使用Google Cloud的Tensorflowjs Edige AutoML model.executedict中提供的dict ['ToFloat']的形状必须为[]

问题描述

准确地使用https://cloud.google.com/vision/automl/object-detection/docs/edge-quickstart将automl创建的最新模型用于tensorflowjs进行边缘处理时。

看到这个问题，从用于tensorflowjs的automl导出模型并在浏览器中使用。

跑步时 const predictions = await model.detect(img,options);

出现以下错误：

util.js:109 Uncaught (in promise) Error: The shape of dict['ToFloat'] provided in model.execute(dict) must be [],but was [1,1280,1920,3]
    at Ev (util.js:109)
    at graph_executor.js:543
    at Array.forEach (<anonymous>)
    at e.t.checkInputShapeAndType (graph_executor.js:534)
    at e.<anonymous> (graph_executor.js:332)
    at u (runtime.js:45)
    at Generator._invoke (runtime.js:274)
    at Generator.forEach.e.<computed> [as next] (runtime.js:97)
    at Um (runtime.js:728)
    at o (runtime.js:728)

使用

"@tensorflow/tfjs": "^2.6.0","@tensorflow/tfjs-automl": "^1.0.0"

完整代码

<script src="/node_modules/@tensorflow/tfjs/dist/tf.min.js"></script>
<script src="/node_modules/@tensorflow/tfjs-automl/dist/tf-automl.min.js"></script>
<img id="img" src="salad.jpg">
<script>
    async function run() {
        const model = await tf.automl.loadobjectDetection('/model/model.json');
        const img = document.getElementById('img');
        const options = { score: 0.5,IoU: 0.5,topk: 20 };
        console.log(model.dictionary);
        const predictions = await model.detect(img,options);
        console.log(predictions);
        // Show the resulting object on the page.
        const pre = document.createElement('pre');
        pre.textContent = JSON.stringify(predictions,null,2);
        document.body.append(pre);
    }
    run();
</script>

解决方法

暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！

如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。

小编邮箱:dio#foxmail.com (将#修改为@）