Image Captioning（1）

for i in inputs:
    # Step through the sequence one element at a time.
    # after each step, hidden contains the hidden state.
    out, hidden = lstm(i.view(1, 1, -1), hidden)

# the first value returned by LSTM is all of the hidden states throughout
# the sequence. the second is just the most recent hidden state

# Add the extra 2nd dimension
inputs = torch.cat(inputs).view(len(inputs), 1, -1)
hidden = (torch.randn(1, 1, 3), torch.randn(1, 1, 3))  # clean out hidden state
out, hidden = lstm(inputs, hidden)

from workspace_utils import active_session

with active_session():
    # do long-running work here

import os
import sys
sys.path.append('/opt/cocoapi/PythonAPI')
from pycocotools.coco import COCO

# initialize COCO API for instance annotations
dataDir = '/opt/cocoapi'
dataType = 'val2014'
instances_annFile = os.path.join(dataDir, 'annotations/instances_{}.json'.format(dataType))
coco = COCO(instances_annFile)

# initialize COCO API for caption annotations
captions_annFile = os.path.join(dataDir, 'annotations/captions_{}.json'.format(dataType))
coco_caps = COCO(captions_annFile)

# get image ids 
ids = list(coco.anns.keys())

import numpy as np
import skimage.io as io
import matplotlib.pyplot as plt
%matplotlib inline

# pick a random image and obtain the corresponding URL
ann_id = np.random.choice(ids)
img_id = coco.anns[ann_id]['image_id']
img = coco.loadImgs(img_id)[0]
url = img['coco_url']

# print URL and visualize corresponding image
print(url)
I = io.imread(url)
plt.axis('off')
plt.imshow(I)
plt.show()

# load and display captions
annIds = coco_caps.getAnnIds(imgIds=img['id']);
anns = coco_caps.loadAnns(annIds)
coco_caps.showAnns(anns)

import sys
sys.path.append('/opt/cocoapi/PythonAPI')
from pycocotools.coco import COCO
!pip install nltk
import nltk
nltk.download('punkt')
from data_loader import get_loader
from torchvision import transforms

# Define a transform to pre-process the training images.
transform_train = transforms.Compose([ 
    transforms.Resize(256),                          # smaller edge of image resized to 256
    transforms.RandomCrop(224),                      # get 224x224 crop from random location
    transforms.RandomHorizontalFlip(),               # horizontally flip image with probability=0.5
    transforms.ToTensor(),                           # convert the PIL Image to a tensor
    transforms.Normalize((0.485, 0.456, 0.406),      # normalize image for pre-trained model
                         (0.229, 0.224, 0.225))])

# Set the minimum word count threshold.
vocab_threshold = 5

# Specify the batch size.
batch_size = 10

# Obtain the data loader.
data_loader = get_loader(transform=transform_train,
                         mode='train',
                         batch_size=batch_size,
                         vocab_threshold=vocab_threshold,
                         vocab_from_file=False)

# Convert image to tensor and pre-process using transform
image = Image.open(os.path.join(self.img_folder, path)).convert('RGB')
image = self.transform(image)

def __init__(self, transform, mode, batch_size, vocab_threshold, vocab_file, start_word, 
        end_word, unk_word, annotations_file, vocab_from_file, img_folder):
        ...
        self.vocab = Vocabulary(vocab_threshold, vocab_file, start_word,
            end_word, unk_word, annotations_file, vocab_from_file)
        ...

# Convert caption to tensor of word ids.
tokens = nltk.tokenize.word_tokenize(str(caption).lower())   # line 1
caption = []                                                 # line 2
caption.append(self.vocab(self.vocab.start_word))            # line 3
caption.extend([self.vocab(token) for token in tokens])      # line 4
caption.append(self.vocab(self.vocab.end_word))              # line 5
caption = torch.Tensor(caption).long()                       # line 6

sample_caption = 'A person doing a trick on a rail while riding a skateboard.'

import nltk

sample_tokens = nltk.tokenize.word_tokenize(str(sample_caption).lower())
print(sample_tokens)

sample_caption = []

start_word = data_loader.dataset.vocab.start_word
print('Special start word:', start_word)
sample_caption.append(data_loader.dataset.vocab(start_word))
print(sample_caption)

sample_caption.extend([data_loader.dataset.vocab(token) for token in sample_tokens])
print(sample_caption)

end_word = data_loader.dataset.vocab.end_word
print('Special end word:', end_word)

sample_caption.append(data_loader.dataset.vocab(end_word))
print(sample_caption)

import torch

sample_caption = torch.Tensor(sample_caption).long()
print(sample_caption)

[<start>, 'a', 'person', 'doing', 'a', 'trick', 'while', 'riding', 'a', 'skateboard', '.', <end>]

[0, 3, 98, 754, 3, 396, 207, 139, 3, 753, 18, 1]

def __call__(self, word):
    if not word in self.word2idx:
        return self.word2idx[self.unk_word]
    return self.word2idx[word]

# Preview the word2idx dictionary.
dict(list(data_loader.dataset.vocab.word2idx.items())[:10])

# Modify the minimum word count threshold.
vocab_threshold = 4

# Obtain the data loader.
data_loader = get_loader(transform=transform_train,
                         mode='train',
                         batch_size=batch_size,
                         vocab_threshold=vocab_threshold,
                         vocab_from_file=False)
# Print the total number of keys in the word2idx dictionary.
print('Total number of tokens in vocabulary:', len(data_loader.dataset.vocab))

unk_word = data_loader.dataset.vocab.unk_word
print('Special unknown word:', unk_word)

print('All unknown words are mapped to this integer:', data_loader.dataset.vocab(unk_word))

print(data_loader.dataset.vocab('jfkafejw'))
print(data_loader.dataset.vocab('ieowoqjf'))

# Obtain the data loader (from file). Note that it runs much faster than before!
data_loader = get_loader(transform=transform_train,
                         mode='train',
                         batch_size=batch_size,
                         vocab_from_file=True)

from collections import Counter

# Tally the total number of training captions with each length.
counter = Counter(data_loader.dataset.caption_lengths)
lengths = sorted(counter.items(), key=lambda pair: pair[1], reverse=True)
for value, count in lengths:
    print('value: %2d --- count: %5d' % (value, count))

import numpy as np
import torch.utils.data as data

# Randomly sample a caption length, and sample indices with that length.
indices = data_loader.dataset.get_train_indices()
print('sampled indices:', indices)

# Create and assign a batch sampler to retrieve a batch with the sampled indices.
new_sampler = data.sampler.SubsetRandomSampler(indices=indices)
data_loader.batch_sampler.sampler = new_sampler
    
# Obtain the batch.
images, captions = next(iter(data_loader))
    
print('images.shape:', images.shape)
print('captions.shape:', captions.shape)

# (Optional) Uncomment the lines of code below to print the pre-processed images and captions.
# print('images:', images)
# print('captions:', captions)

# Watch for any changes in model.py, and re-load it automatically.
% load_ext autoreload
% autoreload 2

# Import EncoderCNN and DecoderRNN. 
from model import EncoderCNN, DecoderRNN

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Specify the dimensionality of the image embedding.
embed_size = 256

#-#-#-# Do NOT modify the code below this line. #-#-#-#

# Initialize the encoder. (Optional: Add additional arguments if necessary.)
encoder = EncoderCNN(embed_size)

# Move the encoder to GPU if CUDA is available.
encoder.to(device)
    
# Move last batch of images (from Step 2) to GPU if CUDA is available.   
images = images.to(device)

# Pass the images through the encoder.
features = encoder(images)

print('type(features):', type(features))
print('features.shape:', features.shape)

# Check that your encoder satisfies some requirements of the project! :D
assert type(features)==torch.Tensor, "Encoder output needs to be a PyTorch Tensor." 
assert (features.shape[0]==batch_size) & (features.shape[1]==embed_size), "The shape of the encoder output is incorrect."

# Specify the number of features in the hidden state of the RNN decoder.
hidden_size = 512

#-#-#-# Do NOT modify the code below this line. #-#-#-#

# Store the size of the vocabulary.
vocab_size = len(data_loader.dataset.vocab)

# Initialize the decoder.
decoder = DecoderRNN(embed_size, hidden_size, vocab_size)

# Move the decoder to GPU if CUDA is available.
decoder.to(device)
    
# Move last batch of captions (from Step 1) to GPU if CUDA is available 
captions = captions.to(device)

# Pass the encoder output and captions through the decoder.
outputs = decoder(features, captions)

print('type(outputs):', type(outputs))
print('outputs.shape:', outputs.shape)

# Check that your decoder satisfies some requirements of the project! :D
assert type(outputs)==torch.Tensor, "Decoder output needs to be a PyTorch Tensor."
assert (outputs.shape[0]==batch_size) & (outputs.shape[1]==captions.shape[1]) & (outputs.shape[2]==vocab_size), "The shape of the decoder output is incorrect."