ResidentMario

echo "Installing base packages"
conda install \
-c conda-forge \
-y \
-q \
dask-yarn>=0.7.0 \
pyarrow \
s3fs \
conda-pack \
tornado=5 \

ResidentMario

import argparse
import torch.multiprocessing as mp
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
import torch.utils.data.distributed
import horovod.torch as hvd

# Training settings

ResidentMario

from rich.console import Console
from rich.table import Column, Table

console = Console()

table = Table(show_header=True, header_style="bold magenta")
table.add_column("Model")
table.add_column("GPU", justify="right")
table.add_column("💾 (w/o MP)", justify="right")
table.add_column("💾 (w/ MP)", justify="right")

ResidentMario

#!/usr/bin/env python
import os
import torch
import torch.distributed as dist
from torch.multiprocessing import Process

def run(rank, size):
    """ Distributed function to be implemented later. """
    # collective ops are performed against groups
    group = dist.new_group([0, 1, 2])

ResidentMario

# NEW additional imports
import torch.distributed as dist
import torch.multiprocessing as mp
from torch.nn.parallel import DistributedDataParallel
from torch.utils.data.distributed import DistributedSampler

# NEW init_process method
def init_process(rank, size, backend='gloo'):
    """ Initialize the distributed environment. """
    os.environ['MASTER_ADDR'] = '127.0.0.1'

ResidentMario

self.train()
X = torch.tensor(X, dtype=torch.float32)
y = torch.tensor(y, dtype=torch.float32)

optimizer = torch.optim.Adam(self.parameters(), lr=self.max_lr)
scheduler = torch.optim.lr_scheduler.OneCycleLR(
    optimizer, self.max_lr,
    cycle_momentum=False,
    epochs=self.n_epochs,
    steps_per_epoch=int(np.ceil(len(X) / self.batch_size)),

ResidentMario

import pandas as pd
from pathlib import Path

path = Path('rossmann')
train_df = pd.read_pickle('/mnt/rossman-fastai-sample/train_clean').drop(['index', 'Date'], axis='columns')
test_df = pd.read_pickle('/mnt/rossman-fastai-sample/test_clean')

from sklearn.preprocessing import OneHotEncoder, LabelEncoder
from sklearn.pipeline import FeatureUnion, Pipeline
import numpy as np

ResidentMario

NAME                                                               READY   STATUS    RESTARTS   AGE
pod/admission-webhook-bootstrap-stateful-set-0                     1/1     Running   0          26m
pod/admission-webhook-deployment-78969d856-dgxrz                   1/1     Running   0          25m
pod/application-controller-stateful-set-0                          1/1     Running   0          26m
pod/argo-ui-55b859f7d7-9m7g7                                       1/1     Running   0          26m
pod/basic-auth-7489dc8bd4-scsg4                                    1/1     Running   0          26m
pod/basic-auth-login-5f77644b79-s8drd                              1/1     Running   0          26m
pod/centraldashboard-7f68f6bf7b-5g9xc                              1/1     Running   0          26m
pod/cloud-endpoints-controller-77756cbf84-4pkkr                    1/1     Running   0          26m
pod/jupyter-web-app-deployment-5b56748d57-q4q7g                    1/1     Running   0          26m

ResidentMario

This gist contains my development environment settings. The idea is that I should be able to reproduce my development environment from scratch.

ResidentMario