wolterlw

import numpy as np

def get_thresholded_indices(inp_array, threshold=10, radius=30):
    y = lambda x: inp_array[x]

    population = np.random.randint(0,len(inp_array),len(inp_array))

    pop_size = len(population)-1
    for delta in range(7,0,-1):
        for i in range(100):

wolterlw

from IPython.core.display import display, HTML
display(HTML("<style>.container { width:100% !important; }</style>"))

wolterlw

/* 
parameter JSON
{
  "num_layers": 5,
  "min_scale": 0.1171875,
  "max_scale": 0.75,
  "input_size_height": 256,
  "input_size_width": 256,
  "anchor_offset_x": 0.5,
  "anchor_offset_y": 0.5,

wolterlw

diff --git a/tensorflow/lite/kernels/internal/BUILD b/tensorflow/lite/kernels/internal/BUILD
index 4be3226938..6bc39a7194 100644
--- a/tensorflow/lite/kernels/internal/BUILD
+++ b/tensorflow/lite/kernels/internal/BUILD
@@ -37,6 +37,18 @@ NEON_FLAGS_IF_APPLICABLE = select({
     ],
 })
 
+cc_library(
+    name = "common",

wolterlw

#!/bin/bash
# 1. create a bot using @BotFather
# 2. create a public channel, add the bot as it's administrator
# 3. fill in the required information below
# 4. do a test run. In the response there will be a chat_id, which is a bunch of numbers
#    now it's possible to make the channel private and use chat_id instead of the public name

bot_token=#YOUR_BOT_TOKEN
chat_id=#UR_CHANNEL_ID
api_call="https://api.telegram.org/bot$bot_token/sendMessage"

wolterlw

#to match the word between foo and bar use:
$ grep -oP '(?<=foo )\w+(?= bar)' test.txt

wolterlw

import torch.nn as nn

def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=1, bias=False)

def conv1x1(in_planes, out_planes, stride=1):
    """1x1 convolution"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)

wolterlw

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision.datasets.mnist import MNIST
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
import visdom
from collections import OrderedDict

class LeNet5(nn.Module):

wolterlw

"""
Sublime shortcuts for jupyter notebook
"""

from jupyter_core.paths import jupyter_config_dir
import os
custom_js_path = os.path.join(jupyter_config_dir(), 'custom', 'custom.js')
custom_path = os.path.join(jupyter_config_dir(), 'custom')

wolterlw

class CustomDataset(torch.utils.data.Dataset):
    def __init__(self):
        # TODO
        # 1. Initialize file paths or a list of file names. 
        pass
    def __getitem__(self, index):
        # TODO
        # 1. Read one data from file (e.g. using numpy.fromfile, PIL.Image.open).
        # 2. Preprocess the data (e.g. torchvision.Transform).
        # 3. Return a data pair (e.g. image and label).