新增mambavision模型 - #3432
Open
Dancho1009 wants to merge 2 commits into
Open
Conversation
|
Thanks for your contribution! |
Dancho1009
force-pushed
the
feat/mambavision
branch
from
July 16, 2026 08:52
3c15522 to
aa9e25e
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
修改内容
sequential和parallelselective scan 实现,不依赖自定义 CUDA 算子。复现精度
本次复现目标为模型结构、预训练权重和前向输出对齐,不包含使用 PaddlePaddle 从头完整训练复现论文精度。
100%。1e-4,最差结果为8.440e-05。1.639e-06。测试
TIPC 使用
MambaVision_T完成lite_train_lite_infer模式验证:训练
训练环境:Python 3.9、PaddlePaddle-GPU 2.6.2、PaddleClas
release/2.6、单卡 NVIDIA GPU。全部 11 个规格均通过 PaddleClas 官方
tools/train.py完成真实 ImageNet-1K 固定批次 50-step 可训练性验证,Loss 均下降且未出现 NaN、Inf 或 AMP overflow。该测试用于验证训练链路,不代表完整 ImageNet 训练或精度复现。模型权重
PaddlePaddle 权重下载地址:AI Studio MambaVision 模型空间
下载对应
.pdparams文件后,通过Global.pretrained_model或模型工厂的pretrained参数传入本地路径。相关链接