CasiaFan’s gists

CasiaFan / install.sh

Created April 27, 2018 07:36

Ubuntu 16.04 中国地区常用工具安装（包括换国内镜像，NVIDIA显卡驱动，chrome，sogou拼音，ss-qt5， atom编辑器，zsh， YCM ）

	sudo mv /etc/apt/sources.list /etc/apt/sources.list.old
	sudo echo "# deb cdrom:[Ubuntu 16.04 LTS _Xenial Xerus_ - Release amd64 (20160420.1)]/ xenial main restricted
	deb-src http://archive.ubuntu.com/ubuntu xenial main restricted #Added by software-properties
	deb http://mirrors.aliyun.com/ubuntu/ xenial main restricted
	deb-src http://mirrors.aliyun.com/ubuntu/ xenial main restricted multiverse universe #Added by software-properties
	deb http://mirrors.aliyun.com/ubuntu/ xenial-updates main restricted
	deb-src http://mirrors.aliyun.com/ubuntu/ xenial-updates main restricted multiverse universe #Added by software-properties
	deb http://mirrors.aliyun.com/ubuntu/ xenial universe
	deb http://mirrors.aliyun.com/ubuntu/ xenial-updates universe
	deb http://mirrors.aliyun.com/ubuntu/ xenial multiverse

CasiaFan / mat2tensor.cpp

Created May 30, 2018 09:03

Convert cv::Mat into tensorflow::Tensor with uint8 datatype using tensorflow c++ API

	tensorflow::Tensor matToTensor(const cv::Mat &frame){
	int height = mat.rows;
	int width = mat.cols;
	int depth = mat.channels();
	Tensor inputTensor(tensorflow::DT_UINT8, tensorflow::TensorShape({1, height, width, depth}));
	auto inputTensorMapped = inputTensor.tensor<tensorflow::uint8, 4>();

	cv::Mat frame;
	mat.convertTo(frame, CV_8UC3);
	const tensorflow::uint8* source_data = (tensorflow::uint8*) frame.data;

CasiaFan / add_local_light_parallel.py

Last active January 11, 2022 16:48

Add local brightness adjustment in parallel for image augmentation

	import cv2
	import numpy as np
	import random
	from scipy.stats import norm

	def generate_parallel_light_mask(mask_size,
	position=None,
	direction=None,
	max_brightness=255,
	min_brightness=0,

CasiaFan / add_local_light_radically.py

Created June 25, 2018 09:03

Add local brightness adjustment radically for image augmentation

	import cv2
	import numpy as np
	import random
	from scipy.stats import norm

	def generate_spot_light_mask(mask_size,
	position=None,
	max_brightness=255,
	min_brightness=0,
	mode="gaussian",

CasiaFan / tf_hub_image_classification_example.py

Created November 22, 2018 08:01

An example of using tensorflow hub for image classification

	from urllib.request import urlopen
	from io import BytesIO
	from PIL import Image, ImageOps
	import cv2

	def download_and_resize_image(url, filename, new_width=256, new_height=256):
	response = urlopen(url)
	image_data = response.read()
	image_data = BytesIO(image_data)
	pil_image = Image.open(image_data)

CasiaFan / tf_hub_biggan_example.py

Created November 22, 2018 08:03

An example of using tensorflow hub for image generation with BigGAN

	import tensorflow as tf
	import tensorflow_hub as hub
	import cv2
	import numpy as np
	from scipy.stats import truncnorm

	# MODULE_PATH = 'https://tfhub.dev/deepmind/biggan-128/2' # 128x128 BigGAN
	MODULE_PATH = 'https://tfhub.dev/deepmind/biggan-256/2' # 256x256 BigGAN
	# MODULE_PATH = 'https://tfhub.dev/deepmind/biggan-512/2' # 512x512 BigGAN

CasiaFan / asynchronous_caching_video_stream.py

Last active July 17, 2024 22:46

Asynchronous caching and analysis of video stream with opencv and multithreading

	import cv2
	from redis import ConnectionPool, Redis
	import numpy as np
	import json, time
	from multithreading import Thread, Event

	redis_config = {"server": "localhost",
	"passwd": '',
	"port": '6379',
	"db": 0}

CasiaFan / tf_model_flops_measure.py

Created March 28, 2019 03:22

Measure model flops in tensorflow

	import tensorflow as tf

	def load_pb(pb_model):
	with tf.gfile.GFile(pb_model, "rb") as f:
	graph_def = tf.GraphDef()
	graph_def.ParseFromString(f.read())
	with tf.Graph().as_default() as graph:
	tf.import_graph_def(graph_def, name='')
	return graph

CasiaFan / tf_model_post_training_quantization.py

Last active June 14, 2022 08:15

post-training quantization tensorflow model to float16

	import tensorflow as tf
	from tensorflow.core.framework import types_pb2, graph_pb2, attr_value_pb2
	from tensorflow.tools.graph_transforms import TransformGraph
	from google.protobuf import text_format
	import numpy as np

	# object detection api input and output nodes
	input_name = "image_tensor"
	output_names = ["detection_boxes", "detection_classes", "detection_scores", "num_detections"]
	# Const should be float32 in object detection api during nms (see here: https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/non-max-suppression-v4.html)

CasiaFan / ffmpeg_python_with_gpu_acceleration.py

Created September 8, 2019 16:35

Use pipe to read ffmped decoded video frames with NVIDIA GPU hardware acceleration

Zong Fan CasiaFan