All Questions
57 questions
3
votes
1
answer
144
views
Different output order in custom Object Detection model causing error in android application
I followed the steps as outlined in the following documentation: https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/training.html to train my custom object detection model. For ...
- 310
-2
votes
1
answer
73
views
Getting this error when trying to run a python file? [duplicate]
Here is the CMD of the issue I run into when I run my python script. I've installed tensorflow with pip, tried to uninstall and reinstall - unsure what else to do.
Error
- 1
0
votes
1
answer
1k
views
Tensorflow quantization process in detail - Anyone don't talk about this in detail
I am checking how the quantization process works in tensorflow lite now. However, the exact process is not explained anywhere. (They are just explaining the code for quantization using TFLite.)
When ...
0
votes
0
answers
1k
views
WARNING:absl:Found untraced functions such as _jit_compiled_convolution_op while saving in tensorflow
i just trained a cnn with 99% accuracy on the mnist dataset. my model is working fine and giving accurate results. but when i converted my h5 model to a tflite model, im getting only one result at ...
- 903
1
vote
0
answers
328
views
Why can't I save my model with tensorflow lite?
Once the training is finished, what I need is to save and convert the model to later export it, but I get the following error:
converter = tf.lite.TFLiteConverter.from_keras_model_file('models/modelo....
- 184
0
votes
1
answer
176
views
Predict with tensorflow lite input_data from CountVectorizer: ValueError: Cannot set tensor: Got value of type STRING but expected type FLOAT32
I saved a Keras CNN with TFLiteConverter and also the CountVectorizer (scikit-learn) that was used during training of the same model using pickle.
When I load both and try to predict the result of a ...
- 549
0
votes
1
answer
448
views
How to do tf.reshape with shape dynamiclly?
i am working on tensorflow 2.x. I want to accept an Integer as one of the Multi-Inputs, and in some stage of the model, i need to do tf.reshape with shape set by the Integer of Input. It is more like:
...
- 11
1
vote
1
answer
2k
views
TensorFlow convert from .pb to .tflite failes due to ops error
Hey everyone this is my first question post. If I do something wrong or u need more information please just tell me I will try to give my best.
I tried to create a object detection for TensorFlow lite....
- 31
1
vote
1
answer
1k
views
Cannot set tensor: Dimension mismatch. Got 3 but expected 4 for input 0
This is probably going to be a stupid question but I am new to deep learning and TensorFlow.
Here I have converted my deep learning model to TF-lite, after that when I am trying to do the inference ...
0
votes
1
answer
36
views
Tensor flow directory syntax
I try to execute the code in google collab to quantize my tensor flow model in my PC
In the code:
import tensorflow as tf
converter = tf.lite.TFLiteConverter.from_saved_model(D:\FYP\tflite floating ...
- 19
2
votes
2
answers
849
views
Tensorflow Lite, Image size is zero error
Actually, my question is very simple. I would like to use my own data in tensorflow lite model. So, i wrote these line of codes:
root_path = r"C:\Users\90531\Desktop\dataset\b"
image_path = ...
- 345
1
vote
1
answer
566
views
TFLite model accuracy worse on Android
I have a custom speech recognition model which, converted to TFLite, performs excellent in python on PC. When running inference with same TFLite model on Android, accuracy drops. All the processing is ...
1
vote
1
answer
919
views
How to combine data preprocessing code within tflite model (Integrate data preprocessing code within tflite)
I am having a SAVED_MODEL_PATH that contains assets, variables and saved_model.pb
SAVED_MODEL_PATH
assets
variables
saved_model.pb
I can convert this into tflite model using the below code (Main ...
- 959
2
votes
2
answers
2k
views
Int8 quantization of a LSTM model. No matter which version, I run into issues
I want to use a generator to quantize a LSTM model.
Questions
I start with the question as this is quite a long post.
I actually want to know if you have manged to quantize (int8) a LSTM model with ...
- 2,177
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