Train a Deep Learning model for custom object detection using TensorFlow 1.x (On Google Colab)

Показать описание

This video shows step by step tutorial on how to train an object detection model for a custom dataset using TensorFlow 1.x. The custom object trained here is a face mask.

① ⚡⚡ My Website Blog post on this ⚡⚡

② ⚡⚡ My Medium post on ⚡⚡

③ ⚡⚡ My Colab notebook for this ⚡⚡

④ ⚡⚡My GitHub link for this ⚡⚡

⑤ ⚡⚡ My labeled dataset for this (PASCAL_VOC format XML files)⚡⚡

⑥ ⚡⚡ Article on Dataset Labeling/Annotation⚡⚡

#TensorFlow #customobjectdetection #mobilenet #TF1 #tensorflow1 #maskdetection #SSDModelTraining #facemaskdetection #objectdetection

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Making these videos takes a lot of time and effort, so if you like these videos and if you can, then please support the channel using any of the following:

► Buy me a coffee! ☕

► Support channel on Patreon! 🖖

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Thanks for watching!

Рекомендации по теме

Комментарии

Thank you thank you thank you thank you very you dont know how much you helped me with this
I watch so much other video and followed different github link but always i stuck with some error. But with this your video i Finnaly train my model on my custom dataset...

and in your google collab troubleshooting you provided is actually helped me and no other had provided earlier in their documentation

ThankYou very much I love you lots of

nemesis

Thank you for such an organized and thorough tutorial, has been extremely helpful

yasminemohamed

superb explanation. i think initially panic then good

mohamedmuaadh

Excuse me sir, if i want to use mobileNet v3 mode which is only availablen in tensorflow 1 model zoo, can i do the training using tensorflow 2

aryao

Could you please me tell how do I get bounding box coordinates of test images if I intend to further process the true positive and false positive instances( say in case of cancer detection problem)?

You know like in a csv file ? So I can just crop out those detected images.

abdulrahimshihabuddin

Hey, i were training using mobilenet_ssd_v2 model and got error like this
"ValueError: num predictions per location must be same for allfeature maps, found: [3, 6, 6, 6, 6, 6]"

do u know where to change that? or how to solve that?

yogaaditya

I have noticed that in TF1.x it is possible to obtain a .meta file as output, which is not possible in TF2.x (in the other guide that you have made). Do I need it to pass from a .pb file to a .h5 file? or there is the possibility to perform this conversion without this .meta file? I need the .h5 file for another code that I need to use. Thank you for the great tutorial!

lucapoli

first of all thanks, my files are bmp, not jpg. Will it work?

AliMuhammedSOYLU

thanks alot this video really helped me out.i would also like to give an output -the name of the image detected, can someone help me out there

sahalayasmin

In config file remove one deprecated field batch_norm_trainable:true . And everything will fine .

cleanbold

how to get the iou score for testing the [erformanceof this model

sakshibhoir

Does it work with real time object detection?

hadif

Thanks for this video.
My results(cat and dog dataset) have multiple bounding boxes in an image. What should I do? T_T

creeda.

As I'm using free colab version so I stopped training when loss =3.1 . Then exported inference graph . While testing it is not detecting objects. Can you help me . I have used vegetable dataset of five classes . It took 3 hrs to train upto 8000 steps . Loss 3.1

cleanbold

I faced problem when i install tensorflow==1.15: No matching distribution found for tensorflow==1.15 how can I solve it

salemsalem-dize

Thanks alot sir, sir please upload the custom detection of faster RCNN, RNN on pytorch using linux also and please upload the tf2 on linux also.Btw your content is amazing sir.

abubakarsaleem

Hi First of all thank you for your efforts.
But I got the following error in training part. And I could not find a solution.
"Cannot convert a symbolic Tensor (cond_2/strided_slice:0) to a numpy array."

canuzun

Getting stuck on saving checkpoints 0 any idea

Daniiijaniii

Why did you do on TF 1?, instead of TF2.

neilh

Hey Thank you for the video!
I am getting this error after training my model,
Transport endpoint is not connected.
what I should do now?

meghna

Train a Deep Learning model for custom object detection using TensorFlow 1.x (On Google Colab)

Epochs, Iterations and Batch Size | Deep Learning Basics

Python for AI #3: How to Train a Machine Learning Model with Python

TensorFlow in 100 Seconds

Deep Learning | What is Deep Learning? | Deep Learning Tutorial For Beginners | 2023 | Simplilearn

Neural Networks Explained in 5 minutes

Machine Learning Explained in 100 Seconds

How to train AI ML models? Full pipeline in 15 mins.

How To Train Deep Learning Models In Google Colab- Must For Everyone

MobileNet - Deep Learning that fits in your pocket | Convolutional Neural Network | Computer Vision

Why do we split data into train test and validation sets?

What are Transformers (Machine Learning Model)?

PyTorch in 100 Seconds

Machine Learning Tutorial Python - 7: Training and Testing Data

But what is a neural network? | Deep learning chapter 1

All Machine Learning Models Explained in 5 Minutes | Types of ML Models Basics

Backpropagation, intuitively | Deep Learning Chapter 3

Build your first machine learning model in Python

Create a Basic Neural Network Model - Deep Learning with PyTorch 5

Load Data and Train Neural Network Model - Deep Learning with PyTorch 6

How to Train YOLO Object Detection Models in Google Colab (YOLO11, YOLOv8, YOLOv5)

Deep Learning Cars

Azure Machine Learning Service Tutorial - Train Your Model

Train, Test, & Validation Sets explained

How is data prepared for machine learning?