neural_net.py

import os
import sys
import numpy as np

from PIL import Image

# Root directory of the project
ROOT_DIR = '.'

# Import Mask RCNN
sys.path.append(ROOT_DIR)  # To find local version of the library
from mrcnn import utils
import mrcnn.model as modellib
# from mrcnn import visualize
# Import COCO config
# sys.path.append(os.path.join(ROOT_DIR, "/coco/"))  # To find local version

from mrcnn.config import Config

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

    # We use a GPU with 12GB memory, which can fit two images.
    # Adjust down if you use a smaller GPU.
    IMAGES_PER_GPU = 2

    # Uncomment to train on 8 GPUs (default is 1)
    # GPU_COUNT = 8

    # Number of classes (including background)
    NUM_CLASSES = 1 + 80  # COCO has 80 classes


# Directory to save logs and trained model
MODEL_DIR = ROOT_DIR + '/logs'

# Local path to trained weights file
COCO_MODEL_PATH = ROOT_DIR + '/mask_rcnn_coco.h5'
# Download COCO trained weights from Releases if needed
if not os.path.exists(COCO_MODEL_PATH):
    utils.download_trained_weights(COCO_MODEL_PATH)

# Directory of images to run detection on
IMAGE_DIR = ROOT_DIR + '/images'

class InferenceConfig(CocoConfig):
    # Set batch size to 1 since we'll be running inference on
    # one image at a time. Batch size = GPU_COUNT * IMAGES_PER_GPU
    GPU_COUNT = 1
    IMAGES_PER_GPU = 1

config = InferenceConfig()
# config.display()


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

# Load weights trained on MS-COCO
model.load_weights(COCO_MODEL_PATH, by_name=True)
model.keras_model._make_predict_function()


# COCO Class names
# Index of the class in the list is its ID. For example, to get ID of
# the teddy bear class, use: class_names.index('teddy bear')
class_names = ['BG', 'person', 'bicycle', 'car', 'motorcycle', 'airplane',
               'bus', 'train', 'truck', 'boat', 'traffic light',
               'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird',
               'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear',
               'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie',
               'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball',
               'kite', 'baseball bat', 'baseball glove', 'skateboard',
               'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup',
               'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
               'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza',
               'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed',
               'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote',
               'keyboard', 'cell phone', 'microwave', 'oven', 'toaster',
               'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors',
               'teddy bear', 'hair drier', 'toothbrush']

def predict_by_image(image):
    # image_path = '/home/ekaterina/code/technosphere/project/druid.jpg'
    # image = skimage.io.imread(image_path)
    global model
    results = model.detect([image], verbose=1)
    return results[0]

def apply_mask(image, result):
    object_number = 0
    # mask = np.where(result['masks'][:, :, object_number] == 0)
    image = np.dstack([image,  (result['masks'][:, :, object_number]*255).astype(np.uint8)])
    return Image.fromarray(image, 'RGBA')