outFile.write('process {}\n'.format(' '.join(
[str(x) for x in range(len(config['backgrounds']) + 1)])))
outFile.write('rate {} {}\n'.format(
globalMatrix[signal].values[binNum - 1], ' '.join([
str(x) for x in globalMatrix[
config['backgrounds']].iloc[binNum - 1].values
])))
outFile.write(uncertFile.read())
outFile.close()
uncertFile.close()
if __name__ == "__main__":
args = getArgs()
configData = readConfig(args.config)
print('Creating output folders...')
outputPath = createOutputFolders(configData)
# create and save global matrix
print('Retrieving individual histogram data...')
getIndHistogramsInfo(configData, outputPath)
print("Creating global matrix...")
createGlobalMatrix(configData, outputPath)
print("Creating yields...")
# create and save yields from matrix
createYields(configData, outputPath)
from utils import getArgs, log
import torch
import torch.optim as optim
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
import os
import sys
import logging
from pathlib import Path
# get settings as input arguments
train = True
args, dl_args = getArgs(train=train)
# save/load directories
load_init = next(Path(f"./results/train/{args.load_init}").glob("*.pth"))
save_path = f"./results/train/{args.fname}/"
PATH = f"{save_path}/{args.fname}.pth"
LogPath = f"{save_path}/{args.fname}.txt"
LossPath = f"{save_path}/{args.fname}.npz"
os.makedirs(Path(save_path).absolute(), exist_ok=True)
# set up logging file
logging.basicConfig(filename=LogPath, filemode='w', format="%(asctime)s;%(message)s", level=logging.ERROR)
logger = logging.getLogger()
split_file = f"./Data/VidSequences/LIRIS/LIRIS_Data_{args.frame_num}_indices.npz" if args.dataset_name == "LIRIS" else None
import torch
from dataloaders import PersonDataloader
import segmentation_models_pytorch as smp
from matplotlib import pyplot as plt
from tqdm import tqdm_notebook as tqdm
import numpy as np
from preprocessing import list_files
import time
import cv2 as cv
from torchvision import transforms
from PIL import Image
from utils import getArgs
# load variables from file
args = getArgs('segmentation/args.yaml')
img_dir = args['img_dir']
mask_dir = args['mask_dir']
mean = args['mean']
std = args['std']
ckpt_path = args['ckpt_path']
df = list_files(img_dir)
dataloader = PersonDataloader(df, img_dir, mask_dir, mean, std, 'val', 1, 4)
device = torch.device("cuda")
model = smp.Unet("resnet101",
encoder_weights="imagenet",
classes=1,
activation=None)
model.to(device)
model.eval()
state = torch.load(ckpt_path, map_location=lambda storage, loc: storage)
import keras
import modelCreator
import parseText
import sys
import numpy
from keras.callbacks import ModelCheckpoint
import utils
if __name__ == "__main__":
args = utils.getArgs(sys.argv[1:])
print args
path = args.path
seq_length = args.seq_length
vocab, char_to_num, num_to_char = parseText.getInfo(path, args)
x, y = parseText.createDataset(path, char_to_num, seq_length, args)
models = [
modelCreator.buildModel, modelCreator.buildModelCNN,
modelCreator.buildModelBiDir
]
model = models[args.model_type](vocab, x)
with open(args.save_path + "/model.json", "w") as f:
f.write(model.to_json())
c = [
from svm import SVM
import sys
import utils
if __name__ == "__main__":
dataName = utils.getArgs(sys.argv, '-i')
svm = SVM(dataName)
c_list = [1, 1, 0.05]
g_list = [1, 0.05, 1]
for c, g in zip(c_list, g_list):
svm.rbf_training(c=c, gamma=g)
result = svm.evalMetrics()
choice = True
else:
choice = False
phases = _separatePhaseFiles(phaseMain)
if phases:
Data.update(phases)
return Data
if __name__ == '__main__':
# Input the location where the data files are present
if len(sys.argv) > 1:
mainpath = getArgs()
else:
mainpath = input("[!] Enter path to Working Directory (Press ENTER for default): ")
if mainpath == '':
mainpath = '../'
# Check if path is valid
if not os.path.isdir(mainpath):
print("[-] Working Directory doesn't exist; Exiting")
sys.exit(2)
outputpath = mainpath + "/alphameltsData/output/{}/".format(
dt.now().strftime('%Y-%m-%d_%H-%M')
)
phase_main = mainpath + "Phase_main_tbl.txt"
