Error: The shape of dict[‘input_tensor’] provided in model.execute(dict) must be [1,-1,-1,3]

[playground]

Please make sure that this is a bug. As per our
GitHub Policy,
we only address code/doc bugs, performance issues, feature requests and
build/installation issues on GitHub. tag:bug_template

System information
MacOS Big Sur
Node v15.7.0
NPM 7.20.0

I'm running @tensorflow/tfjs-node v 3.7.0

I attempted to convert my saved model to friendly model json using tensorflowjs_converter

    tensorflowjs_converter \                            
    --input_format=tf_saved_model \   
    --output_format=tfjs_graph_model \    
    --saved_model_tags=serve \
    --signature_name=serving_default \
    /saved_model \
   /json-model

When run model.predict(), it's throwing these errors

Error: The shape of dict['input_tensor'] provided in model.execute(dict) must be [1,-1,-1,3], but was [1,600,800,4]
    at Object.assert (/object-detection/node_modules/@tensorflow/tfjs-core/dist/tf-core.node.js:337:15)
    at /object-detection/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:7478:28
    at Array.forEach (<anonymous>)
    at GraphExecutor.checkInputShapeAndType (/object-detection/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:7470:29)
    at GraphExecutor.<anonymous> (/object-detection/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:7272:34)
    at step (/object-detection/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:81:23)
    at Object.next (/object-detection/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:62:53)
    at /object-detection/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:55:71
    at new Promise (<anonymous>)
    at __awaiter (/object-detection/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:51:12) 

I have also tried model.executeAsync() instead of model.predict(), executeAsync()
NOTE: When use with SavedModel(without the conversion) it works for both image types

for jpg image

Image: 1440000 bytes with shape: Tensor {
  kept: false,
  isDisposedInternal: false,
  shape: [ 1, 600, 800, 3 ],
  dtype: 'int32',
  size: 1440000,
  strides: [ 1440000, 2400, 3 ],
  dataId: {},
  id: 918,
  rankType: '4',
  scopeId: 2
}

Error: Invalid TF_Status: 3
Message: In[0] and In[1] has different ndims: [1,8,8,64,2] vs. [2,1]

for png image

Error: The shape of dict['input_tensor'] provided in model.execute(dict) must be [1,-1,-1,3], but was [1,600,800,4]

If I add ----control_flow_v2=True to do the conversion, it will fail to loadGraphModel.

I'm running @tensorflow/tfjs-node v 3.7.0 and I'm still getting this error "Cannot read property 'outputs' of undefined" when tried to load model json that was converted from saved model using tensorflowjs_converter.
When I changed to @tensorflow/tfjs-node@next, it would throw "Cannot read property 'children' of undefined"

model = await tf.loadGraphModel(modelPath);

2021-07-10 13:26:00.618147: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.

TypeError: Cannot read property 'outputs' of undefined
at /object-detection/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:3851:31
at Array.forEach ()
at /object-detection/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:3848:29
at Array.forEach ()
at OperationMapper.mapFunction (/object-detection/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:3846:18)
at /object-detection/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:3679:56
at Array.reduce ()
at OperationMapper.transformGraph (/object-detection/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:3678:48)
at GraphModel.loadSync (/object-detection/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:7763:68)
at GraphModel. (/object-detection/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:7737:52)

[rthadur]

Can you try to reshape like this tensor = tensor.reshape([1, 224, 224, 3]); before you call predict ?

[playground]

Yes I did that too, that didn't help.

[playground]

Also with tfjs-node v3.8.0 seems to have broken the functionality for loadSavedModel() for MacOS. Looks like a regression bug, I have posted that here tensorflow/tensorflow#38260

[rthadur]

In order to expedite the trouble-shooting process, please provide a code pen example or sample code to reproduce the issue. Thanks!

[playground]

Basically this is what I did
tfnode.loadGraphModel(modelUrl);
const image = fs.readFileSync(imageFile);
let decodedImage = tfnode.node.decodeImage(image);

tried both predict and executeAsync

I can share the converted model.json if that will help.

[rthadur]

sure, if possible a working codepen example or a git repo. Thank you

[playground]

Here is the converted model.json https://github.com/playground/tfjs-object-detection/tree/main/model-json-service/model

[playground]

@rthadur v3.8.0 seems to have broken for Mac for loadSavedModel, model.predict() is throwing this error

Error: Session fail to run with error: Cannot parse tensor from proto: dtype: DT_VARIANT
tensor_shape {
}
variant_val {
  type_name: "tensorflow::TensorList"
  metadata: "\001\000\001\377\377\377\377\377\377\377\377\377\001\030\001"
}

         [[{{node StatefulPartitionedCall/StatefulPartitionedCall/map/TensorArrayV2_1/_9__cf__9}}]]

[google-ml-butler]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you.