Tensorflow object detection API by default has output tensor names num_detections , detection_boxes, detection_scores and detection_classes . How can I change these default names ? Unfortunately an inference platform that I am testing does not accept tensor names with underscores. Thank you ..
How can I change the default output, input tensor names in tensorflow object detection API?
511 views Asked by Shaaa At
1
There are 1 answers
Related Questions in PYTHON
- How to store a date/time in sqlite (or something similar to a date)
- Instagrapi recently showing HTTPError and UnknownError
- How to Retrieve Data from an MySQL Database and Display it in a GUI?
- How to create a regular expression to partition a string that terminates in either ": 45" or ",", without the ": "
- Python Geopandas unable to convert latitude longitude to points
- Influence of Unused FFN on Model Accuracy in PyTorch
- Seeking Python Libraries for Removing Extraneous Characters and Spaces in Text
- Writes to child subprocess.Popen.stdin don't work from within process group?
- Conda has two different python binarys (python and python3) with the same version for a single environment. Why?
- Problem with add new attribute in table with BOTO3 on python
- Can't install packages in python conda environment
- Setting diagonal of a matrix to zero
- List of numbers converted to list of strings to iterate over it. But receiving TypeError messages
- Basic Python Question: Shortening If Statements
- Python and regex, can't understand why some words are left out of the match
Related Questions in TENSORFLOW
- A deterministic GPU implementation of fused batch-norm backprop, when training is disabled, is not currently available
- Keras similarity calculation. Enumerating distance between two tensors, which indicates as lists
- Does tensorflow have a way of calculating input importance for simple neural networks
- How to predict input parameters from target parameter in a machine learning model?
- Windows 10 TensorFlow cannot detect Nvidia GPU
- unable to use ignore_class in SparseCategoricalCrossentropy
- Why is this code not working? I've tried everything and everything seems to be fine, but no
- Why convert jpeg into tfrecords?
- ValueError: The shape of the target variable and the shape of the target value in `variable.assign(value)` must match
- The kernel appears to have died. It will restart automatically. whenever i try to run the plt.imshow() and plt.show() function in jupyter notebook
- Pneumonia detection, using transfer learning
- Cannot install tensorflow ver 2.3.0 (distribution not found)
- AttributeError: module 'keras._tf_keras.keras.layers' has no attribute 'experimental'
- Error while loading .keras model: Layer node index out of bounds
- prediction model with python tensorflow and keras, gives error when predicting
Related Questions in OBJECT-DETECTION-API
- unable to import model model_main (from object_detection import model_main)
- Tensorflow Object Detection API - FasterCNN - Able to use normalised floats array stored in tfrecord
- improve Tensorflow.support.task to be able object tracking
- Options to reduce size of trained model protobuf file from TF object detection API
- ImportError: cannot import name 'model_lib_v2' from 'object_detection' (already installed an still not working)
- KeyError: 1720: Python
- No module named 'tensorflow.python.keras.layers.preprocessing'
- Object Detection API, TensorFlow and Keras compatibility issue
- raise core._status_to_exception(e) from None tensorflow.python.framework.errors_impl.InvalidArgumentError:
- TFLite converter not replacing dummy_function with TFLite_Detection_PostProcess
- Problems trying to train a custom object detection model using Tensorflow2 and Google Colab
- image = control_flow_ops.case( AttributeError: module 'tensorflow.python.ops.control_flow_ops' has no attribute 'case'
- Training modern object detection with Tensorflow
- Google MLkit object Detection Bounding Boxes with Image Classification Model
- Installing Tensorflow Model Garden error " Getting requirements to build wheel did not run successfully." How to resolve this?
Related Questions in TENSORFLOW-MODEL-GARDEN
- GradCAM for MoViNet
- why importing tensorflow_models interrupt matplotlib in colab?
- How to acces models from tf-models-official? (Module Not Found tensorflow_models)
- TFLite converter not replacing dummy_function with TFLite_Detection_PostProcess
- Tensorflow Model Garden Tutorial with different models
- Tensorflow Model Garden always outputs validation loss equals zero for Instance / Semantic Segmentation
- Installing Tensorflow Model Garden error " Getting requirements to build wheel did not run successfully." How to resolve this?
- Tensorflow saved_model loading issue in version 2.7
- Using tensorboard profiler with orbit controller?
- Measuring Top-1 and Top-5 Accuracy using TensorFlow Model Garden
- Is it possible to install tf-models-official for Mask RCNN with Python 3.10 and tf 2.9.3?
- How can i use Tensorflows official models from the TF Model Garden?
- how can i run the lstm_objection_detection code to train?
- how to use mobilenetV3 small to train my custom dataset for object detection?
- BERT pre-training - masked_lm_accuracy is always zero
Popular Questions
- How do I undo the most recent local commits in Git?
- How can I remove a specific item from an array in JavaScript?
- How do I delete a Git branch locally and remotely?
- Find all files containing a specific text (string) on Linux?
- How do I revert a Git repository to a previous commit?
- How do I create an HTML button that acts like a link?
- How do I check out a remote Git branch?
- How do I force "git pull" to overwrite local files?
- How do I list all files of a directory?
- How to check whether a string contains a substring in JavaScript?
- How do I redirect to another webpage?
- How can I iterate over rows in a Pandas DataFrame?
- How do I convert a String to an int in Java?
- Does Python have a string 'contains' substring method?
- How do I check if a string contains a specific word?
Trending Questions
- UIImageView Frame Doesn't Reflect Constraints
- Is it possible to use adb commands to click on a view by finding its ID?
- How to create a new web character symbol recognizable by html/javascript?
- Why isn't my CSS3 animation smooth in Google Chrome (but very smooth on other browsers)?
- Heap Gives Page Fault
- Connect ffmpeg to Visual Studio 2008
- Both Object- and ValueAnimator jumps when Duration is set above API LvL 24
- How to avoid default initialization of objects in std::vector?
- second argument of the command line arguments in a format other than char** argv or char* argv[]
- How to improve efficiency of algorithm which generates next lexicographic permutation?
- Navigating to the another actvity app getting crash in android
- How to read the particular message format in android and store in sqlite database?
- Resetting inventory status after order is cancelled
- Efficiently compute powers of X in SSE/AVX
- Insert into an external database using ajax and php : POST 500 (Internal Server Error)
The output tensor names are defined in the "meta_architectures" python files in the object detection project which can be found here. You could try to adjust/convert the naming of the output tensors there for when you are doing the model export for inference but I haven't tried this myself.