Alan Bi alankbi

## detecto_demo_0.py
from detecto import core, utils, visualize

image = utils.read_image('fruit.jpg')
model = core.Model()

labels, boxes, scores = model.predict_top(image)
visualize.show_labeled_image(image, boxes, labels)

## detecto_demo_1.py
from detecto.utils import split_video

split_video('video.mp4', 'frames/', step_size=4)

## detecto_demo_2.py
import torch

print(torch.cuda.is_available())

## detecto_demo_3.py
import os
from google.colab import drive

drive.mount('/content/drive')

os.chdir('/content/drive/My Drive/Detecto Tutorial')

!pip install detecto

## detecto_demo_4.py
from detecto import core, utils, visualize

dataset = core.Dataset('images/')
model = core.Model(['alien', 'bat', 'witch'])

model.fit(dataset)

## detecto_demo_5.py
# Specify the path to your image
image = utils.read_image('images/image0.jpg')
predictions = model.predict(image)

# predictions format: (labels, boxes, scores)
labels, boxes, scores = predictions

# ['alien', 'bat', 'bat']
print(labels)

## detecto_demo_6.py
visualize.show_labeled_image(image, boxes, labels)

## detecto_demo_7.py
visualize.detect_video(model, 'input.mp4', 'output.avi')

## detecto_demo_9.py
from torchvision import transforms

augmentations = transforms.Compose([
    transforms.ToPILImage(),
    transforms.RandomHorizontalFlip(0.5),
    transforms.ColorJitter(saturation=0.5),
    transforms.ToTensor(),
    utils.normalize_transform(),
])

## detecto_demo_8.py
model.save('model_weights.pth')

# ... Later ...

model = core.Model.load('model_weights.pth', ['alien', 'bat', 'witch'])
	from detecto import core, utils, visualize

	image = utils.read_image('fruit.jpg')
	model = core.Model()

	labels, boxes, scores = model.predict_top(image)
	visualize.show_labeled_image(image, boxes, labels)
	from detecto.utils import split_video

	split_video('video.mp4', 'frames/', step_size=4)
	import os
	from google.colab import drive

	drive.mount('/content/drive')

	os.chdir('/content/drive/My Drive/Detecto Tutorial')

	!pip install detecto
	from detecto import core, utils, visualize

	dataset = core.Dataset('images/')
	model = core.Model(['alien', 'bat', 'witch'])

	model.fit(dataset)
	# Specify the path to your image
	image = utils.read_image('images/image0.jpg')
	predictions = model.predict(image)

	# predictions format: (labels, boxes, scores)
	labels, boxes, scores = predictions

	# ['alien', 'bat', 'bat']
	print(labels)
	from torchvision import transforms

	augmentations = transforms.Compose([
	transforms.ToPILImage(),
	transforms.RandomHorizontalFlip(0.5),
	transforms.ColorJitter(saturation=0.5),
	transforms.ToTensor(),
	utils.normalize_transform(),
	])
	model.save('model_weights.pth')

	# ... Later ...

	model = core.Model.load('model_weights.pth', ['alien', 'bat', 'witch'])