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 https://github.com/tensorflow/tensorflow/issues/38260/#issuecomment-881928290

[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[bot]]

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.

[playground]

Any update?

[lucky0604]

Any update? I meet the same issue, but the different thing is when I use tf.browser.fromPixels(imgPath), I got the shape 3(it's a JPG file), not 4(as the doc says it should be 4). the img path is an image URL that stores in the cloud. The same thing is that when I use the model.execute or model.predict, I got the Uncaught (in promise) Error: The shape of dict['input_tensor'] provided in model.execute(dict) must be [1,-1,-1,3], but was [711,474,3] error.

[gaikwadrahul8]

Hi, @playground

Apologize for the delayed response and we're re-visiting our older issues and checking whether those issues got resolved or not as of now so May I know are you still looking for the solution or your issue got resolved ?

If issue still persists after trying with latest version of TFJs please let us know with error log and code snippet to replicate the same issue from our end ?

Could you please confirm if this issue is resolved for you ? Please feel free to close the issue if it is resolved ? Thank you!

[google-ml-butler[bot]]

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.

[playground]

Yes, this issue still exists, please keep this open until it's resolved.

[gaikwadrahul8]

Hi, @playground

Apologize for the delayed response and I was trying to replicate the same issue from my end and I'm getting below error and I have added error log below so Could you please help me with the steps to replicate the same issue from my end ?

I have tried your code snippet from here and also I used the same model from your Github repo which you converted with the help of TFJs convertor so may be I'm doing something wrong here to replicate the same issue from my end. Thank you!

gaikwadrahul-macbookpro:TFJS gaikwadrahul$ node index.js
/Users/gaikwadrahul/Desktop/TFJS/node_modules/@tensorflow/tfjs-core/dist/tf-core.node.js:25608
                        throw new Error(message);
                              ^

Error: Failed to parse model JSON of response from https://github.com/playground/tfjs-object-detection/blob/main/model-json-service/model/model.json. Please make sure the server is serving valid JSON for this request.
    at HTTPRequest.<anonymous> (/Users/gaikwadrahul/Desktop/TFJS/node_modules/@tensorflow/tfjs-core/dist/tf-core.node.js:25608:31)
    at step (/Users/gaikwadrahul/Desktop/TFJS/node_modules/@tensorflow/tfjs-core/dist/tf-core.node.js:138:27)
    at Object.throw (/Users/gaikwadrahul/Desktop/TFJS/node_modules/@tensorflow/tfjs-core/dist/tf-core.node.js:87:53)
    at rejected (/Users/gaikwadrahul/Desktop/TFJS/node_modules/@tensorflow/tfjs-core/dist/tf-core.node.js:74:36)
    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)

Node.js v18.15.0
gaikwadrahul-macbookpro:TFJS gaikwadrahul$ 

[pyu10055]

@gaikwadrahul8 I think you need to try the raw link of the model https://raw.githubusercontent.com/playground/tfjs-object-detection/main/model-json-service/model/model.json

[github-actions[bot]]

This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.

[github-actions[bot]]

This issue was closed due to lack of activity after being marked stale for past 7 days.

[google-ml-butler[bot]]

Are you satisfied with the resolution of your issue? Yes No

[gaikwadrahul8]

Hi, @playground

I'm really sorry due to google-ml-butler bot this issue got closed so now I have re-opened this issue, we'll update you about this issue soon. Thank you!

[gaikwadrahul8]

Hi, @playground

Apologize for the delayed response and I tried to replicate the same issue from my end and it's giving similar error message so we'll have to dig more into this issue and will update you soon, thank you for noticing this issue I really appreciate your efforts and time. Thank you!

CC :@mattsoulanille

Here is error log output for your reference, I tried with .predict(), .execute() and .executeAsync() :

gaikwadrahul-macbookpro:test-5366 gaikwadrahul$ node index.js
/Users/gaikwadrahul/Desktop/TFJS/test-5366/node_modules/@tensorflow/tfjs-core/dist/tf-core.node.js:454
        throw new Error(typeof msg === 'string' ? msg : msg());
              ^

Error: The shape of dict['input_tensor'] provided in model.execute(dict) must be [1,-1,-1,3], but was [400,600,3]
    at Object.assert (/Users/gaikwadrahul/Desktop/TFJS/test-5366/node_modules/@tensorflow/tfjs-core/dist/tf-core.node.js:454:15)
    at /Users/gaikwadrahul/Desktop/TFJS/test-5366/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:31349:26
    at Array.forEach (<anonymous>)
    at GraphExecutor.checkInputShapeAndType (/Users/gaikwadrahul/Desktop/TFJS/test-5366/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:31341:29)
    at GraphExecutor.execute (/Users/gaikwadrahul/Desktop/TFJS/test-5366/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:30855:14)
    at GraphModel.execute (/Users/gaikwadrahul/Desktop/TFJS/test-5366/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:31913:36)
    at GraphModel.predict (/Users/gaikwadrahul/Desktop/TFJS/test-5366/node_modules/@tensorflow/tfjs-converter/dist/tf-converter.node.js:31758:34)
    at file:///Users/gaikwadrahul/Desktop/TFJS/test-5366/index.js:9:33
    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)

Node.js v18.15.0
gaikwadrahul-macbookpro:test-5366 gaikwadrahul$ 

[playground]

Thanks @gaikwadrahul8 , I look forward to your update. I also have this issue sitting out there for sometime https://github.com/tensorflow/tfjs/issues/7398#issuecomment-1503170942, can you please provide an update there too?