cityscapes_training.py

import os
import sys
import random
import math
import re
import time
import numpy as np
import cv2
import matplotlib
import matplotlib.pyplot as plt

from config import Config
import utils
import model as modellib
import visualize
from model import log
import argparse

# example of execution
#python -i cityscapes_training.py --training_path_annot cityscapes/train_annot --training_path_images cityscapes/train_img --validation_path_annot cityscapes/val_annot --validation_path_images cityscapes/val_img

PARSER = argparse.ArgumentParser()

PARSER.add_argument(
	"--training_path_annot",
	type=str,
	required=True,
	help="where to find the cities folders with the annotation for training.")

PARSER.add_argument(
	"--training_path_images",
	type=str,
	required=True,
	help="where to find the cities folders with the images for training.")

PARSER.add_argument(
	"--validation_path_annot",
	type=str,
	required=True,
	help="where to find the cities folders with the annotation for validation.")

PARSER.add_argument(
	"--validation_path_images",
	type=str,
	required=True,
	help="where to find the cities folders with the images for validation.")

ARGS = vars(PARSER.parse_args())


from cityscapes_dataset_creator import CityscapesDataset


# Root directory of the project
ROOT_DIR = os.getcwd()

# Directory to save logs and trained model
MODEL_DIR = os.path.join(ROOT_DIR, "logs")

# Path to COCO trained weights
COCO_MODEL_PATH = os.path.join(ROOT_DIR, "mask_rcnn_coco.h5")

# Training dataset
dataset_train = CityscapesDataset()
dataset_train.create_dataset(ARGS['training_path_annot'], ARGS['training_path_images'])
dataset_train.prepare()

# Validation dataset
dataset_val = CityscapesDataset()
dataset_val.create_dataset(ARGS['validation_path_annot'], ARGS['validation_path_images'])
dataset_val.prepare()

class CityscapesConfig(Config):
    """Configuration for training on the Cityscapes dataset.
    Derives from the base Config class and overrides values specific
    to this dataset.
    """
    # Give the configuration a recognizable name
    NAME = "Cityscapes"

    # Train on 1 GPU and 8 images per GPU. We can put multiple images on each
    # GPU because the images are small. Batch size is 8 (GPUs * images/GPU).
    GPU_COUNT = 1
    IMAGES_PER_GPU = 8

    # Number of classes (including background)
    NUM_CLASSES = dataset_train.num_classes  # background + normal classses

    # Use small images for faster training. Set the limits of the small side
    # the large side, and that determines the image shape.
    IMAGE_MIN_DIM = 256
    IMAGE_MAX_DIM = 256

    # Use smaller anchors because our image and objects are small
    RPN_ANCHOR_SCALES = (8, 16, 32, 64, 128)  # anchor side in pixels

    # Reduce training ROIs per image because the images are small and have
    # few objects. Aim to allow ROI sampling to pick 33% positive ROIs.
    TRAIN_ROIS_PER_IMAGE = 32

    # Use a small epoch since the data is simple
    STEPS_PER_EPOCH = 100

    # use small validation steps since the epoch is small
    VALIDATION_STPES = 5
    
config = CityscapesConfig()
config.display()



# not sure why we need this...
def get_ax(rows=1, cols=1, size=8):
    """Return a Matplotlib Axes array to be used in
    all visualizations in the notebook. Provide a
    central point to control graph sizes.
    
    Change the default size attribute to control the size
    of rendered images
    """
    _, ax = plt.subplots(rows, cols, figsize=(size*cols, size*rows))
    return ax




# Load and display random samples
image_ids = np.random.choice(dataset_train.image_ids, 4)
for image_id in image_ids:
    image = dataset_train.load_image(image_id)
    mask, class_ids = dataset_train.load_mask(image_id)
    visualize.display_top_masks(image, mask, class_ids, dataset_train.class_names)
plt.show()


# Create model in training mode
model = modellib.MaskRCNN(mode="training", config=config,
                          model_dir=MODEL_DIR)

# Which weights to start with?
init_with = "coco"  # imagenet, coco, or last

if init_with == "imagenet":
    model.load_weights(model.get_imagenet_weights(), by_name=True)
elif init_with == "coco":
    # Load weights trained on MS COCO, but skip layers that
    # are different due to the different number of classes
    # See README for instructions to download the COCO weights
    model.load_weights(COCO_MODEL_PATH, by_name=True,
                       exclude=["mrcnn_class_logits", "mrcnn_bbox_fc", 
                                "mrcnn_bbox", "mrcnn_mask"])
elif init_with == "last":
    # Load the last model you trained and continue training
    model.load_weights(model.find_last()[1], by_name=True)

# Train the head branches
# Passing layers="heads" freezes all layers except the head
# layers. You can also pass a regular expression to select
# which layers to train by name pattern.
model.train(dataset_train, dataset_val, 
            learning_rate=config.LEARNING_RATE, 
            epochs=1, 
            layers='heads')

# Fine tune all layers
# Passing layers="all" trains all layers. You can also 
# pass a regular expression to select which layers to
# train by name pattern.
model.train(dataset_train, dataset_val, 
            learning_rate=config.LEARNING_RATE / 10,
            epochs=2, 
            layers="all")

# Save weights
# Typically not needed because callbacks save after every epoch
# Uncomment to save manually
# model_path = os.path.join(MODEL_DIR, "mask_rcnn_shapes.h5")
# model.keras_model.save_weights(model_path)

# Detection

class InferenceConfig(CityscapesConfig):
    GPU_COUNT = 1
    IMAGES_PER_GPU = 1

inference_config = InferenceConfig()

# Recreate the model in inference mode
model = modellib.MaskRCNN(mode="inference", 
                          config=inference_config,
                          model_dir=MODEL_DIR)

# Get path to saved weights
# Either set a specific path or find last trained weights
# model_path = os.path.join(ROOT_DIR, ".h5 file name here")
model_path = model.find_last()[1]

# Load trained weights (fill in path to trained weights here)
assert model_path != "", "Provide path to trained weights"
print("Loading weights from ", model_path)
model.load_weights(model_path, by_name=True)

# Test on a random image
image_id = random.choice(dataset_val.image_ids)
original_image, image_meta, gt_bbox, gt_mask =\
    modellib.load_image_gt(dataset_val, inference_config, 
                           image_id, use_mini_mask=False)

log("original_image", original_image)
log("image_meta", image_meta)
log("gt_bbox", gt_bbox)
log("gt_mask", gt_mask)

visualize.display_instances(original_image, gt_bbox[:,:4], gt_mask, gt_bbox[:,4], 
                            dataset_train.class_names, figsize=(8, 8))
plt.show()

results = model.detect([original_image], verbose=1)

r = results[0]
visualize.display_instances(original_image, r['rois'], r['masks'], r['class_ids'], 
                            dataset_val.class_names, r['scores'], ax=get_ax())
plt.show()


# Compute VOC-Style mAP @ IoU=0.5
# Running on 10 images. Increase for better accuracy.
image_ids = np.random.choice(dataset_val.image_ids, 10)
APs = []
for image_id in image_ids:
    # Load image and ground truth data
    image, image_meta, gt_bbox, gt_mask =\
        modellib.load_image_gt(dataset_val, inference_config,
                               image_id, use_mini_mask=False)
    molded_images = np.expand_dims(modellib.mold_image(image, inference_config), 0)
    # Run object detection
    results = model.detect([image], verbose=0)
    r = results[0]
    # Compute AP
    AP, precisions, recalls, overlaps =\
        utils.compute_ap(gt_bbox[:,:4], gt_bbox[:,4],
                         r["rois"], r["class_ids"], r["scores"])
    APs.append(AP)
    
print("mAP: ", np.mean(APs))