a92a0b29e9
更新模型结构，大步长反卷积后移，启用BN和tanh
2026-01-15 21:12:27 +08:00
df703638da
清理代码，删除跳连接部分
2026-01-11 13:25:34 +08:00
c5502cc87c
修改梯度裁剪的恶性bug，当前能进行训练，但是无论是否使用跳连接，预测帧总是输出对称的的效果，mse收敛到0.10
2026-01-11 10:50:11 +08:00
12de74f130
完善了跳连接，在上decode块后增加特征精炼层，未测效果
2026-01-09 18:23:45 +08:00
500c2eb18f
更新归一化方式，当前直接映射，不利用均值标准差进行标准化
2026-01-08 16:10:24 +08:00
f7601e9170
初步可跑通，但loss计算有问题，不收敛
2026-01-08 09:43:23 +08:00
efd76bccd2
update .gitignore
2026-01-07 15:54:52 +08:00
4888619f9d
iniit .gitignore
2026-01-07 15:54:20 +08:00
7e9564ef20
test modify swiftformer to temporal input
2026-01-07 11:03:33 +08:00
Abdelrahman Shaker
4aa6cd6752
Create LICENSE
2025-07-18 16:04:30 +04:00
Abdelrahman Shaker
898d23ca89
Update README.md
2024-01-12 17:00:03 +04:00
Abdelrahman Shaker
3daedbd499
Merge pull request #15 from escorciav/main
...
Update README.md
2024-01-12 16:41:43 +04:00
Victor Escorcia
28ce806f55
Update README.md
...
Community drive contributions: SwiftFormer meets Android. Qualcomm S8G2
DSP/HTP hardware, via Qualcomm tooling (QNN). Details in #14 . Work done
by @3scorciav . Refer to his fork for details.
2024-01-12 10:27:15 +00:00
Abdelrahman Shaker
9b7df0d145
Merge pull request #12 from ThomasCai/main
...
Fix the issue when the distillation type is set to none.
2023-11-30 15:41:26 +04:00
caitianren
0ddadad723
Fix this bug when setting distillation-type to none
2023-11-29 20:15:00 +08:00
Abdelrahman Shaker
cd1f854e59
Update README.md
2023-10-02 21:54:23 +02:00
Abdelrahman Shaker
5c9b4ceece
Update README.md
2023-08-17 21:23:06 +04:00
Abdelrahman Shaker
7d5ca0c25b
Update README.md
2023-08-10 18:54:53 +04:00
Abdelrahman Shaker
28fd075488
Merge pull request #6 from Amshaker/code_enhancement
...
Code organization
2023-07-26 01:35:53 +04:00
Abdelrahman Shaker
37a4fe953d
Update swiftformer.py
2023-07-26 01:32:27 +04:00
Abdelrahman Shaker
ef5daec20c
Update slurm_train.sh
2023-07-26 01:20:31 +04:00
Abdelrahman Shaker
49bf3f55f0
Update README.md
2023-07-26 01:18:39 +04:00
amshaker
adae6417b6
update dist_train.sh
2023-07-26 01:11:47 +04:00
amshaker
ff08bf624d
update dis_train.sh
2023-07-26 01:05:35 +04:00
amshaker
670dea3e1f
update README.md
2023-07-26 00:59:51 +04:00
Abdelrahman Shaker
075daf69f8
Update README.md
2023-06-14 06:04:06 +04:00
Abdelrahman Shaker
18ed44ad4c
Update README.md
2023-04-24 12:16:24 +04:00
Abdelrahman Shaker
2d33114967
Update README.md
2023-03-28 05:10:26 +04:00
amshaker
574907f49b
Initial release of SwiftFormer
2023-03-26 23:31:59 +04:00
