Get data using http://www.vision.caltech.edu/datasets/cub_200_2011/ Untar using tar -czvf CUB_200_2011.tgz Place the python files from this repo in the same folder.

Execute below code only once

To get the data in one folder and the desired info: python pre_process.py

To load the images and save as np format so we don't have to re-run it for every training iteration Note: this saves the labels in the y_train and y_test data so you might want to change it to use bounding boxes, segmentations. python save_as_np.py

Before creating the model if checkpoints are desired, create the folder specified in checkpoint_path variable. python train.py

Below is original readme from the dataset

For more information about the dataset, visit the project website:

http://www.vision.caltech.edu/visipedia

If you use the dataset in a publication, please cite the dataset in the style described on the dataset website (see url above).

• images/ The images organized in subdirectories based on species. See IMAGES AND CLASS LABELS section below for more info.
• parts/ 15 part locations per image. See PART LOCATIONS section below for more info.
• attributes/ 322 binary attribute labels from MTurk workers. See ATTRIBUTE LABELS section below for more info.

Images are contained in the directory images/, with 200 subdirectories (one for each bird species)

------- List of image files (images.txt) ------ The list of image file names is contained in the file images.txt, with each line corresponding to one image:

------- Train/test split (train_test_split.txt) ------ The suggested train/test split is contained in the file train_test_split.txt, with each line corresponding to one image:

<image_id> <is_training_image>

------- List of class names (classes.txt) ------ The list of class names (bird species) is contained in the file classes.txt, with each line corresponding to one class:

------- Image class labels (image_class_labels.txt) ------ The ground truth class labels (bird species labels) for each image are contained in the file image_class_labels.txt, with each line corresponding to one image:

<image_id> <class_id>

Each image contains a single bounding box label. Bounding box labels are contained in the file bounding_boxes.txt, with each line corresponding to one image:

<image_id>

where <image_id> corresponds to the ID in images.txt, and , , , and are all measured in pixels

------- List of part names (parts/parts.txt) ------ The list of all part names is contained in the file parts/parts.txt, with each line corresponding to one part:

------- Part locations (parts/part_locs.txt) ------ The set of all ground truth part locations is contained in the file parts/part_locs.txt, with each line corresponding to the annotation of a particular part in a particular image:

<image_id> <part_id>

------- MTurk part locations (parts/part_click_locs.txt) ------ A set of multiple part locations for each image and part, as perceived by multiple MTurk users is contained in parts/part_click_locs.txt, with each line corresponding to the annotation of a particular part in a particular image by a different MTurk worker:

<image_id> <part_id>

------- List of attribute names (attributes/attributes.txt) ------ The list of all attribute names is contained in the file attributes/attributes.txt, with each line corresponding to one attribute:

------- List of certainty names (attributes/certainties.txt) ------ The list of all certainty names (used by workers to specify their certainty of an attribute response of is contained in the file attributes/certainties.txt, with each line corresponding to one certainty:

------- MTurk image attribute labels (attributes/image_attribute_labels.txt) ------ The set of attribute labels as perceived by MTurkers for each image is contained in the file attributes/image_attribute_labels.txt, with each line corresponding to one image/attribute/worker triplet:

<image_id> <attribute_id> <is_present> <certainty_id>