Training of images in tensorflow

Asked

Viewed 632 times

1

Good night!

I’m trying to build a neural network in python using tensorflow and its other libraries, my doubt and, I have 4 classes and I need to do a training of them I have many images for each class, I need to use the CNN neural network, and I have a very modest understanding of how it works. I needed to program mount it in python using tensorflow someone in some example? Simple in python because I needed to generate the dataset or pb file (protoboof) so I know that it can take days training in order my greatest difficulty and start programming in python CNN network.

Does anyone have an example? Everyone that exists on the internet I’ve seen but almost migrate has tutorial teaching how to generate a dataset file all tutorials teach with datasets downloaded from websites like Imagenet, Incept, and Mnist. What I need is a simple example of how to generate dataset of my own images

Also from Li videos of Iris data (flower classification) but he also works with information already ready.

Hugs!

python machine-learning tensorflow

1 answer

1

You can use this model with tensorflow-hub (https://github.com/tensorflow/hub/tree/master/examples/image_retraining). With this model you can perform several manipulations, including include a new dataset. Just run it with the command lines python retrain.py --image_dir "directory path where your folders are with images"

The algorithm will already separate according to the structure of your folders, after trained just use an image classifieds to test new images.

Browser other questions tagged python machine-learning tensorflow

You are not signed in. Login or sign up in order to post.