Cecilia

How to finetune the refine part if I want to cascade two model together?

2

Hello, xuebinqin, I got some tough problem when using u2net alone, which is just like the belowing, the left if pred from u2net with input resolution of 768, and the...

Any idea to deal with the following not perfect case in your showing cases?

1

Seeing from the cases you offered, it seems like the cases are not all perfect, just like the following, so does that mean the receptive filed is not big enough...

创建可以登陆的管理员用户这一步失败了。

1

python manage.py cmdb_create_superuser #这一步创建一可以登陆的管理员用户 错误如下，  但要是把mgmt.models.Permission加入到django的settings里面去的话，还是会报错， 

What you written in your README, about Supported Data Types, is that the n_features of imdb data is 1, and that of music mfcc data is 13, I wanna know...

Question about validation

3

Hello, first thanks for your pytorch version of deeplab v3+, I try it at last days of 2018, and I got a perfect model whose performance is great both on...

As you written in your paper, > In addition, we multiply the newly generated labels with the original binary image I to remove the background interference as But I see...

想请问一下为什么选择数据目录之后没有任何变化，按理说应该会弹出主页对么？

2

 经历千辛万苦终于编译完成之后选择了demo-data作为数据目录，然而并没有主页弹出，请问可能的原因是什么呢？  如题，万分感谢~

Always failed to DensifyPointCloud with some default params on openMVS_sample dataset

5

Here is my script, ```dataset=/dataset/openMVS_sample-master/images dataset_out=/dataset/openMVS_sample-master # Initialize the scene (spherical camera model) openMVG_main_SfMInit_ImageListing -i $dataset -o $dataset_out/matches -f 3.4 # Compute of the features (you can add -n to...