You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

98 lines
3.1 KiB

import argparse
import json
import os
import pickle
import sys
import sagemaker_containers
import pandas as pd
import numpy as np
import torch
import torch.nn as nn
import torch.optim as optim
from model import LSTMClassifier
from utils import review_to_words, convert_and_pad
def model_fn(model_dir):
"""Load the PyTorch model from the `model_dir` directory."""
print("Loading model.")
# First, load the parameters used to create the model.
model_info = {}
model_info_path = os.path.join(model_dir, 'model_info.pth')
with open(model_info_path, 'rb') as f:
model_info = torch.load(f)
print("model_info: {}".format(model_info))
# Determine the device and construct the model.
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = LSTMClassifier(model_info['embedding_dim'], model_info['hidden_dim'], model_info['vocab_size'])
# Load the store model parameters.
model_path = os.path.join(model_dir, 'model.pth')
with open(model_path, 'rb') as f:
# Load the saved word_dict.
word_dict_path = os.path.join(model_dir, 'word_dict.pkl')
with open(word_dict_path, 'rb') as f:
model.word_dict = pickle.load(f)
print("Done loading model.")
return model
def input_fn(serialized_input_data, content_type):
print('Deserializing the input data.')
if content_type == 'text/plain':
data = serialized_input_data.decode('utf-8')
return data
raise Exception('Requested unsupported ContentType in content_type: ' + content_type)
def output_fn(prediction_output, accept):
print('Serializing the generated output.')
return str(prediction_output)
def predict_fn(input_data, model):
print('Inferring sentiment of input data.')
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
if model.word_dict is None:
raise Exception('Model has not been loaded properly, no word_dict.')
# TODO: Process input_data so that it is ready to be sent to our model.
# You should produce two variables:
# data_X - A sequence of length 500 which represents the converted review
# data_len - The length of the review
input = convert_and_pad(model.word_dict, review_to_words(input_data))
data_X = input[0]
data_len = input[1]
# Using data_X and data_len we construct an appropriate input tensor. Remember
# that our model expects input data of the form 'len, review[500]'.
data_pack = np.hstack((data_len, data_X))
data_pack = data_pack.reshape(1, -1)
data = torch.from_numpy(data_pack)
data =
# Make sure to put the model into evaluation mode
# TODO: Compute the result of applying the model to the input data. The variable `result` should
# be a numpy array which contains a single integer which is either 1 or 0
with torch.no_grad():
output = model.forward(data)
if output >= 0.5:
result =
result =
return result