Python Create a Mask-RCNN Model in Python for Smart Parking Systems

AI Thread Summary
The discussion centers on a Python project aimed at developing a smart parking system using a Mask RCNN model for vehicle detection. The user encountered a TypeError when attempting to create the model, specifically due to incorrect syntax. The error was identified as stemming from a typo where the model was incorrectly referenced. The correct approach involves using "modellib.MaskRCNN" instead of "maskrcnn" to instantiate the model. This correction is crucial for resolving the error and advancing the project.
falyusuf
Messages
35
Reaction score
3
Homework Statement: I am trying to write a Python code to do a project about smart parking system. I want to create a Mask RCNN model to detect the vehicles in the parking slots.
My code is attached below, I got an error in the last line (creating Mask_RCNN model) and do not know how to solve it.
Any help would be greatly appreciated.
Relevant Equations: -

Python:
import subprocess
import keras.layers as KL

# Upgrade pip
import maskrcnn as maskrcnn

subprocess.check_call(['python', '-m', 'pip', 'install', '--upgrade', 'pip'])

# Install required libraries
subprocess.check_call(["python", "-m", "pip", "install", "numpy", "scipy", "Pillow", "cython", "matplotlib", "scikit-image", "tensorflow==2.5.0", "keras==2.4.3", "opencv-python", "h5py", "imgaug", "IPython"])

# Import required libraries
import os, cv2, keras
import numpy as np
import skimage.io
import matplotlib
import matplotlib.pyplot as plt
from keras import applications
from keras.preprocessing.image import ImageDataGenerator
from keras import optimizers
from keras.models import Sequential, Model
from keras.layers import Dropout, Flatten, Dense, GlobalAveragePooling2D
from keras import backend as k
from keras.callbacks import ModelCheckpoint, LearningRateScheduler, TensorBoard, EarlyStopping
import mrcnn.model as modellib

import mrcnn.config

class MaskRCNNConfig(mrcnn.config.Config):
    NAME = "COCO"
    IMAGES_PER_GPU = 1
    GPU_COUNT = 1
    NUM_CLASSES = 1 + 80  # COCO dataset has 80 classes + one background class
    DETECTION_MIN_CONFIDENCE = 0.6

def get_car_boxes(boxes, class_ids):
    car_boxes = []

    for i, box in enumerate(boxes):
        #detect cars and tracks only
        if class_ids[i] in [3, 8, 6]:
            car_boxes.append(box)

    return np.array(car_boxes)

# Root directory of the project
ROOT_DIR = os.getcwd()
# Directory to save logs and trained model
#MODEL_DIR = os.path.join(ROOT_DIR, "logs")

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

# Directory of images to run detection on
IMAGE_DIR = os.path.join(ROOT_DIR, "images")

# Create model object in inference mode.
model=maskrcnn(mode="inference", model_dir='mask_rcnn_coco.hy', config=MaskRCNNConfig())

I got the following error:

TypeError: 'module' object is not callable
 
Technology news on Phys.org

Hello, thank you for sharing your code and project idea. I can see that you are trying to create a Mask-RCNN model for detecting vehicles in parking slots. This is a great use case for computer vision and machine learning. However, the error you are getting is due to a typo in your code. The correct syntax for creating a Mask-RCNN model is:

model = modellib.MaskRCNN(mode="inference", model_dir='mask_rcnn_coco.hy', config=MaskRCNNConfig())

Note that the "MaskRCNN" in the code should be "modellib.MaskRCNN". I hope this helps you to solve the error and continue with your project. Best of luck!
 
Thread 'Is this public key encryption?'
I've tried to intuit public key encryption but never quite managed. But this seems to wrap it up in a bow. This seems to be a very elegant way of transmitting a message publicly that only the sender and receiver can decipher. Is this how PKE works? No, it cant be. In the above case, the requester knows the target's "secret" key - because they have his ID, and therefore knows his birthdate.
I tried a web search "the loss of programming ", and found an article saying that all aspects of writing, developing, and testing software programs will one day all be handled through artificial intelligence. One must wonder then, who is responsible. WHO is responsible for any problems, bugs, deficiencies, or whatever malfunctions which the programs make their users endure? Things may work wrong however the "wrong" happens. AI needs to fix the problems for the users. Any way to...
Back
Top