How to show confidence value on "PredictionEntry"

Answer:

return (
        <div key={label} className="prediction-entry">
            {label} {!!confidence ? (confidence*100).toFixed(1) +"%" : "0.0%"}
            {!!confidence ?
                <div
                    className={"prediction-bar" + (top ? " prediction-green" : "")}
                    style={{width: (confidence*100).toString() + "%"}} />
            : null}
        </div>
    );

Dear all,

Does anyone have the last version of MAC lobe installer before the update in July this year (2022)?

Thanks a lot in advance!

a lobe export Option to tensorflow js would be nice.

Hi, I tested this project, but I can't genarate compatible files from MS Lobe.
But I tested with an export from Google Teachable Machine and this works very well.

Steps :

• Export a project from Lobe
• Select the format "Tenserflow Saved Model"
• execute the following command to convert the export for TenserFlow js:

tensorflowjs_converter --input_format=tf_saved_model --output_format=tfjs_graph_model . ./web-model

• copy / paste the exported files in le directory public/model

Actual result :

• an error message is display on the web page
• the file metadata.json doesn't exist
• the library "@teachablemachine/image" is used in the file Prediction.js

Expected result :

• The labels who correspond to my webcam are displayed

My usage of tensorflowjs_converter is may be bad ?

I ran the web app, but it opens the camera,

with
Note
Thumbs down
Thumbs up

It does not appear that the webcam detects anything.

What is this app supposed to do?

What pictures/labels are loaded into the model?

I am trying to get more users to click pictures and then inform our model if it's right or wrong in its detection. Is there a way we can use the web-bootstrap to do that?

Hi,

i manage to start Yarn and example project working fine. after i drag the model.json, signature.json, and all the *.bin files to the public/model/ folder, it is showing as "Loading". please advise

thanks in advance
Raghavendra

No se entiende como usar el paquete botstrap web, hay lineas que no existen como "yarn start", satrt no es un comando, podrian mejorar los pasos, gracias.

Hello, after replacing the template's files in the model folder I got this error. I'm using the latest version of Lobe: 0.11.714.2. I Can't figure out what could be the issue, any idea?

Cloned and deployed the web-bootstrap app on Netifly. Works.

I then updated model, tested locally, exported, re-deployed and it does not work.
Just loads for ever.

UI appears, no errors, but just loading text in bottom left.

In console there is this message - imageClassificationModel.ts:112 Model not loaded, please await this.load() first.

URL - https://naughty-bose-d279c2.netlify.app/

Any help would be great. If i cant get this to work online, I can't use it.

Great project and lots of good ideas! I'm testing lobe within a Chrome extension but can't seem to make it work. I was wondering if you had any guideline specifically for extension with tfjs?

My code is working only up to @tensorflow/tfjs ^1.7.4 for some reason and the official Google example also uses a very old release: https://github.com/tensorflow/tfjs-examples/blob/master/chrome-extension/src/background.js. I'm using the same settings as the example file generated during the Lobe export (scalar 255, center crop, resize).

Unfortunately the predictions are wrong. They are very accurate when tested locally with Lobe but do not seem to work at all within the extension (all confidence levels seem to be the same, no matter the image). I had to replace the RVhQTElDSVQ= padding with U0FNRQ== as well (not supported in 1.7.4) - could that be the reason?