search

aws-samples / amazon-sagemaker-tensorflow-object-detection-api

Train and deploy models using TensorFlow 2 with the Object Detection API on Amazon SageMaker
MIT No Attribution
42 stars 34 forks source link

Error while making predictions ,input mismatch #17

Closed ipshita-saxena closed 2 years ago

ipshita-saxena commented 2 years ago

I have deployed tensorflow model , while doing predictions on images im getting this error

An error occurred (ModelError) when calling the InvokeEndpoint operation: Received client error (400) from primary with message "{ "error": "2 root error(s) found.\n (0) Invalid argument: ConcatOp : Dimensions of inputs should match: shape[0] = [1,20,20,256] vs. shape[1] = [1,26,26,256]\n\t [[{{node functional_1/tf_op_layer_concat_6/concat_6}}]]\n\t [[StatefulPartitionedCall/_1121]]\n (1) Invalid argument: ConcatOp : Dimensions of inputs should match: shape[0] = [1,20,20,256] vs. shape[1] = [1,26,26,256]\n\t [[{{node functional_1/tf_op_layer_concat_6/concat_6}}]]\n0 successful operations.\n0 derived errors ignored." }".

sofianhamiti commented 2 years ago

Hi @ipshita-saxena, i have updated the repo with new TF version. Can you have a try and confirm it works now?