,90,100,110,120,130,140,150,160], gamma=0.27030)
基本超参
- config.core.cls_num = 4
- 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)
- BorderTargetAugFactory('[email protected] => [email protected] => [email protected] => [email protected] => [email protected] => [email protected]
=> [email protected] => [email protected] => [email protected] => [email protected] => [email protected] =>
[email protected] => ImageWithMasksCenterCropAug => ImageWithMasksScaleAug => [email protected] =>
ImageWithMasksNormalizeAug => BorderTargetAug => ImageWithTwoMasksToTensorAug', deepvac_config)
from espnet.
Related Issues (9)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from espnet.