Use the Cars Dataset, which contains 16,185 images of 196 classes of cars. The data is split into 8,144 training images and 8,041 testing images, where each class has been split roughly in a 50-50 split.
$ cd Car-Recognition
$ wget http://imagenet.stanford.edu/internal/car196/cars_train.tgz
$ wget http://imagenet.stanford.edu/internal/car196/cars_test.tgz
$ wget --no-check-certificate https://ai.stanford.edu/~jkrause/cars/car_devkit.tgz
Extract 8,144 training images, and split them by 80:20 rule (6,515 for training, 1,629 for validation):
$ python pre_process.py
$ python train.py
To visualize during training, run in your terminal:
$ tensorboard --logdir path_to_current_dir/logs
Update "model_weights_path" in "utils.py" with your best model, and use 1,629 validation images for result analysis:
$ python analyze.py
88.70%
$ python demo.py --i [image_path]
If no argument, a sample image is used:
$ python demo.py
class_name: Lamborghini Reventon Coupe 2008
prob: 0.9999994