Zhou Botao
Zhou Botao
They are same! If we use sigmoid, BPRloss = -logσ(pos-neg) = -log(1 / (1+e^-(pos - neg))). If we use softplus, BPRloss = softplus(neg - pos) = log(1+e^(neg - pos)) =...
They are same! If we use sigmoid, BPRloss = -logσ(pos-neg) = -log(1 / (1+e^-(pos - neg))). If we use softplus, BPRloss = softplus(neg - pos) = log(1+e^(neg - pos)) =...
测试的时候建议先不添加新的测试文件,在原测试文件test_sparse_unary_op.py里进行修改。
hello,这个可以revieew一下吗~
谢谢 ------------------ 原始邮件 ------------------ 发件人: "201220014/WhaleMarket-Framework" ***@***.***>; 发送时间: 2022年2月22日(星期二) 下午3:18 ***@***.***>; ***@***.******@***.***>; 主题: Re: [201220014/WhaleMarket-Framework] 问题 (Issue #7) 视频教程:https://www.bilibili.com/video/BV1k44y1s7TS 需要的环境:Linux + GCC + Make 运行步骤: cd path # 进入项目所在工作目录 make # 构建项目 ./main #...
在model.py的 107行 `light_out = torch.mean(embs, dim=1)` 作者好像是对这三层求平均值了.
hello,when i install vision by source code,i got this error: ```bash /home/gai_test/wuyang/vision/torchvision/csrc/ops/nms.cpp:22:5: error: ‘class torch::Library’ has no member named ‘set_python_module’ 22 | m.set_python_module("torchvision._meta_registrations"); | ^~~~~~~~~~~~~~~~~ error: command '/usr/bin/gcc' failed with...