Stack Overflow
Stack Overflow

Questions tagged [single-shot-detector]

19 questions
3
votes
0 answers

Output tensor size mismatch with SSD FPN Models on mobile

I am trying to get different SSD Models from Tensorflow 2 to work in Android. The example .tflite file works fine, but different other models i've converted and tried all seem to have the same issue. I've mostly followed this guide on how to convert…
puelo
  • 5,464
  • 2
  • 34
  • 62
2
votes
2 answers

Reduce Training steps for SSD-300

I am new to deep learning and I am trying to train my SSD-300 (single shot detector) model which is taking too long. For example even though I ran 50 epochs, it is training for 108370+ global steps. I am using the default train_ssd_network.py file…
EverydayDeveloper
  • 1,110
  • 4
  • 11
  • 34
1
vote
0 answers

How to Convert labelme json data to Pascal VOC format using labelme2voc.py

I have annotated images in label-me and the annotation is saved in .json file. I am trying to train a SSD object dictation model and I need data in Pascal VOC format. Label me has a file named labelme2voc.py I tried multiple time and failed each…
What
  • 15
  • 5
1
vote
0 answers

Getting Nan value for the loss while training a SSD-Mobilenet that was using a custom loss function

Implementing the SSD-Mobilenetv1 from scratch with Pascal VOC -2007 and 2012 dataset and using GPU 3060 for training in tensorflow mainly using this code - https://github.com/ManishSoni1908/Mobilenet-ssd-keras. the error would look like Epoch 1/10 …
manish
  • 21
  • 1
1
vote
1 answer

How to fix 'tensor is out of scope and cannot be use here' ? in Python

I need help to fix this error. I got code of SSD (single shot multibox detector) in GitHub and I convert some TF 1.x function to TF 2.x function, everything works well until this chunk of code. I've got this code from…
Franz Junior
  • 31
  • 3
1
vote
1 answer

OpenVino anchor output Python

I am using openvino action recognition model to detect person's actions. I referred to the C++ Smart Classroom demo, but I have trouble parsing the output in python. The following is my code. I can see the output shapes for all acnhors. How can I…
Hasala
  • 126
  • 10
1
vote
1 answer

Post process of tf2 SSD detection models

I need to use a detection model of tensorflow on ios. The tflite model file available in 1 is in uint8 format which doesn't work well with CoreML, so I decided to download a full model and convert it to tflite myself. All SSD models in the TF zoo…
gozi
  • 63
  • 6
0
votes
0 answers

Quantization for Single shot detector(SSD)

I have SSD model with good accuracy above 80per and detection will happen in 0.20 seconds. However, I want to reduce the detection period to about 0.05-0.08seconds and reduce model size. I came to know that quantization is the process to reduce the…
ajith
  • 1
0
votes
0 answers

No such file or directory: '/home/vinay/DS/data/VOCdevkit/VOC2007/ImageSets/Main/trainval.txt'

I was trying to train the mobilenet ssd for some coco images. I ran into this issue. I have tried to split he dataset and split the dataset based on my knowledge of VOC2007 and VOC2012 format. But i am still running into issues. I request my fellows…
Vinay Hegde
  • 1
  • 1
0
votes
0 answers

Optimize sizes and aspect ratios of prior boxes in SSD network

I use SSD network to detect objects in thermal image. Since our camera has only the resolution of 160x120 pixels, I don't resize image to 300x300 but use the camera resolution as the input into the SSD network. The network is prototxt trained using…
bigmuscle
  • 419
  • 1
  • 6
  • 16
0
votes
0 answers

How do I write a script to save a screenshot from a specific object in a webcam?

I'm currently using a ssd mobilenet algorithm to detect objects in a webcam live time. It shows me the predicted item on the webcam and the position from the blob at the terminal as well. Here is the code as it follows: import cv2 cap =…
Borghi97
  • 1
0
votes
0 answers

Problem detecting zebra crossings with SSD's using TensorFlow Object detection API

My task is to evaluate different Models of the TensorFlow Object detection API for the detection of zebra crossings. I have a dataset of 400 labeled pictures. I already tried the Faster R-CNN based models of the model zoo, and they all perform…
Benedikt Halbritter
  • 1
0
votes
0 answers

Accuracy and Loss Plots for Tensorflow Model 2.0

I am following this tutorial https://www.youtube.com/watch?v=amURyS6CAaY exactly on training a TensorFlow model with a custom dataset. I tried adding a Tensorboard however it does not show the accuracy and loss by epoch. The issue with the below…
maximus
  • 335
  • 2
  • 16
0
votes
2 answers

How to display the number of objects in an image for single class?

I am new to programming and been learning the tutorial in google colab for algorithm in object detection. Below is the code used in google object detection API…
CKT
  • 3
  • 2
0
votes
1 answer

Unstable loss SSD-300 due to which mAP is low

I am training my SSD-300 model for which I have resized images to 300x300. I am using the default settings as mentioned in github repo:https://github.com/balancap/SSD-Tensorflow The loss is unstable while training. I tried training it till 50,000…
EverydayDeveloper
  • 1,110
  • 4
  • 11
  • 34
1
2