Image Classification Tutorial: Train and Detect Objects with TensorFlow and Pixellib

preview_player
Показать описание
Welcome to our comprehensive tutorial on image annotation, training, and object detection using TensorFlow, Pixellib, and ResNet101! In this video, we'll guide you through the process of annotating objects within images, creating JSON files to label each image accurately, and training a custom model with the powerful ResNet101 architecture.

First, we'll demonstrate how to annotate objects by placing dots along the image, effectively defining their boundaries. We'll then generate a JSON file for each image, which serves as a label containing the coordinates of the annotated dots. This step is crucial for training our custom model accurately.

Next, we'll introduce ResNet101, a pre-trained deep learning model renowned for its exceptional performance in image classification tasks. Leveraging transfer learning, we'll train our custom images and corresponding labels using ResNet101. This process allows us to harness the capabilities of a well-established model while adapting it to our specific object detection requirements.

~~~~~~~~~~~~~~~ recommended courses and books ~~~~~~~~~~~~~~~

I am using one of these desktop cameras in my projects :

~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~

~~~~~~~~~~~~~~ SUPPORT ME 🙏~~~~~~~~~~~~~~
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#EranFeit #Pixellib #python
~~~~~~~~~~~~~~ Credits ~~~~~~~~~~~~~
Music by Vincent Rubinetti
Рекомендации по теме
Комментарии
Автор

I am willing to learn Python programming after watching your videos. It's really great.

offerxs
Автор

Nice video! I tried following along to use this training method toward my current research project in undergrad. I got a permission error when loading the data set (around 4:43 in your video). Any tips or resources that you could give me would be greatly appreciated.
Cheers!

oliviaharman
Автор

I followed and got error "ValueError:cannot reshape array size 390 into shape (256, 3) " in the line .train_model is there anyway to fix this?

chantip_mim
Автор

thx for this great video but i have a problem the training takes more than 24h also when i try to select one model all of them give me and i don't know where the problem is

amagdiie
Автор

How to learn Coding like you? I am very interested

iklstudio
Автор

Nice video but This is object segmentation

aboudezoa
visit shbcf.ru