FengMu1995
FengMu1995
I want to finetune the arcface with the ms1mv3, but I have only one gpu. How to load all weight into softmax layer from rank_0_softmax_weight.pt to rank_7_softmax_weight.pt ?
I wonder why the backbone was trained with only one dataset every time. Why can't the backbone be trained with multiple dataset. As you upload "ResNet50@WebFace600K" Looking forward to your...
**Describe the bug** I convert my onnx to tf saved model by onnx-tensorflow. When I tested by onnx_tf, it runs successfully: _# onnx_model = onnx.load("./rvm_144*256.onnx") # load onnx model #...
why the Y channel of YCbCr was the only input into model?
Hi, How wonderful is your work! I have a question ''How much is the cpu's memory overhead when data loading?" Only 15G I have, But it shows this is not...
which dataset was used to train the pretrained model" IR-SE50" ?
我的理解是cpu会把数据传到npu,执行每一层算子. cpu刚开始就会生成整个npu的计算图,在算子执行前后不需要cpu参与计算吗
1. Ground-truth images of the datasets applied to train realesr-general-x4v3&realesr-general-wdn-x4v3 are the sharped ground-truth images as Real-ESRGAN+ in paper? 2. What are the datasets applied to train realesr-general-x4v3&realesr-general-wdn-x4v3? 3. which...
The log is as follows: /home/XXX/Software/gcc-sigmastar-9.1.0-2019.11-x86_64_arm-linux-gnueabihf/bin/../lib/gcc/arm-linux-gnueabihf/9.1.0/../../../../arm-linux-gnueabihf/bin/ld: cannot find -ldbus-1 collect2: error: ld returned 1 exit status Makefile:761: recipe for target 'libzbar.la' failed make[2]: *** [libzbar.la] Error 1 make[2]: Leaving directory...