I have been working on this project since August 0f 2023. I'm happy that i could get the classifier accuracy more than 80%. there are 3 main fies in this repository. i don't attach the data directory which consisit of 102 flower varities since it's more than 25Mb. i would like to give link later. @predict.py and @train.py can be accessed only from the commandline. i will provide the basic commands below.
Train a new network on a data set with train.py
Basic usage:
python train.py data_directory
Prints out training loss, validation loss, and validation accuracy as the network trains
Options:
Set directory to save checkpoints: python train.py data_dir --save_dir save_directory
Choose architecture: python train.py data_dir --arch "vgg13"
Set hyperparameters: python train.py data_dir --learning_rate 0.01 --hidden_units 512 --epochs 20\
Use GPU for training: python train.py data_dir --gpu
Predict flower name from an image with predict.py along with the probability of that name. That is, you'll pass in a single image /path/to/image and return the flower name and class probability.\
Basic usage:
python predict.py /path/to/image checkpoint
Options:
Return top K most likely classes: python predict.py input checkpoint --top_k 3
Use a mapping of categories to real names: python predict.py input checkpoint --category_names cat_to_name.json
Use GPU for inference: python predict.py input checkpoint --gpu
@image classifier.ipynb jupyter notebook is there to learn how to develop the model. more over it's not a model from scratch. using the transfer learning i could get code only for the classifier.
i will provide the further improvements below.
(This is a draft ..)\