THEH：

config.DATASET = edict()
config.DATASET.H_min = 96 # 192
config.DATASET.H_max = 224 # 448
config.DATASET.W_mid = 128 # 256
config.DATASET.train_num = 200
config.DATASET.val_num = 10
config.DATASET.all_num = 210
config.DATASET.data_size = [80,256,256] # [80,512,512] # [160,256,256]
config.DATASET.CutWindow = [-150,350] # [-50, 200] # [-79, 304]
config.DATASET.Z_Score_mean = -150
config.DATASET.Z_Score_std = 500

config.TRAIN = edict()
config.TRAIN.with_eval = True
config.TRAIN.loss_weights = [1,1,2] # [0.1, 0.5, 5]#[0.05, 0.45, 0.5]
config.TRAIN.patch_size = [64, 128, 128] # [80, 256, 256] #
config.TRAIN.batch_size = 18
config.TRAIN.lr = 0.001 # 0.001
config.TRAIN.WD = 0.0005
config.TRAIN.END_EPOCH = 200
config.TRAIN.BEGIN_EPOCH = 0

1667736125381.png

50 KiB

GBB：

1667804178385

1667794165377.png

50 KiB

1667789643690.png

70 KiB

1667804178385.png

51 KiB

WPF

config.DATASET.data_size = [80,256,256] # [80,512,512] # [160,256,256]
config.DATASET.CutWindow = [-79, 304] # [-150,350] # [-50, 200] # [-79, 304]
config.DATASET.Z_Score_mean = 101 # 101 # -150
config.DATASET.Z_Score_std = 76.9 # 76.9 # 500

1667810197569.png

50 KiB

Deleting a branch is permanent. It CANNOT be undone. Continue?

Dear OpenI User

Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.

For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》

#1 实验记录

THEH：

GBB：

WPF