1,112 questions
0
votes
1
answer
295
views
Limelight Detector Notebook suddenly not working. Any ideas?
I've been trying to train a custom detector model for a LimeLight3A through the Google Colab notebook they provided. I successfully trained one on April 4th, but since then any of my attempts at ...
0
votes
0
answers
95
views
Implementing class activation maps for models in Tensorflow Object Detection API
I need to implement CAM for a model trained on the base model ssd_mobilenet_v2_320x320_coco17_tpu-8 in the pre-trained Object Detection Zoo.
How could I accesses the layers and other fields necessary ...
0
votes
0
answers
4k
views
ImportError: cannot import name 'runtime_version' from 'google.protobuf' in TensorFlow Object Detection API
I'm encountering an ImportError when trying to run the TensorFlow Object Detection API's test script. The error message is:
(tfod) dev@dev:/media/dev/96E0A5D3E0A5BA3F/tfod/models/research$ python ...
1
vote
0
answers
55
views
Dimension Error in MobileNet SSD object detection
I am trying to implement an object detection algorithm using ssd_mobilenet_v2_fpnlite_320x320 using Tensorflow Object Detection API. My input image is of size 1024x33. But when I run the training ...
-1
votes
1
answer
131
views
Tensorflow Object Detection API installation issues
I am trying to install tensorflow object detection API using this link in my Ubuntu PC.
My goal is to use MobileNet SSD for object detection.
My tensorflow version is 2.13.1. I was able to install the ...
0
votes
0
answers
72
views
python model_builder_tf2_test.py generates errors
I am trying to use the Tensorflow object detection API to create my own model, so I created a virtudal enviorement,installed tensorflow 2.16.1, and I am using python 3.12.3. I installed Slim as well, ...
0
votes
0
answers
30
views
tensorflow_object_detection_api installation incomplete?
I need to import DetectorAPI from tensorflow_object_detection_API. But there seems to be an installation problem.
I get the no module found error, even though i just installed it.
I installed it using ...
0
votes
0
answers
36
views
Tensorflow : TypeError: create_estimator_and_inputs() missing 1 required positional argument: 'hparams'
Hello everyone I am trying to train my object detection model using model_main.py from Tensorflow
But when I execute the command in the cmd : python model_main.py --alsologtostderr --model_dir=...
0
votes
0
answers
129
views
Prevent duplicate results from previous frame in object tracking
Currently, I am working on Object detection, tracking, and counting. I want to store the results whenever the vehicle crosses the line, however, I always get duplicate results.
How can I prevent these ...
0
votes
1
answer
54
views
unable to import model model_main (from object_detection import model_main)
I'm trying to import the package model_main from object_detection but it Is throwing an error like
Traceback (most recent call last): File "../LearningSpace/ObJTEST01/main.py", line 9, in &...
0
votes
0
answers
22
views
Tensorflow Object Detection API - FasterCNN - Able to use normalised floats array stored in tfrecord
When using TensorFlow Object Detection API, and FasterCNN model from the Detection Zoo, are you able to store a normalised 2D array (0-1) as floats into a tfrecord and use this as model inputs?
I am ...
0
votes
1
answer
156
views
ImportError: cannot import name 'model_lib_v2' from 'object_detection' (already installed an still not working)
**Hey guys, currently doing tensorflow object detection and stuck because of an error. Already tried all the method in the internet, still not working.
**
I use tensorflow == 2.10.0, the model is http:...
0
votes
0
answers
62
views
KeyError: 1720: Python
I'm following this tutorial on how to export my saved model to tflite for building an android app using my custom detection model Link
But after executing this code
ObjectDetectorWriter = ...
1
vote
0
answers
156
views
Object Detection API, TensorFlow and Keras compatibility issue
I'm trying to follow this tutorial and I'm running into issue setting up the environment.
https://towardsdatascience.com/borderless-tables-detection-with-deep-learning-and-opencv-ebf568580fe2
The ...
0
votes
1
answer
595
views
raise core._status_to_exception(e) from None tensorflow.python.framework.errors_impl.InvalidArgumentError:
Trying to train an object detection model on the Citypersons dataset following this tutorial.
https://neptune.ai/blog/how-to-train-your-own-object-detector-using-tensorflow-object-detection-api
I run ...
0
votes
1
answer
138
views
TFLite converter not replacing dummy_function with TFLite_Detection_PostProcess
I want to implement a tf.Module for decoding box predictions and applying NonMaxSuppression that is convertible to tflite.
This implementation includes elements from here.
It also follows this guide ...
0
votes
1
answer
388
views
Training modern object detection with Tensorflow
The Tensorflow object detection API is deprecated, and refers to Tensorflow-vision. Unfortunately, the documentation, as far as I can see, is just links to a series of preprints. All the other ...
1
vote
1
answer
188
views
Google MLkit object Detection Bounding Boxes with Image Classification Model
So ive developed an application using google MlKit and its object detection api. One thing I noticed that the tflite image classification model that im using, ( TFLite (efficientnet/lite3/int8) ) only ...
1
vote
0
answers
72
views
Tensorflow 2.0 - Training model issues
I am currently learning how to train a model object detection using google colab and tensorflow 2.0 based on this website link Link
During training the model process we received this output in the ...
0
votes
1
answer
387
views
Object Detection API installation
I am trying to setup tensorflow object detection, and I'm following this video.The video refers to this website.
I have successfully cloned Tensorflow Garden and Coco API
I have also successfully ...
0
votes
1
answer
127
views
Problem detecting large number of objects with Tensorflow object detection API
When i try to detect large amount of objects (more than 100 on single image) with tensorflow object detection API and model efficientdet d0, it detects them mostly well, but completely ignores some of ...
1
vote
0
answers
63
views
object detection api is not working with colab
!apt-get install protobuf-compiler
!cd Tensorflow/models/research && protoc object_detection/protos/*.proto --python_out=. && cp object_detection/packages/tf2/setup.py . && ...
1
vote
1
answer
220
views
Tensorflow Object Detection API Installation Verification Issues: "No module named 'official.legacy'"
I was installing the Object Detection API for a personal project, I did all the steps mentioned in the official documentation from installing the COCO API to installing the Object Detection API.
In ...
0
votes
1
answer
333
views
Error with pre-trained Mask R-CNN Inception ResNet V2 1024x1024 model using TensorFlow Object Detection API
I am attempting to fine-tune a pre-trained Mask R-CNN Inception ResNet V2 1024x1024 model using the TensorFlow Object Detection API for a custom task. I have downloaded the model from this location.
I ...
5
votes
0
answers
1k
views
FileNotFoundError: Op type not registered 'DisableCopyOnRead'
I've trained the EfficientDet D1 model in google collab. but, when i want to load the model in jetson nano, i'm facing this error
Traceback (most recent call last):
File "E:\software\conda2023\...
0
votes
0
answers
47
views
err obj detect TF2 model: ImportError: No module named numpy
while creating customer object detection I'm facing an issue on make cmd
~/object/models/research/cocoapi/PythonAPI$ make all
python setup.py build_ext --inplace
Traceback (most recent call last):
...
1
vote
0
answers
669
views
Training TensorFlow models
When I started training the TensorFlow models using model_main_tf2.py I got this:
TensorFlow Addons (TFA) has ended development and introduction of new features.
TFA has entered a minimal maintenance ...
0
votes
1
answer
50
views
I have -1 mAP and model detects objects as "N/A" with 100% during object detection training using tensorflow object detection API
I tried to make my own object detection model with this tutorial on Colab.
I followed this tutorial with my 2083 train and 263 test examples and training is done. And when i checked the model using ...
1
vote
1
answer
880
views
ModuleNotFoundError: tensorflow.python.keras.layers.preprocessing
Even though I have tensorflow installed in the venv at version 2.12.0 it kinda does not have tensorflow.python.keras.layers.preprocessing. I tried to install the object-detection API and I am still ...
2
votes
2
answers
3k
views
Object Detection - draw rectangle around objects using bounding box
First of all, I want to address that I know a lot of similar questions have been posted here on SO, but none of them provide an answer of explaining steps and logic behind it - just simply points to ...
0
votes
1
answer
558
views
how to load a saved_model.pb that was previously exported from Tensorflow Object Detection API
So previously I have trained a model based on the Tensorflow Models Zoo on Tensorflow Object Detection API using my own data. After that, I had exported the saved model in a pb format, just as the ...
1
vote
1
answer
199
views
Is CVAT's TFRecord export incorrect?
ML newbie here...
I've been working on an object detection model for the last half of this semester for my university's enterprise program (like a school-sponsored business, sort of). I decided to use ...
2
votes
2
answers
3k
views
Why my model training automatically stopped during training?
I was trying to make a custom detector using SSD MobileNet. I never tried this model before for making a custom detector using TensorFlow API. I was following this tutorial. I am facing a problem ...
1
vote
0
answers
191
views
StatefulPartitionedCall Tensorflow 2 layer
I've trained the TF 2 OD API model, now I'm trying to run it through the OpenCV DNN module. I am running into a lot of problems, but most are related to the StatefulPartitionedCall layer. please ...
1
vote
0
answers
201
views
Conversion of TF2 model (saved_model.pb) to TF1 format (frozen_inference_graph.pb)
Currently OpenCV does not support TF2 Object Detection models. I would like to convert a MobileNet V2 FPNLite 640x640 SSD model from TF2 to TF1 to run via cv2.readNetFromTensorflow. How is this ...
1
vote
1
answer
103
views
Tensorflow using all of one GPU but little of the other
After running into OOM errors using Tensorflow Object Detection API with an NVIDIA 3080 (10GB) I bought a 4090 (24GB). I am currently running both together, but I noticed that in high batch size runs, ...
0
votes
1
answer
676
views
How to use an object detection tensor flow lite model (converted from yolo v5) in android camera app?
I'm making an object detection app using kotlin and tensor flow lite model (I used yolo v5 and then converted it to tensor flow lite using the following line:
python export.py --weights best.pt --...
0
votes
0
answers
578
views
Tensorflow object detection api installation problem
I'm trying to install the TF Object Detection API following instructions from here.
Not using anything related to GPU.
I successfully have already gone through everything except this line:
python -m ...
0
votes
1
answer
884
views
How to modify output from TFLite exported Yolov5s model to work with an android app built with kotlin?
I want to load my TFLite exported Yolov5s model into my object detection android app. I followed this tutorial: https://www.youtube.com/watch?v=zs43IrWTzB0
However, my TFLite Yolov5 model outputs an ...
0
votes
0
answers
216
views
How do I deploy my custom trained tensorflow 2.0 model into my react.js webapp
I have converted my tensorflow model into a .tflite file, not sure if it is the correct format, but I tried uploading it onto firebase but it was not compatible with reactjs as it only gives the code ...
-2
votes
1
answer
148
views
How to Convert tensorflow saved_model to frozen inference graph?
I train a model by tensorflow 2 to detecting vehicles, but I want to Convert tensorflow saved_model to frozen inference graph.
Can any one help?
0
votes
1
answer
97
views
unable to from Convert Pascal VOC to tfrecords for tensor flow object detection API
unable to from Convert Pascal VOC to tfrecords for tensor flow object detection API , reference : https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/training.html#create-...
0
votes
1
answer
124
views
Installing tensorflow object_detection api in a repo in google drive
I have cloned the models repo from TensorFlow and installed it into my project folder in google drive.
but when I try to run the model_builder_tf2_test.py I am getting ModuleNotFoundError: No module ...
0
votes
1
answer
893
views
CUDA and CUDAtoolkit TensorFlow in wsl2 ubuntu 20.04 with gpu enabled
are CUDA and CUDAtoolkit different?
I installed CUDA using this tutorial
I ran the sample too and it worked but to run tensorflow using gpu Do I need to install CUDAtoolkit and cudnn along with the ...
0
votes
2
answers
344
views
Python Tensorflow stopped working; cannot import tensorflow due to keras import error
I was playing around with a custom object detector through the Tensorflow object detection API in Python. All of a sudden my code stopped working and is producing the following error when trying to ...
0
votes
0
answers
138
views
Object Detection API List index out of range
I'm trying to use the ssd mobilenetv3 object detection model, I found this tutorial
I tried running the python file on my device using an image I snapped with my phone
but I keep getting this error
...
1
vote
1
answer
1k
views
Serialization error while exporting Object detection model
While expoting an object detection model inference graph with Tensorflow Object Detection API (TFODAPI), I am getting a warning as:
WARNING:tensorflow:Skipping full serialization of Keras layer ...
0
votes
1
answer
778
views
"import tensorflow" results in error: No module named 'tensorflow.python.eager.polymorphic_function' (Python in Jupyter Lab)
Python 3.9.12.
Windows 10.
jupyterlab 3.3.2.
Import tensorflow
When I try to import Tensorflow, I get the following 'tensorflow.python.eager.polymorphic_function' error.
------------------------------...
1
vote
1
answer
215
views
Tensorflow object detection API only evaluates the latest checkpoint
I've trained SSD mobilent v2 320x320 model with around 4k steps which produced quite a few checkpoints that are saved in my training folder.The issue I am experiencing now is that this only evaluates ...
0
votes
0
answers
135
views
Adjust "max_detection_per_class" for every class in Tensorflow Object Detection API
I am training an object detection algorithm using the Tensorflow Object Detection API. I am currently using the vanilla version of the config files, I just changed what was absolutely necessary to ...