关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
edwardyehuang
/
iSeg
mirror of https://github.com/edwardyehuang/iSeg
Not watched
1
0
Fork 0
Code
Releases 7 Wiki Activity
Issues 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
374 Commits
1 Branch
2.1 MiB
240 Download
 
Branch: master
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'master'
${ noResults }
iSeg/utils
edwardyehuang 70a33051d5 add bfloat16 weights.h5 load support 2 months ago
..
__init__.py relocate get_tensor_shape 3 months ago
attention_utils.py relocate get_tensor_shape 3 months ago
common.py predict code refactor 3 months ago
data_loader.py code improvement 3 months ago
distribution_utils.py sync inner changes 2 months ago
drops.py drop path sep to drop.py 2 years ago
hdf5_utils.py fix single loss issue in keras 3 2 months ago
keras3_utils.py fixed maa issue in keras 3 2 months ago
keras_ops.py sync internal code (keras3 warpper) 2 months ago
slash_utils.py Now the code can run in keras 3 2 months ago
sliding_window_inference_utils.py predict code refactor 3 months ago
sugars.py improve patch emb 4 months ago
tensor_convert_utils.py add bfloat16 weights.h5 load support 2 months ago
train_utils.py refactor layerwise decay 4 months ago
value_check.py add check_numerics level 1 year ago
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

No Description

Python

Contributors (1)
All

Please read the following content carefully:

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》

Agree and continue
Disagree, exit