Pytorch LSTM in ONNX.js - Uncaught (in promise) Error: unrecognized input '' for node: LSTM_4

Question

我正在尝试运行浏览器中的 Pytorch LSTM 网络。但我收到此错误：

graph.ts:313 Uncaught (in promise) Error: unrecognized input '' for node: LSTM_4
    at t.buildGraph (graph.ts:313)
    at new t (graph.ts:139)
    at Object.from (graph.ts:77)
    at t.load (model.ts:25)
    at session.ts:85
    at t.event (instrument.ts:294)
    at e.initialize (session.ts:81)
    at e.<anonymous> (session.ts:63)
    at onnx.min.js:14
    at Object.next (onnx.min.js:14)

我该如何解决这个问题？这是我将模型保存到 onnx 的代码：

net = torch.load('trained_model/trained_model.pt')
net.eval()

with torch.no_grad():
    input = torch.tensor([[1,2,3,4,5,6,7,8,9]])
    h0, c0 = net.init_hidden(1)
    output, (hn, cn) = net.forward(input, (h0,c0))


    torch.onnx.export(net, (input, (h0, c0)), 'trained_model/trained_model.onnx',
                    input_names=['input', 'h0', 'c0'],
                    output_names=['output', 'hn', 'cn'],
                    dynamic_axes={'input': {0: 'sequence'}})

我将输入作为唯一的动态轴，因为它是唯一可以改变大小的轴。使用此代码，模型可以正确保存为 trained_model.onnx。它确实给了我一个警告：

UserWarning: Exporting a model to ONNX with a batch_size other than 1, with a variable length with LSTM can cause an error when running the ONNX model with a different batch size. Make sure to save the model with a batch size of 1, or define the initial states (h0/c0) as inputs of the model. 
  warnings.warn("Exporting a model to ONNX with a batch_size other than 1, "

这个警告有点混乱，因为我用 batch_size 1:

导出它

输入的形状为 torch.Size([1, 9])
h0 的形状为 torch.Size([2, 1, 256]) - 对应于 (num_lstm_layers, batch_size, hidden_dim)
c0 也有形状 torch.Size([2, 1, 256])

但由于我确实将 h0/c0 定义为模型的输入，所以我认为这与问题无关。

这是我在浏览器中用于运行ning 的 javascript 代码：

<script src="https://cdn.jsdelivr.net/npm/onnxjs/dist/onnx.min.js"></script>
<!-- Code that consume ONNX.js -->
<script>
  // create a session
  const myOnnxSession = new onnx.InferenceSession();

  console.log('trying to load the model')

  // load the ONNX model file
  myOnnxSession.loadModel("./trained_model.onnx").then(() => {

    console.log('successfully loaded model!')

    // after this I generate input and run the model
    // since my code fails before this it isn't relevant
  });
</script>

根据 console.log 语句，无法加载到模型。我应该如何解决这个问题？如果相关，我正在使用 Python 3.8.5、Pytorch 1.6.0、ONNX 1.8.0。

Answer 1

对于将来遇到此问题的任何人，我相信我会收到此错误，因为即使 ONNX 支持 Pytorch LSTM 网络，ONNX.js 还不支持它。

为了解决这个问题，我可能会在浏览器中使用一个名为 streamlit.

的简单 Web 应用程序框架，而不是运行

Pytorch LSTM in ONNX.js - Uncaught (in promise) Error: unrecognized input '' for node: LSTM_4

Pytorch LSTM in ONNX.js - Uncaught (in promise) Error: unrecognized input '' for node: LSTM_4

javascript

python

lstm

pytorch