Skip to content

Y
yolo3-pytorch

Calabaza amarga / yolo3-pytorch
与 Fork 源项目一致

从无法访问的项目Fork

通知 5
Star 0
Fork 0
Y
yolo3-pytorch

体验新版 GitCode，发现更多精彩内容 >>

未验证 提交 415a0184 编写于 作者: B Bubbliiiing 提交者： GitHub
浏览文件
操作

Update train.py

上级 7daaff0b
隐藏空白更改
内联 并排
Showing with 3 addition and 3 deletion
train.py
浏览文件 @ 415a0184
...@@ -152,7 +152,7 @@ if __name__ == "__main__": ...@@ -152,7 +152,7 @@ if __name__ == "__main__":
lr = 1e-3 lr = 1e-3
Batch_size = 8 Batch_size = 8
Init_Epoch = 0 Init_Epoch = 0
Freeze_Epoch = 25 Freeze_Epoch = 50
optimizer = optim.Adam(net.parameters(),lr) optimizer = optim.Adam(net.parameters(),lr)
lr_scheduler = optim.lr_scheduler.StepLR(optimizer,step_size=1,gamma=0.95) lr_scheduler = optim.lr_scheduler.StepLR(optimizer,step_size=1,gamma=0.95)
...@@ -185,8 +185,8 @@ if __name__ == "__main__": ...@@ -185,8 +185,8 @@ if __name__ == "__main__":
if True: if True:
lr = 1e-4 lr = 1e-4
Batch_size = 4 Batch_size = 4
Freeze_Epoch = 25 Freeze_Epoch = 50
Unfreeze_Epoch = 50 Unfreeze_Epoch = 100
optimizer = optim.Adam(net.parameters(),lr) optimizer = optim.Adam(net.parameters(),lr)
lr_scheduler = optim.lr_scheduler.StepLR(optimizer,step_size=1,gamma=0.95) lr_scheduler = optim.lr_scheduler.StepLR(optimizer,step_size=1,gamma=0.95)
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或