All Questions
19 questions
0
votes
0
answers
86
views
How can I extract a specific data from a function?
I printed a variable print(detection_result) which I called from detection_result = detector.detect(input_tensor) and it printed
DetectionResult(detections=[Detection(bounding_box=BoundingBox(origin_x=...
0
votes
1
answer
2k
views
Regular tensorflow ops not supported by the interpreter error during inference
I am currently trying to convert a saved model trained using Tensorflow (v2.7.0) and Keras to a Tensorflow Lite model. The structure of the model is the following:
model_lstm = Sequential()
model_lstm....
- 11
1
vote
1
answer
3k
views
TensorFlow TypeError: 'generator' object is not callable
Edit: Possible answer at the end of the post
Hi I am trying to convert a LSTM into tflite model and I am running into
TypeError: 'generator' object is not callable
error. My code worked before with ...
- 2,177
1
vote
0
answers
400
views
'Invalid input shapes: expected 1 items got 16 items' when trying to quantize model for tflite
I was trying to quantise a TF model into a TFLite model to deploy it on my ESP32 by calling the dataset through tf.keras.preprocessing.image_dataset_from_directory() and used images_batch and ...
- 11
0
votes
2
answers
2k
views
'EndVector() takes 1 positional argument but 2 were given' while trying to quantize a tensorflow model
I was trying to quantize a TF model into a TFLite model to deploy it on my ESP32 by calling the dataset through tf.keras.preprocessing.image_dataset_from_directory() and used images_batch and ...
- 11
0
votes
1
answer
556
views
Is it possible to apply GradCam to a TF Lite model
I have been studying about GradCam and I noticed most cases are used on a Keras/Tensorflow model. However I have a tensorflow lite model that has been compiled to .tflite format. I am not sure if it's ...
user13861457
0
votes
1
answer
3k
views
Use fn_output_signature instead stop problem
My Input;
python model_main_tf2.py --model_dir=models\my_ssd_mobilenet_v2_fpnlite --pipeline_config_path=models\my_ssd_mobilenet_v2_fpnlite\pipeline.config
Output;
prnt.sc/104ecjv
My learning stopped ...
user15259511
2
votes
1
answer
369
views
Tensorflow 1.15 is not loading frozen graph, and has given me the same error for the past week
Okay, so I'm working on a large project in Google Colab, where I have to detect a certain object from all the others.
Now, for the better half of the past week, I've been working tirelessly trying to ...
- 21
0
votes
1
answer
238
views
how to get names of all detected models from existing tensorflow lite instance?
I'm looking to build a system that alerts me when there's a package at my front door. I already have a solution for detecting when there's a package (tflite), but I don't know how to get the array of ...
1
vote
2
answers
1k
views
Tensorflow - Train.py - ValueError: ('%s is not decorated with @add_arg_scope', ('nets.mobilenet.mobilenet', 'depth_multiplier'))
I'm trying to make a custom object-detection model following this tutorial: https://towardsdatascience.com/custom-object-detection-using-tensorflow-from-scratch-e61da2e10087
Everything worked fine ...
- 8,616
2
votes
1
answer
619
views
TFLite Converter: RandomStandardNormal implemented for keras model, but not for pure TensorFlow model
Task
I have two models which should be equivalent. The first one is built with keras, the second one with tensorflow. Both variational autoencoders use the tf.random.normal method in their model. ...
- 4,014
0
votes
2
answers
1k
views
Is there an equivalent of tf.lite.Interpreter.get_input_details for C++?
In TensorFlow lite's Python API, there are methods to retrieve details concerning the input and output tensors, called tf.lite.Interpreter.get_input_details and tf.lite.Interpreter.get_output_details. ...
- 4,014
31
votes
1
answer
2k
views
Description of TF Lite's Toco converter args for quantization aware training
These days I am trying to track down an error concerning the deployment of a TF model with TPU support.
I can get a model without TPU support running, but as soon as I enable quantization, I get ...
- 4,014
1
vote
0
answers
662
views
Cannot convert frozen graph to tflite model
I am trying to convert a frozen graph into a tflite model using the provided tflite_converter. I am reconstructing how I created the .pb file to make sure I did not mess up something on the way there.
...
- 4,014
1
vote
1
answer
588
views
mobilenetv2 tflite not expected output size with python3
I am running into an issue with my mobilenetV2 SSD model.
I converted it using the steps detailed here, except the fact that I use the CLI tool tflite_convert for the related step.
This works fine ...
- 457