【Mask R-CNN ubuntu安装教程及识别人物去检测框】

这位大佬的有用，适合python3.7+cuda10.1/2+cudnn7.6.5+tensorflow2.2.0
提取图片很耐思，适合小白
下面是改好的代码

 
#!/usr/bin/env python
# coding: utf-8

# # Mask R-CNN Demo
# 
# A quick intro to using the pre-trained model to detect and segment objects.

# In[1]:


import os
import sys
import random
import math
import numpy as np
import skimage.io
import matplotlib
import matplotlib.pyplot as plt

import itertools
import colorsys

import numpy as np
from skimage.measure import find_contours
import matplotlib.pyplot as plt
from matplotlib import patches,  lines
from matplotlib.patches import Polygon
import IPython.display

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

#get_ipython().run_line_magic('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)

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

# ## Configurations
# 
# We'll be using a model trained on the MS-COCO dataset. The configurations of this model are in the ```CocoConfig```class in ```coco.py```.
# 
# For inferencing, modify the configurations a bit to fit the task. To do so, sub-class the ```CocoConfig```class and override the attributes you need to change.

# In[2]:

class InferenceConfig(coco.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 and Load Trained Weights

# In[3]:

# 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)

# ## Class Names
# 
# The model classifies objects and returns class IDs, which are integer value that identify each class. Some datasets assign integer values to their classes and some don't. For example, in the MS-COCO dataset, the 'person' class is 1 and 'teddy bear' is 88. The IDs are often sequential, but not always. The COCO dataset, for example, has classes associated with class IDs 70 and 72, but not 71.
# 
# To improve consistency, and to support training on data from multiple sources at the same time, our ```Dataset```class assigns it's own sequential integer IDs to each class. For example, if you load the COCO dataset using our ```Dataset```class, the 'person' class would get class ID = 1 (just like COCO) and the 'teddy bear' class is 78 (different from COCO). Keep that in mind when mapping class IDs to class names.
# 
# To get the list of class names, you'd load the dataset and then use the ```class_names```property like this.
# ```
# # Load COCO dataset
# dataset = coco.CocoDataset()
# dataset.load_coco(COCO_DIR, "train")
# dataset.prepare()
# 
# # Print class names
# print(dataset.class_names)
# ```
# 
# We don't want to require you to download the COCO dataset just to run this demo, so we're including the list of class names below. The index of the class name in the list represent its ID (first class is 0, second is 1, third is 2, ...etc.)

# In[4]:
# # visualize.py
#************************************************************
#************************************************************
def display_images(images, titles=None, cols=4, cmap=None, norm=None,
                   interpolation=None):
    """Display the given set of images, optionally with titles.
    images: list or array of image tensors in HWC format.
    titles: optional. A list of titles to display with each image.
    cols: number of images per row
    cmap: Optional. Color map to use. For example, "Blues".
    norm: Optional. A Normalize instance to map values to colors.
    interpolation: Optional. Image interpolation to use for display.
    """
    titles = titles if titles is not None else [""] * len(images)
    rows = len(images) // cols + 1
    plt.figure(figsize=(14, 14 * rows // cols))
    i = 1
    for image, title in zip(images, titles):
        plt.subplot(rows, cols, i)
        plt.title(title, fontsize=9)
        plt.axis('off')
        plt.imshow(image.astype(np.uint8), cmap=cmap,
                   norm=norm, interpolation=interpolation)
        i += 1
    plt.show()



def random_colors(N, bright=True):
    """
    Generate random colors.
    To get visually distinct colors, generate them in HSV space then
    convert to RGB.
    """
    brightness = 1.0 if bright else 0.7
    hsv = [(i / N, 1, brightness) for i in range(N)]
    colors = list(map(lambda c: colorsys.hsv_to_rgb(*c), hsv))
    random.shuffle(colors)
    return colors


def apply_mask(image, mask, color, alpha=0.5):
    """Apply the given mask to the image.
    """
    for c in range(3):
        image[:, :, c] = np.where(mask == 1,
                                image[:, :, c] *
                                    0,
                                  image[:, :, c])
    return image


def display_instances(count,image, boxes, masks, class_ids, class_names,
                      scores=None, title="",
                      figsize=(6.4, 4.8), ax=None,
                      show_mask=True, show_bbox=True,
                      colors=None, captions=None):
    """
    boxes: [num_instance, (y1, x1, y2, x2, class_id)] in image coordinates.
    masks: [height, width, num_instances]
    class_ids: [num_instances]
    class_names: list of class names of the dataset
    scores: (optional) confidence scores for each box
    title: (optional) Figure title
    show_mask, show_bbox: To show masks and bounding boxes or not
    figsize: (optional) the size of the image
    colors: (optional) An array or colors to use with each object
    captions: (optional) A list of strings to use as captions for each object
    """
    # Number of instances
    N = boxes.shape[0]
    if not N:
        print("\n*** No instances to display *** \n")
    else:
        assert boxes.shape[0] == masks.shape[-1] == class_ids.shape[0]

    # If no axis is passed, create one and automatically call show()
    auto_show = False
    if not ax:
        _, ax = plt.subplots(1, figsize=figsize)
        auto_show = True

    # Generate random colors
    colors = colors or random_colors(N)

    # Show area outside image boundaries.
    #height, width = image.shape[:2]
    #ax.set_ylim(height + 10, -10)
    #ax.set_xlim(-10, width + 10)
    #ax.axis('off')
    #ax.set_title(title)
    ax.axis('off')

    masked_image = image.astype(np.uint32).copy()
    for i in range(N):
        color = colors[i]

        # Bounding box