curryJ

Exception: It's not possible to apply those transforms to your dataset: expected scalar type Float but found Double

1

### Description Thanks for this great project. I run the 02_state_of_the_art.ipynb,but I get a Exception which is the title; My computer is cuda10.1 and GPU version is rtx2080ti.I update the...

deeplabv3训练cityscapes数据集，loss是负数

2

我在aistudio上利用百度提供的cityscapes数据集进行deeplabv3p的训练，我按照paddleseg的教程进行训练，但是loss出现了负数。我调小了lr之后，问题还是没有解决。请问这是什么原因呀？谢谢 


I don't understand the parameter layer_inter's meaning. Is it a representation of the type of layer,like the 1 is conv layer and the two is another type layer,or is it...

AttributeError: 'GQNTFRecordDataset' object has no attribute '_graph_attr'

2

Hello, I am trying to use your code to perform training again but I got this error I have downloaded the dataset and place it properly. And the dataset I...

Hi!Thanks for your code about DELG. I train my model by my own data,which has 116 classes.I edit the config file and generate the text file,where the line is like...

Pytorch vision

1

Could you tell me the pytorch vision of this code? Thank you!

Import Error

2

Thx for your code！ When I import VOC07PolygonMApMetric by this commad,I get this error,but I have this .py file in my gluoncv folder This is my python script  ...

 Do you know something about this problem? I search it in Internet but no clear answer. Thanks! edit at 2020/11/23 I find the issue above is caused by gpu...

谢谢楼主的工程；我在使用yolov4进行稀疏训练然后进行剪枝的时候，对一个地方有点困惑； 当我在进行稀疏训练的时候，bn weights分布如下  剪枝代码中，选取的阈值上限是每个BN层的gamma的最大值的最小值，但是当我稀疏训练迭代的次数越多，我在实验中观察到这个阈值是越来越小的，对应的剪枝率也是越来越小。当我设置的剪枝率比较大的时候，效果就很差了。