V2EX = way to explore
V2EX 是一个关于分享和探索的地方
Sign Up Now
For Existing Member  Sign In
waitfor

Tensorflow 1.x 版本如何对 Tensorflow hub 的模型进行微调?

  •  
  •   waitfor · Feb 4, 2021 · 4084 views
    This topic created in 1919 days ago, the information mentioned may be changed or developed.

    我看了官方的文档,就几行代码,有没有一个全的代码呀。。 官方的代码全是 TF2 keras 的,难受! 急急急! https://hub.tensorflow.google.cn/google/imagenet/resnet_v2_50/classification/3以这个为例,就只有几行代码,

    module = hub.Module("https://hub.tensorflow.google.cn/google/imagenet/resnet_v2_50/classification/3",
                        trainable=True, tags={"train"})
    logits = module(inputs=dict(images=images, batch_norm_momentum=0.997),
                    signature="image_classification_with_bn_hparams")
    

    到底如何微调?

    No Comments Yet
    About   ·   Help   ·   Advertise   ·   Blog   ·   API   ·   FAQ   ·   Solana   ·   3314 Online   Highest 6679   ·     Select Language
    创意工作者们的社区
    World is powered by solitude
    VERSION: 3.9.8.5 · 29ms · UTC 12:54 · PVG 20:54 · LAX 05:54 · JFK 08:54
    ♥ Do have faith in what you're doing.