starovoitovs

Namespace(root='examples/domain_adaptation/image_classification/data/wbc', data='WBC', source=['A', 'M'], target=['W'], train_resizing='crop.resize', val_resizing='crop.resize', resize_size=224, scale=[0.8, 1.0], ratio=[0.8, 1.2], no_hflip=False, norm_mean=(0.485, 0.456, 0.406), norm_std=(0.229, 0.224, 0.225), arch='resnet18', bottleneck_dim=1024, no_pool=False, scratch=False, margin=4.0, trade_off=1.0, batch_size=32, lr=0.004, lr_gamma=0.0002, lr_decay=0.75, momentum=0.9, wd=0.0005, workers=2, epochs=20, iters_per_epoch=1000, print_freq=100, seed=1, per_class_eval=False, log='logs/mdd/WBC_AM2W', phase='train')
/p/home/jusers/starovoitovs1/juwels/projects/tlda/examples/domain_adaptation/image_classification/mdd.py:39: UserWarning: You have chosen to seed training. This will turn on the CUDNN deterministic setting, which can slow down your training considerably! You may see unexpected behavior when restarting from checkpoints.
  warnings.warn('You have chosen to seed training. '
train_source_transforms:  [Comp

starovoitovs

import numpy as np
from sklearn.model_selection import train_test_split
from keras import Model
from keras.layers import Input, LSTM, Conv1D, Conv2D, Reshape, Dense, BatchNormalization, Dropout, concatenate
from keras.callbacks import ModelCheckpoint
from sklearn.preprocessing import OneHotEncoder
from sklearn.metrics import accuracy_score, precision_recall_fscore_support


def build_model(window_size, n_features, depth):

starovoitovs

GIF animation

Run this command in the directory that contains frames/ directory (needs installed imagemagick)

convert -delay 5 -loop 0 -dispose previous frames/*.png animation.gif

starovoitovs

starovoitovs

starovoitovs

starovoitovs

const express = require("express");
const compression = require("compression");
const url = require("url");
const path = require("path");

const PORT = 4200;

// resolve pathname whether it is a static file or rewrite it to index.html (default start page for all pages)
const getFilename = (req) => {
  const pathname = url.parse(req.url).pathname;

starovoitovs

from random import random
from scipy import mean
from math import log, pow

import matplotlib.pyplot as plt


def simulate_single(n):
    sample = [random() - 0.5 for _ in range(n)]

starovoitovs

const xtry = (xtry, xcatch, xfinally) => {
  try {return xtry()} catch (e) {return xcatch && xcatch()} finally {xfinally && xfinally()}
}

// undefined
xtry(() => {throw new Error})

// default
xtry(() => {throw new Error}, () => "default")

starovoitovs

import itertools
import random
import nltk


def shuffled(language, term):

    # while part of speech tag is not a punctuation mark
    while term[1] not in [".", ","]:
        yield term[0]