ikhlestov

import torch
from torch.autograd import Variable

# new way with `init` module
w = torch.Tensor(3, 5)
torch.nn.init.normal(w)
# work for Variables also
w2 = Variable(w)
torch.nn.init.normal(w2)
# old styled direct access to tensors data attribute

ikhlestov

import json


class TimeLiner:
    _timeline_dict = None

    def update_timeline(self, chrome_trace):
        # convert crome trace to python dict
        chrome_trace_dict = json.loads(chrome_trace)
        # for first run store full trace

ikhlestov

import tensorflow as tf
from tensorflow.python.client import timeline

a = tf.random_normal([2000, 5000])
b = tf.random_normal([5000, 1000])
res = tf.matmul(a, b)

with tf.Session() as sess:
    # add additional options to trace the session execution
    options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)

ikhlestov

class ImagesDataset(torch.utils.data.Dataset):
    pass

class Net(nn.Module):
    pass

model = Net()
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
scheduler = lr_scheduler.StepLR(optimizer, step_size=30, gamma=0.1)
criterion = torch.nn.MSELoss()

ikhlestov

import torch
import torchvision as tv


class ImagesDataset(torch.utils.data.Dataset):
    def __init__(self, df, transform=None,
                 loader=tv.datasets.folder.default_loader):
        self.df = df
        self.transform = transform
        self.loader = loader

ikhlestov

import torch
import numpy as np

numpy_tensor = np.random.randn(10, 20)

# convert numpy array to pytorch array
pytorch_tensor = torch.Tensor(numpy_tensor)
# or another way
pytorch_tensor = torch.from_numpy(numpy_tensor)

ikhlestov

import torch

### tensor example
x_cpu = torch.randn(10, 20)
w_cpu = torch.randn(20, 10)
# direct transfer to the GPU
x_gpu = x_cpu.cuda()
w_gpu = w_cpu.cuda()
result_gpu = x_gpu @ w_gpu
# get back from GPU to CPU

ikhlestov

# scheduler example
from torch.optim import lr_scheduler

optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
scheduler = lr_scheduler.StepLR(optimizer, step_size=30, gamma=0.1)

for epoch in range(100):
    scheduler.step()
    train()
    validate()

ikhlestov

from torch import nn


class Model(nn.Module):
    def __init__(self):
        super().__init__()
        self.feature_extractor = nn.Sequential(
            nn.Conv2d(3, 12, kernel_size=3, padding=1, stride=1),
            nn.Conv2d(12, 24, kernel_size=3, padding=1, stride=1),
        )

ikhlestov

from itertools import combinations, permutations
import numpy as np

def check_line(line):
    start = False
    for i in line:
        if i != 0 and not start:
            start = True
            counter = 0
        elif i == 0 and start: