ccl

I want Dlib to use GPU. Can I?

when I ran ./gradlew assembleDebug * Where: Build file '/home/ccl/Documents/codes/android/dlib-android/androidstudio-examples/dlib-android-app/app/build.gradle' line: 1 * What went wrong: A problem occurred evaluating project ':app'. > Could not initialize class com.android.repository.api.RepoManager ./gradlew --version...

install failed.

training loss not decrease

4

I train the landcover dataset in the image segment model you provide, but the loss does not decrease. 

How to improve performance?

10

First, thank you for sharing. I tested your pre-trained model on my Linux(GTX 1080), but my fps was about 5. Do you have some ideas to may it real-time? Really...

I want to convert the frozen graph to trt model on my x86 pc, can I install the program on x86 pc.

p.ground_truth not work for p.add_operation

3

custom functions not work in mask labels. 

如题，我用pycharm创建了一个虚拟环境，c代码怎么用这个python的虚拟环境呢？

generate_hierarchy() missing 1 required positional argument: 'method'

1

when I run generate_hierarchy(dataset='Imagenet1000', arch='fbresnet152', model=model) a error accurred. TypeError: generate_hierarchy() missing 1 required positional argument: 'method' I then tried 3 methods in hierarchy.py, all failed. 

opencv‘s dnn moudle is now support for Nvidia cuda。

1

opencv‘s dnn moudle is now support for Nvidia cuda, and needs opencv version of 4.2.0. Can you updata the opencv version and build opencv with DNN_CUDA support? Please~