-
Hi Fangda,
Thanks for the great work!
I have some questions about the unsupervised image-to-image translation baselines, namely CycleGAN and CUT, reported in the paper (Table 1). I was wondering…
-
Hi,
I tried to train a dsvt-pillar model using the kitti dataset, below is my config:
CLASS_NAMES: ['Car', 'Pedestrian', 'Cyclist']
DATA_CONFIG:
_BASE_CONFIG_: cfgs/dataset_…
-
执行：
cmake -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local -D BUILD_opencv_python2=OFF -D BUILD_opencv_python3=ON -D PYTHON3_EXCUTABLE=/usr/bin/python -D PYTHON3_INCL…
-
### 一、BackGround 📚
飞桨新IR（PIR）功能建设已经基本完成，当前CI流水线上静态图依然是以飞桨旧IR运行，我们想将CI默认运行的IR切换至PIR，从而能顺利支持未来飞桨基于PIR下的代码提交与验证。但是当前依然有很多单测在PIR模式下的运行会存在问题，修复这些问题成为实现默认切换PIR的必要条件。
### 二、Task Introduction📚
对于存在问题的单测，我们已统一…
-
微博内容精选
-
Hello;
Is there any way to train the models without coco_train_script.py and just using model.fit? I made a custom model for object detection that uses head and anchorfree loss function of keras_c…
-
**Introduction**
I recently updated the OS on my Mac to Big Sur (11.6.3), and then noticed the image preview on the darkroom is broken when OpenCL support is activated.
**Describe the bug/issue**
…
-
**Avogadro version: (please complete the following information from the About box):**
- Avogadrolibs: 1.96.0 as by the AppImage for Linux by July 21
- Qt: 5.12.12
**Desktop version: (please com…
-
Package: pcl[apps,core,opengl,openni2,qt,visualization,vtk]:x64-windows-my@1.14.0#2
**Host Environment**
- Host: x64-windows
- Compiler: MSVC 19.39.33523.0
- vcpkg-tool version: 2024-03-14-7d3…
-
optimize color is taking too much time. it took me 1 hr time for 5 second video (~100 frames) on a 6GB GPU
I am planning to use the tracker for the INSTA repo. To generate for 1000 frames, it will …