ben0it8

FROM nvidia/cuda:10.0-cudnn7-devel-ubuntu18.04

WORKDIR /srv
RUN chmod 777 /tmp

RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    python3.7 python3.7-dev python3-virtualenv

ben0it8

# Set up paths 
ENV RESOURCES_PATH="/resources" \ 
    DATA_PATH="/data" \ 
    LOG_PATH="/logs" 
        
RUN \
    mkdir -p $RESOURCES_PATH && \
    mkdir -p $DATA_PATH && \
    chmod -R a+rwx $DATA_PATH

ben0it8

# Install training requirements
COPY docker-res/requirements.txt "/tmp/"
RUN pip install -r "tmp/requirements.txt"

# Install app requirements
RUN pip install --upgrade uvicorn fastapi

ben0it8

#!/usr/local/bin/python3
import logging, sys, os
logging.basicConfig(stream=sys.stdout,
                    format='%(asctime)s : %(levelname)s : %(message)s',
                    level=logging.INFO)
import torch
import torch.nn.functional as F
from pytorch_transformers import BertTokenizer
from utils import TransformerWithClfHead
from types import SimpleNamespace

ben0it8

# fit the model on `train_dl`"
trainer.run(train_dl, max_epochs=finetuning_config.n_epochs)

# save model weights
torch.save(model.state_dict(), os.path.join(finetuning_config.log_dir, "model_weights.pth"))

# evaluate the model on `test_dl`"
evaluator.run(test_dl)
print(f"Test accuracy: {100*evaluator.state.metrics['accuracy']:.3f}")

ben0it8

from concurrent.futures import ProcessPoolExecutor
from multiprocessing import cpu_count
from itertools import repeat

num_cores = cpu_count()

def process_row(processor, row):
    return processor.process_example((row[1][LABEL_COL], row[1][TEXT_COL]))

def create_dataloader(df: pd.DataFrame,

ben0it8

from ignite.engine import Engine, Events
from ignite.metrics import RunningAverage, Accuracy 
from ignite.handlers import ModelCheckpoint
from ignite.contrib.handlers import CosineAnnealingScheduler, PiecewiseLinear, create_lr_scheduler_with_warmup, ProgressBar
import torch.nn.functional as F
from pytorch_transformers.optimization import AdamW

# Bert optimizer
optimizer = AdamW(model.parameters(), lr=finetuning_config.lr, correct_bias=False) 

ben0it8

import torch
from torch.utils.data import TensorDataset, random_split, DataLoader
import numpy as np
import warnings
from tqdm import tqdm_notebook as tqdm
from typing import Tuple

NUM_MAX_POSITIONS = 256
BATCH_SIZE = 32

ben0it8

import pandas as pd
import re

# text and label column names
TEXT_COL = "text"
LABEL_COL = "label"

def clean_html(text: str):
    "remove html tags and whitespaces"
    cleanr = re.compile('<.*?>')

ben0it8

import os
import requests
import tarfile
from tqdm import tqdm

# path to data 
DATA_DIR = os.path.abspath('./data')

# path to IMDB
IMDB_DIR = os.path.join(DATA_DIR, "imdb5k")