Notebook

Mask R-CNN - Inspect Trained Model¶

Code and visualizations to test, debug, and evaluate the Mask R-CNN model.

In [1]:

import os
import sys
import random
import math
import re
import time
import numpy as np
import tensorflow as tf
import matplotlib
import matplotlib.pyplot as plt
import matplotlib.patches as patches

# Root directory of the project
ROOT_DIR = os.path.abspath("../../")

# Import Mask RCNN
sys.path.append(ROOT_DIR)  # To find local version of the library
from mrcnn import utils
from mrcnn import visualize
from mrcnn.visualize import display_images
import mrcnn.model as modellib
from mrcnn.model import log

%matplotlib inline 

# 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")
# Download COCO trained weights from Releases if needed
if not os.path.exists(COCO_MODEL_PATH):
    utils.download_trained_weights(COCO_MODEL_PATH)

# Path to Shapes trained weights
SHAPES_MODEL_PATH = os.path.join(ROOT_DIR, "mask_rcnn_shapes.h5")

Using TensorFlow backend.

Configurations¶

In [2]:

# Run one of the code blocks

# Shapes toy dataset
# import shapes
# config = shapes.ShapesConfig()

# MS COCO Dataset
import coco
config = coco.CocoConfig()
COCO_DIR = "path to COCO dataset"  # TODO: enter value here

In [3]:

# Override the training configurations with a few
# changes for inferencing.
class InferenceConfig(config.__class__):
    # Run detection on one image at a time
    GPU_COUNT = 1
    IMAGES_PER_GPU = 1

config = InferenceConfig()
config.display()

Configurations:
BACKBONE_SHAPES                [[256 256]
 [128 128]
 [ 64  64]
 [ 32  32]
 [ 16  16]]
BACKBONE_STRIDES               [4, 8, 16, 32, 64]
BATCH_SIZE                     1
BBOX_STD_DEV                   [ 0.1  0.1  0.2  0.2]
DETECTION_MAX_INSTANCES        100
DETECTION_MIN_CONFIDENCE       0.5
DETECTION_NMS_THRESHOLD        0.3
GPU_COUNT                      1
IMAGES_PER_GPU                 1
IMAGE_MAX_DIM                  1024
IMAGE_MIN_DIM                  800
IMAGE_PADDING                  True
IMAGE_SHAPE                    [1024 1024    3]
LEARNING_MOMENTUM              0.9
LEARNING_RATE                  0.002
MASK_POOL_SIZE                 14
MASK_SHAPE                     [28, 28]
MAX_GT_INSTANCES               100
MEAN_PIXEL                     [ 123.7  116.8  103.9]
MINI_MASK_SHAPE                (56, 56)
NAME                           coco
NUM_CLASSES                    81
POOL_SIZE                      7
POST_NMS_ROIS_INFERENCE        1000
POST_NMS_ROIS_TRAINING         2000
ROI_POSITIVE_RATIO             0.33
RPN_ANCHOR_RATIOS              [0.5, 1, 2]
RPN_ANCHOR_SCALES              (32, 64, 128, 256, 512)
RPN_ANCHOR_STRIDE              2
RPN_BBOX_STD_DEV               [ 0.1  0.1  0.2  0.2]
RPN_TRAIN_ANCHORS_PER_IMAGE    256
STEPS_PER_EPOCH                1000
TRAIN_ROIS_PER_IMAGE           128
USE_MINI_MASK                  True
USE_RPN_ROIS                   True
VALIDATION_STEPS               50
WEIGHT_DECAY                   0.0001

Notebook Preferences¶

In [4]:

# Device to load the neural network on.
# Useful if you're training a model on the same 
# machine, in which case use CPU and leave the
# GPU for training.
DEVICE = "/cpu:0"  # /cpu:0 or /gpu:0

# Inspect the model in training or inference modes
# values: 'inference' or 'training'
# TODO: code for 'training' test mode not ready yet
TEST_MODE = "inference"

In [5]:

def get_ax(rows=1, cols=1, size=16):
    """Return a Matplotlib Axes array to be used in
    all visualizations in the notebook. Provide a
    central point to control graph sizes.
    
    Adjust the size attribute to control how big to render images
    """
    _, ax = plt.subplots(rows, cols, figsize=(size*cols, size*rows))
    return ax

Load Validation Dataset¶

In [6]:

# Build validation dataset
if config.NAME == 'shapes':
    dataset = shapes.ShapesDataset()
    dataset.load_shapes(500, config.IMAGE_SHAPE[0], config.IMAGE_SHAPE[1])
elif config.NAME == "coco":
    dataset = coco.CocoDataset()
    dataset.load_coco(COCO_DIR, "minival")

# Must call before using the dataset
dataset.prepare()

print("Images: {}\nClasses: {}".format(len(dataset.image_ids), dataset.class_names))

loading annotations into memory...
Done (t=4.86s)
creating index...
index created!
Images: 35185
Classes: ['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']

Load Model¶

In [7]:

# Create model in inference mode
with tf.device(DEVICE):
    model = modellib.MaskRCNN(mode="inference", model_dir=MODEL_DIR,
                              config=config)

# Set weights file path
if config.NAME == "shapes":
    weights_path = SHAPES_MODEL_PATH
elif config.NAME == "coco":
    weights_path = COCO_MODEL_PATH
# Or, uncomment to load the last model you trained
# weights_path = model.find_last()

# Load weights
print("Loading weights ", weights_path)
model.load_weights(weights_path, by_name=True)

Run Detection¶

In [8]:

image_id = random.choice(dataset.image_ids)
image, image_meta, gt_class_id, gt_bbox, gt_mask =\
    modellib.load_image_gt(dataset, config, image_id, use_mini_mask=False)
info = dataset.image_info[image_id]
print("image ID: {}.{} ({}) {}".format(info["source"], info["id"], image_id, 
                                       dataset.image_reference(image_id)))
# Run object detection
results = model.detect([image], verbose=1)

# Display results
ax = get_ax(1)
r = results[0]
visualize.display_instances(image, r['rois'], r['masks'], r['class_ids'], 
                            dataset.class_names, r['scores'], ax=ax,
                            title="Predictions")
log("gt_class_id", gt_class_id)
log("gt_bbox", gt_bbox)
log("gt_mask", gt_mask)

image ID: coco.392144 (34940) http://cocodataset.org/#explore?id=392144
Processing 1 images
image                    shape: (1024, 1024, 3)       min:    0.00000  max:  255.00000
molded_images            shape: (1, 1024, 1024, 3)    min: -123.70000  max:  151.10000
image_metas              shape: (1, 89)               min:    0.00000  max: 1024.00000
gt_class_id              shape: (10,)                 min:    1.00000  max:   40.00000
gt_bbox                  shape: (10, 5)               min:    0.00000  max: 1024.00000
gt_mask                  shape: (1024, 1024, 10)      min:    0.00000  max:    1.00000