python - 将稳定基线 tensorflow 模型转换为 tensorflow js

Question

我正在尝试从 stable-baselines 转换底层 tensorflow 模型至 tensorflowjs能够在浏览器上使用该模型。但我无法进行转换

我关注了this github issue使用代码创建必要的 tensorflow 文件:

def generate_checkpoint_from_model(model, checkpoint_name):  
        tf.saved_model.simple_save(model.sess, checkpoint_name, inputs={"obs": model.act_model.obs_ph}, outputs={"action": model.action_ph})

然后我尝试使用 tensorflowjs_converter 转换模型

tensorflowjs_converter --input_format=tf_saved_model test/ web_test

但是，它给了我以下错误:

Unable to lift tensor <tf.Tensor 'loss/action_ph:0' shape=(?,) dtype=int32> because it depends transitively on placeholder <tf.Operation 'loss/action_ph' type=Placeholder> via at least one path, e.g.: loss/action_ph (Placeholder)

我创建了以下colab notebook出现错误，您可以尝试一下。

有人知道如何进行此转换吗？

感谢您的帮助

Answer 1

我将问题发布为 issue in stable-baselines他们回答了。我将复制这里作为其他人的引用:

You are trying to save the action placeholder used in PPO training (part of PPO agent), but for inference you only need the trained policy and its placeholders (model.act_model). The code on colab runs without errors by changing call to simple_save to this:

tf.saved_model.simple_save(model.sess, checkpoint_name,
inputs={"obs": model.act_model.obs_ph}, outputs={"action": model.act_model._policy_proba})

The value of _policy_proba depends on the environment/algorithm.