# Mounting google drive
from google.colab import drive
root_dir = ('/content/drive')
drive.mount(root_dir, force_remount=True)
# For running inference on the TF-Hub module.
import tensorflow as tf
import tensorflow_hub as hub
# For downloading the image.
import matplotlib.pyplot as plt
import tempfile
from six.moves.urllib.request import urlopen
from six import BytesIO
# For drawing onto the image.
import numpy as np
from PIL import Image
from PIL import ImageColor
from PIL import ImageDraw
from PIL import ImageFont
from PIL import ImageOps
# For measuring the inference time.
import time
# Print Tensorflow version
print(tf.__version__)
# Check available GPU devices.
print("The following GPU devices are available: %s" % tf.test.gpu_device_name())
# Functions for downloading images and for visualization
def display_image(image):
fig = plt.figure(figsize=(20, 15))
plt.grid(False)
plt.imshow(image)
def download_and_resize_image(url, new_width=256, new_height=256,
display=False):
_, filename = tempfile.mkstemp(suffix=".jpg")
response = urlopen(url)
image_data = response.read()
image_data = BytesIO(image_data)
pil_image = Image.open(image_data)
pil_image = ImageOps.fit(pil_image, (new_width, new_height), Image.ANTIALIAS)
pil_image_rgb = pil_image.convert("RGB")
pil_image_rgb.save(filename, format="JPEG", quality=90)
print("Image downloaded to %s." % filename)
if display:
display_image(pil_image)
return filename
def draw_bounding_box_on_image(image,
ymin,
xmin,
ymax,
xmax,
color,
font,
thickness=4,
display_str_list=()):
"""Adds a bounding box to an image."""
draw = ImageDraw.Draw(image)
im_width, im_height = image.size
(left, right, top, bottom) = (xmin * im_width, xmax * im_width,
ymin * im_height, ymax * im_height)
draw.line([(left, top), (left, bottom), (right, bottom), (right, top),
(left, top)],
width=thickness,
fill=color)
# If the total height of the display strings added to the top of the bounding
# box exceeds the top of the image, stack the strings below the bounding box
# instead of above.
display_str_heights = [font.getsize(ds)[1] for ds in display_str_list]
# Each display_str has a top and bottom margin of 0.05x.
total_display_str_height = (1 + 2 * 0.05) * sum(display_str_heights)
if top > total_display_str_height:
text_bottom = top
else:
text_bottom = top + total_display_str_height
# Reverse list and print from bottom to top.
for display_str in display_str_list[::-1]:
text_width, text_height = font.getsize(display_str)
margin = np.ceil(0.05 * text_height)
draw.rectangle([(left, text_bottom - text_height - 2 * margin),
(left + text_width, text_bottom)],
fill=color)
draw.text((left + margin, text_bottom - text_height - margin),
display_str,
fill="black",
font=font)
text_bottom -= text_height - 2 * margin
def draw_boxes(image, boxes, class_names, scores, max_boxes=10, min_score=0.1):
"""Overlay labeled boxes on an image with formatted scores and label names."""
colors = list(ImageColor.colormap.values())
try:
font = ImageFont.truetype("/usr/share/fonts/truetype/liberation/LiberationSansNarrow-Regular.ttf",25)
except IOError:
print("Font not found, using default font.")
font = ImageFont.load_default()
for i in range(min(boxes.shape[0], max_boxes)):
if scores[i] >= min_score:
ymin, xmin, ymax, xmax = tuple(boxes[i])
display_str = "{}: {}%".format(class_names[i].decode("ascii"),
int(100 * scores[i]))
color = colors[hash(class_names[i]) % len(colors)]
image_pil = Image.fromarray(np.uint8(image)).convert("RGB")
draw_bounding_box_on_image(
image_pil,
ymin,
xmin,
ymax,
xmax,
color,
font,
display_str_list=[display_str])
np.copyto(image, np.array(image_pil))
return image
# Load a public image from Open Images v4, save locally, and display.
image_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/8/85/Danza_del_pac%C3%ADfico.jpg/1280px-Danza_del_pac%C3%ADfico.jpg"
downloaded_image_path = download_and_resize_image(image_url, 1280, 856, True)
# Pick an object detection module and apply on the downloaded image. Modules:
# FasterRCNN+InceptionResNet V2: high accuracy,
# ssd+mobilenet V2: small and fast.
module_handle = "https://tfhub.dev/google/faster_rcnn/openimages_v4/inception_resnet_v2/1"
detector = hub.load(module_handle).signatures['default']
def load_img(path):
img = tf.io.read_file(path)
img = tf.image.decode_jpeg(img, channels=3)
return img
def run_detector(detector, path):
img = load_img(path)
converted_img = tf.image.convert_image_dtype(img, tf.float32)[tf.newaxis, ...]
start_time = time.time()
result = detector(converted_img)
end_time = time.time()
result = {key:value.numpy() for key,value in result.items()}
print("Found %d objects." % len(result["detection_scores"]))
print("Inference time: ", end_time-start_time)
image_with_boxes = draw_boxes(
img.numpy(), result["detection_boxes"],
result["detection_class_entities"], result["detection_scores"])
display_image(image_with_boxes)
# Run model
run_detector(detector, downloaded_image_path)
#Links to my images
#https://upload.wikimedia.org/wikipedia/commons/thumb/8/85/Danza_del_pac%C3%ADfico.jpg/1280px-Danza_del_pac%C3%ADfico.jpg
#https://upload.wikimedia.org/wikipedia/commons/thumb/1/12/Arts_and_Feminism_Campaign_2023_Editathon_in_Tamale%2C_Ghana.jpg/1280px-Arts_and_Feminism_Campaign_2023_Editathon_in_Tamale%2C_Ghana.jpg
# https://digitalhub.fifa.com/transform/12b045c4-66a8-4519-af76-a57f77a43704/Croatia-v-Morocco-3rd-Place-FIFA-World-Cup-Qatar-2022?io=transform:fill,aspectratio:16x9,width:1400&quality=100&io=overlay:box,color:000f2c,opacity:15
# https://cloudinary.fifa.com/m/4af7e1fc389e50b5/webimage-FC-Bayern-Munchen-v-Raja-Casablanca-FIFA-Club-World-Cup-Final-21-Dec-2013.png?tx=c_fill,g_auto,q_auto:best,w_746,h_485
# https://images.unsplash.com/photo-1618773928121-c32242e63f39?ixlib=rb-4.0.3&ixid=MnwxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8&auto=format&fit=crop&w=1470&q=80
#https://upload.wikimedia.org/wikipedia/commons/1/1b/The_Coleoptera_of_the_British_islands_%28Plate_125%29_%288592917784%29.jpg
Week11_Task