-
Notifications
You must be signed in to change notification settings - Fork 55
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
基于libai复现SegFormer[projects] #342
Comments
YOLO系列的有相关同事在做. 从我个人的角度来说 比较偏向于添加不同任务的模型, 也就是Segformer. 看看其他同事有什么意见 |
嗯我也觉得添加不同任务的模型目前是个不错的选择,另外这里的yolos不是基于卷积的yolo v1-v5等等,是基于transformer的目目标检测, 与DETR也有所不同。这个按任务分类的话可以在分割做完后推进。 |
OneFlow 算子缺失:oneflow.nn.Dropout2d Pytorch文档
dropout2d在图像处理中用的较多,让一个feature map的channel归零,当然类似还有dropout3d |
libai lazycall与flowvision的类型问题:
size为int没问题,是其他的就会报错,因为lazycall后类型改变omegaconf.listconfig.ListConfig |
from libai.config import LazyCall, instantiate
from flowvision import transforms
train_aug = LazyCall(transforms.Compose)(
transforms=[
LazyCall(transforms.RandomResizedCrop)(
size=(512, 1024),
)
]
)
print(instantiate(train_aug))
# (oneflow-dev-gcc7-v2) xiezipeng@vs008:~/libai/xzp$ python test.py
# loaded library: /lib/libibverbs.so.1
# Compose(
# RandomResizedCrop(size=[512, 1024], scale=(0.08, 1.0), ratio=(0.75, 1.3333), interpolation=bilinear)
# ) 是这个意思吗,我这好像没问题, @zhanggj821 |
打印是没有问题的,但是将这个数据增强size=( _ , _)应用到数据集上就会类型检查报错,但是我看cifar的数据增强的size也是元组形式,不知道会不会报错,我等下将分支更新一下可以跑看看 |
moudle无参数问题
当在module中设置参数nn.Parameter to_global后打印模型无该参数 |
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
基于transformer的语义分割模型
论文地址
项目目的
预期结果
The text was updated successfully, but these errors were encountered: