davidnvq

#!/bin/bash

# Script for installing tmux on systems where you don't have root access.
# tmux will be installed in $HOME/local/bin.
# It's assumed that wget and a C/C++ compiler are installed.

# exit on error
set -e

TMUX_VERSION=1.8

davidnvq

import torch
import torch.nn as nn

nn.Dropout(p=0.0).eval()(torch.ones(4, 10))
"""Output
tensor([[1., 1., 1., 1., 1., 1., 1., 1., 1., 1.],
        [1., 1., 1., 1., 1., 1., 1., 1., 1., 1.],
        [1., 1., 1., 1., 1., 1., 1., 1., 1., 1.],
        [1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]])
"""

davidnvq

class Foo():
    
    def __init__(self, a, b, c, d=0):
        
        self.a = a
        self.b = b
        self.c = c
        self.d = d

params = {

davidnvq

import torch

print("HELLO")

x = torch.randn(100, 100).cuda()

def print_hello(name):
  print("Hello", name)
  print("Very nice to meet you")

davidnvq

# https://github.com/pytorch/examples/blob/master/imagenet/main.py#L392-L396

def adjust_learning_rate(optimizer, epoch, args):
    """Sets the learning rate to the initial LR decayed by 10 every 30 epochs"""
    lr = args.lr * (0.1 ** (epoch // 30))
    for param_group in optimizer.param_groups:
        param_group['lr'] = lr

        # Create a learning rate adjustment function that divides the learning rate by 10 every 30 epochs
def adjust_learning_rate(epoch):

davidnvq

import torch
from torch import nn
from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence


class DynamicRNN(nn.Module):
	"""
	The wrapper version of recurrent modules including RNN, LSTM
	that support packed sequence batch.
	"""

davidnvq

import argparse

	parser.add_argument(
			"--list",
			nargs="+",
			help="This will accept the list of values or a single value",
			default=['1']
			)

  args = parser.parse_args()

davidnvq

"""
Reference: https://pytorch.org/docs/master/torchvision/models.html
"""

from urllib.request import urlopen
from PIL import Image

from torchvision import transforms

# Read an example image

davidnvq

import time

import torch
import torch.nn as nn


device = 'cuda:0'
batch_size = 10
channels = 64
h, w = 128, 128

davidnvq

import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F


torch.manual_seed(2809)