mohapatras

import numpy as np
from sklearn.metrics import roc_curve

def sensivity_specifity_cutoff(y_true, y_score):
    '''Find data-driven cut-off for classification
    
    Cut-off is determied using Youden's index defined as sensitivity + specificity - 1.
    
    Parameters
    ----------

NSWG

VMware Workstation Pro 16.x Serials

YA7RA-F6Y46-H889Z-LZMXZ-WF8UA
ZV7HR-4YX17-M80EP-JDMQG-PF0RF
UC3XK-8DD1J-089NP-MYPXT-QGU80
GV100-84W16-M85JP-WXZ7E-ZP2R6
YF5X2-8MW91-4888Y-DNWGC-W68TF
AY1XK-0NG5P-0855Y-K6ZXG-YK0T4

VMware Workstation Player 16.x Serials

mcvarer

#!/bin/bash
## This gist contains instructions about cuda v11.2 and cudnn 8.1 installation in Ubuntu 18.04 for PyTorch

#############################################################################################
##### forked by : https://gist.github.com/Mahedi-61/2a2f1579d4271717d421065168ce6a73 ########
#############################################################################################


### steps ####
# verify the system has a cuda-capable gpu

kmhofmann

Installing the NVIDIA driver, CUDA and cuDNN on Linux (Ubuntu 20.04)

This is a companion piece to my instructions on building TensorFlow from source. In particular, the aim is to install the following pieces of software

• NVIDIA graphics card driver (v450.57)
• CUDA (v11.0.2)
• cuDNN (v8.0.2.39)

on an Ubuntu Linux system, in particular Ubuntu 20.04.

moodoki

import os, argparse

import tensorflow as tf
from tensorflow.python.framework import graph_util

dir = os.path.dirname(os.path.realpath(__file__))

def freeze_graph(model_folder, output_nodes='y_hat', 
                 output_filename='frozen-graph.pb', 
                 rename_outputs=None):

sunsided

import argparse
import os
import sys
from typing import Iterable
import tensorflow as tf


parser = argparse.ArgumentParser()
parser.add_argument('file', type=str, help='The file name of the frozen graph.')
args = parser.parse_args()

joepie91

Don't use VPN services.

No, seriously, don't. You're probably reading this because you've asked what VPN service to use, and this is the answer.

Note: The content in this post does not apply to using VPN for their intended purpose; that is, as a virtual private (internal) network. It only applies to using it as a glorified proxy, which is what every third-party "VPN provider" does.

• A Russian translation of this article can be found here, contributed by Timur Demin.
• A Turkish translation can be found here, contributed by agyild.
• There's also this article about VPN services, which is honestly better written (and has more cat pictures!) than my article.

erogol

FROM: http://benanne.github.io/2015/03/17/plankton.html

Meta-Tricks:
	- Use %10 for validation with STRATIFIED SAMPLING (my mistake)
	- Cyclic Pooling 
	- Leaky ReLU = max(x, a*x) learned a
		- reduces overfitting with a ~= 1/3
	- Orthogonal initialization http://arxiv.org/pdf/1312.6120v3.pdf
	- Use larger weight decay for larger models since otherwise some layers might diverge

zacstewart

import os
import numpy
from pandas import DataFrame
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import Pipeline
from sklearn.cross_validation import KFold
from sklearn.metrics import confusion_matrix, f1_score

NEWLINE = '\n'