Ferhat Culfaz ferhat00

Data Scientist, flaneur, into science & engineering, machine learning and AI.

ferhat00 / extract_json.py

Last active December 26, 2022 22:45

	# _sleepData.json'
	def build_sleep_data(file_name):
	"""
	Take in ...sleepData.json file and output pandas
	Input:
	file_name \| str
	_sleepData file
	Output
	sleep_pd \| pdf
	pandas dataframe of sleep data

ferhat00 / transfer18.py

Created October 31, 2018 08:38

	def load_image(img_path, show=False):

	img = image.load_img(img_path, target_size=(150, 150))
	img_tensor = image.img_to_array(img) # (height, width, channels)
	img_tensor = np.expand_dims(img_tensor, axis=0) # (1, height, width, channels), add a dimension because the model expects this shape: (batch_size, height, width, channels)
	img_tensor /= 255. # imshow expects values in the range [0, 1]

	if show:
	plt.imshow(img_tensor[0])
	plt.axis('off')

ferhat00 / transfer17.py

Created October 31, 2018 08:36


	model.compile(optimizer='Adam',loss='categorical_crossentropy',metrics=['accuracy'])
	# Adam optimizer
	# loss function will be categorical cross entropy
	# evaluation metric will be accuracy

	step_size_train=train_generator.n//train_generator.batch_size
	model.fit_generator(generator=train_generator,
	steps_per_epoch=step_size_train,
	epochs=10)

ferhat00 / transfer16.py

Created October 31, 2018 08:35

	train_datagen=ImageDataGenerator(preprocessing_function=preprocess_input) #included in our dependencies

	train_generator=train_datagen.flow_from_directory('C:/Users/Ferhat/Python Code/Workshop/Tensoorflow transfer learning/downloads',
	target_size=(224,224),
	color_mode='rgb',
	batch_size=32,
	class_mode='categorical',
	shuffle=True)

ferhat00 / transfer15.py

Created October 31, 2018 08:34

	for layer in model.layers:
	layer.trainable=False
	# or if we want to set the first 20 layers of the network to be non-trainable
	for layer in model.layers[:20]:
	layer.trainable=False
	for layer in model.layers[20:]:
	layer.trainable=True

ferhat00 / transfer14.py

Created October 31, 2018 08:32

	for i,layer in enumerate(model.layers):
	print(i,layer.name)

ferhat00 / transfer13.py

Created October 31, 2018 08:31

	model=Model(inputs=base_model.input,outputs=preds)
	#specify the inputs
	#specify the outputs
	#now a model has been created based on our architecture

ferhat00 / transfer12.py

Created October 31, 2018 08:30

	base_model=MobileNet(weights='imagenet',include_top=False) #imports the mobilenet model and discards the last 1000 neuron layer.

	x=base_model.output
	x=GlobalAveragePooling2D()(x)
	x=Dense(1024,activation='relu')(x) #we add dense layers so that the model can learn more complex functions and classify for better results.
	x=Dense(1024,activation='relu')(x) #dense layer 2
	x=Dense(512,activation='relu')(x) #dense layer 3
	preds=Dense(2,activation='softmax')(x) #final layer with softmax activation

ferhat00 / transfer11.py

Created October 31, 2018 08:29

	!pip install google_images_download
	from google_images_download import google_images_download
	response = google_images_download.googleimagesdownload()
	arguments = {"keywords":"blue tit","limit":100,"print_urls":False,"format":"jpg", "size":">400*300"}
	paths = response.download(arguments)
	arguments = {"keywords":"crow","limit":100,"print_urls":False, "format":"jpg", "size":">400*300"}
	paths = response.download(arguments)

ferhat00 / transfer10.py

Created October 31, 2018 08:25

	preprocessed_image = prepare_image('blue_tit.jpg')
	predictions = mobile.predict(preprocessed_image)
	results = imagenet_utils.decode_predictions(predictions)
	results