The first part of a SageMaker script for building an MXNet model that counts shapes in an image.

object-counting-sagemaker-script.py

import logging
from pickle import load

import mxnet as mx
import numpy as np
from mxnet import autograd, nd, gluon
from mxnet.gluon import Trainer
from mxnet.gluon.loss import L2Loss
from mxnet.gluon.nn import Conv2D, MaxPool2D, Dropout, Flatten, Dense, Sequential
from mxnet.initializer import Xavier

logging.basicConfig(level=logging.INFO)


def train(hyperparameters, channel_input_dirs, num_gpus):
    batch_size = hyperparameters.get("batch_size", 64)
    epochs = hyperparameters.get("epochs", 3)

    mx.random.seed(42)

    training_dir = channel_input_dirs['training']

    logging.info("Loading data from {}".format(training_dir))

    with open("{}/train/data.p".format(training_dir), "rb") as pickle:
        train_nd = load(pickle)
    with open("{}/validation/data.p".format(training_dir), "rb") as pickle:
        validation_nd = load(pickle)

    train_data = DataLoader(train_nd, batch_size, shuffle=True)
    validation_data = DataLoader(validation_nd, batch_size, shuffle=True)

    net = Sequential()
    with net.name_scope():
        net.add(Conv2D(channels=32, kernel_size=(3, 3),
                       padding=0, activation="relu"))
        net.add(Conv2D(channels=32, kernel_size=(3, 3),
                       padding=0, activation="relu"))
        net.add(MaxPool2D(pool_size=(2, 2)))
        net.add(Dropout(.25))
        net.add(Flatten())
        net.add(Dense(1))

    ctx = mx.gpu() if num_gpus > 0 else mx.cpu()

    net.collect_params().initialize(Xavier(magnitude=2.24), ctx=ctx)
    loss = L2Loss()

    trainer = Trainer(net.collect_params(), optimizer="adam")

    smoothing_constant = .01

    for e in range(epochs):
        moving_loss = 0
        for i, (data, label) in enumerate(train_data):
            data = data.as_in_context(ctx)
            label = label.as_in_context(ctx)
            with autograd.record():
                output = net(data)
                loss_result = loss(output, label)
            loss_result.backward()
            trainer.step(batch_size)

            curr_loss = nd.mean(loss_result).asscalar()
            if (i == 0) and (e == 0):
                moving_loss = curr_loss
            else:
                moving_loss = (1 - smoothing_constant) * moving_loss + \
                              smoothing_constant * curr_loss

        trn_total, trn_detected = calc_perf(net, ctx, train_data)
        val_total, val_detected = calc_perf(net, ctx, validation_data)

        log = "Epoch: {} loss: {:0.4f} perf_test: {:0.2f} perf_val: {:0.2f}" \
            .format(e, moving_loss,
                    trn_detected / trn_total,
                    val_detected / val_total)
        logging.info(log)

    return net


def calc_perf(model, ctx, data_iter):
    raw_predictions = np.array([])
    rounded_predictions = np.array([])
    actual_labels = np.array([])
    for i, (data, label) in enumerate(data_iter):
        data = data.as_in_context(ctx)
        label = label.as_in_context(ctx)
        output = model(data)
        predictions = nd.round(output)
        raw_predictions = np.append(raw_predictions,
                                    output.asnumpy().squeeze())
        rounded_predictions = np.append(rounded_predictions,
                                        predictions.asnumpy().squeeze())
        actual_labels = np.append(actual_labels,
                                  label.asnumpy().squeeze())

    results = np.concatenate((raw_predictions.reshape((-1, 1)),
                              rounded_predictions.reshape((-1, 1)),
                              actual_labels.reshape((-1, 1))), axis=1)
    detected = 0
    i = -1
    for i in range(int(results.size / 3)):
        if results[i][1] == results[i][2]:
            detected += 1
    return i + 1, detected


def save(net, model_dir):
    y = net(mx.sym.var("data"))
    y.save("{}/model.json".format(model_dir))
    net.collect_params().save("{}/model.params".format(model_dir))