SaschaDittmann / tfjs-cv-objectdetection

TensorFlow.js Example: Using an Azure Custom Vision Object Detection model to detect Logos in a web browser
MIT License
14 stars 6 forks source link

ellipsis mask is not yet supported #11

Open krushal-kyada opened 3 years ago

krushal-kyada commented 3 years ago

Hello

The model provided by you in this repo is not getting loaded. Please refer to the below error which I got in the console.

Uncaught Error: Based on the provided shape, [3,3,3,16], the tensor should have 432 values but has 363

So i was testing with my model, the loading was successful. But when I hit predict button i am getting following error.

Uncaught (in promise) Error: ellipsis mask is not yet supported
    stridedSlice_ strided_slice.js:67
    a operation.js:45
    r slice_join_executor.js:87
    r operation_executor.js:88
    tidy engine.js:425
    scopedRun engine.js:436
    tidy engine.js:423
    Nb globals.js:182
    r operation_executor.js:87
    fO operation_executor.js:108
    h graph_executor.js:362
    processStack graph_executor.js:348
    t graph_executor.js:310
    u runtime.js:45
    _invoke runtime.js:274
    e runtime.js:97
    Wm runtime.js:728
    o runtime.js:728
    Vm runtime.js:728
    Vm runtime.js:728
    executeWithControlFlow graph_executor.js:338
    t graph_executor.js:258
    u runtime.js:45
    _invoke runtime.js:274
    e runtime.js:97
    Wm runtime.js:728
    o runtime.js:728
    Vm runtime.js:728
    Vm runtime.js:728
    executeAsync graph_executor.js:275
    t graph_model.js:311
    u runtime.js:45
    _invoke runtime.js:274
    e runtime.js:97
    Wm runtime.js:728
    o runtime.js:728
    Vm runtime.js:728
    Vm runtime.js:728
    executeAsync graph_model.js:312
    predictLogos predict.js:69
strided_slice.js:67:10

I am new to using JS, Can you help me fixing the issue.

Thanks Krushal Kyada