SnowMasaya’s gists

SnowMasaya / deply_deep_stream_Azure_IoT_version3.json

Created December 14, 2020 03:17

deply_deep_stream_Azure_IoT_version3.json

	"$edgeHub": {
	"properties.desired": {
	"schemaVersion": "1.0",
	"routes": {
	"DeepstreamToIoTHub": "FROM /messages/modules/NVIDIADeepStreamSDK/outputs/* INTO $upstream"
	},
	"storeAndForwardConfiguration": {
	"timeToLiveSecs": 7200
	}
	}

SnowMasaya / deply_deep_stream_Azure_IoT_version2.json

Created December 14, 2020 03:15

deply_deep_stream_Azure_IoT_version2.json

	"systemModules": {
	"edgeAgent": {
	"type": "docker",
	"settings": {
	"image": "mcr.microsoft.com/azureiotedge-agent:1.0",
	"createOptions": {}
	}
	},
	"edgeHub": {
	"type": "docker",

SnowMasaya / deply_deep_stream_Azure_IoT_version1.json

Created December 14, 2020 03:12

deply_deep_stream_Azure_IoT_version1.json

	"NVIDIADeepStreamSDK": {
	"version": "1.0",
	"type": "docker",
	"status": "running",
	"restartPolicy": "always",
	"settings": {
	"image": "marketplace.azurecr.io/nvidia/deepstream-iot2-l4t:latest",
	"createOptions": {
	"HostConfig": {
	"runtime": "nvidia"

SnowMasaya / file0.py

Last active February 8, 2018 09:35

時系列データの予測ライブラリ--PyFlux-- ref: https://qiita.com/GushiSnow/items/437dde3293f6d77bfa58

	import numpy as np
	import pandas as pd
	import pyflux as pf
	from datetime import datetime
	import matplotlib.pyplot as plt
	%matplotlib inline

	data = pd.read_csv('https://vincentarelbundock.github.io/Rdatasets/csv/datasets/sunspot.year.csv')
	data.index = data['time'].values

SnowMasaya / file0.txt

Created December 11, 2017 23:27

'Define by Run'型の深層学習フレームワークが自然言語処理に向いている理由 ref: https://qiita.com/GushiSnow/items/aa660c7228b7024076a8

SnowMasaya / file0.txt

Last active December 5, 2017 23:11

高速かつ高性能な分散表現Gloveについて(PyTorch実装) ref: https://qiita.com/GushiSnow/items/e92ac2fea4f8448491ba

J(\theta) = \frac{1}{2}\sum^{W}_{i,j=1}f(P_{ij})(u^{T}_{i}v_j - \log{P_(ij)})^2

SnowMasaya / file0.txt

Last active June 28, 2018 23:23

KerasでTensorboardを使用する際のTips ref: https://qiita.com/GushiSnow/items/6808121ba54fb2e53497


	TensorBoard(log_dir=log_dir,
	histogram_freq=1,
	write_grads=True,
	write_images=1,
	embeddings_freq=1,
	embeddings_layer_names=layer_name,
	embeddings_metadata=metadata_file
	)

SnowMasaya / file0.txt

Last active April 15, 2018 23:52

PyTorchではじめるチャットボット ref: https://qiita.com/GushiSnow/items/f5ed09fd37315357eeae

SnowMasaya / file0.py

Last active October 24, 2018 10:38

PyTorchで始める物体検出:Yolo 9000 Better, Faster, Stronger ref: https://qiita.com/GushiSnow/items/470512e5c04fcdfe7c59

	class Conv2d_BatchNorm(nn.Module):
	def __init__(self, in_channels, out_channels, kernel_size, stride=1, relu=True, same_padding=False):
	super(Conv2d_BatchNorm, self).__init__()
	padding = int((kernel_size - 1) / 2) if same_padding else 0

	self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding=padding, bias=False)
	self.bn = nn.BatchNorm2d(out_channels, momentum=0.01)
	self.relu = nn.LeakyReLU(0.1, inplace=True) if relu else None

	def forward(self, x):

SnowMasaya / file0.txt

Last active June 28, 2018 23:22

KerasによるLSTMの高速化: cuDNNLSTM ref: https://qiita.com/GushiSnow/items/65975667482291329bd5

pip install git+https://github.com/fchollet/keras.git

SnowGushiGit SnowMasaya