Btukfyl

I need a help in PyTorch,
Regarding Dataloader, and dataset
Can someone aid/guide me

Here is my query :
I am trying for Image Captioning using https://github.com/yunjey/pytorch-tutorial/tree/master/tutorials/03-advanced/image_captioning.

Here they have used Standard COCO Dataset.

I have dataset as images/ and captions/ directory .

Example

Directory Structure:

images/T001.jpg 

images/T002.jpg 

...

...

captions/T001.txt

captions/T002.txt

....

....

The above is the relation. Caption file has 'n' number of captions in each separate line.

I am able to create a custom Dataset class, in that the complete caption file content is being returned. But I want only one line alone gas to be returned.

Any guidance/suggestion on how to achieving this.

++++++++++++++++++++++++++++++++++++++++++++++++
Here is the class that i have designed:

from __future__ import print_function

import torch

from torchvision import datasets, models, transforms

from torchvision import transforms

from torch.autograd import Variable

from torch.nn.utils.rnn import pack_padded_sequence

import torch.optim as optim

import torch.nn as nn

#from torch import np

import numpy as np

import utils_c

from data_loader_c import get_cust_data_loader 

from models import CNN, RNN

from vocab_custom import Vocabulary, load_vocab

import os



class ImageCaptionDataSet(data.Dataset):

    def __init__(self, path, json, vocab=None, transform=None):

        self.vocab = vocab 

        self.transform = transform

        self.img_dir_path = path  

        self.cap_dir_path = json 

        self.all_imgs_path = glob.glob(os.path.join(self.img_dir_path,'*.jpg'))

        self.all_caps_path = glob.glob(os.path.join(self.cap_dir_path,'*.txt'))

        pass



    def __getitem__(self,index):

        vocab = self.vocab



        img_path = self.all_imgs_path[index]

        img_base_name = os.path.basename(img_path) 

        cap_base_name = img_base_name.replace(".jpg",".txt")

        cap_path  = os.path.join(self.cap_dir_path,cap_base_name)



        caption_all_for_a_image = open(cap_path).read().split("n")



        image = Image.open(img_path)

        image = image.convert('RGB')



        if self.transform != None:

            # apply image preprocessing

            image = self.transform(image)



        #captions_combined = 

        #max_len = 0  

        #for caption in caption_all_for_a_image:

        #    caption_str = str(caption).lower()

        #    tokens = nltk.tokenize.word_tokenize(caption_str)

        #    m = len(tokens) + 2 

        #    if m>max_len:

        #        max_len = m 

        #    caption = torch.Tensor([vocab(vocab.start_token())] +

        #                           [vocab(token) for token in tokens] +

        #                           [vocab(vocab.end_token())])

        #    captions_combined.append(caption) 

        #    #yield image, caption

        #return image,torch.Tensor(captions_combined)



        caption_str = str(caption_all_for_a_image).lower()

        tokens = nltk.tokenize.word_tokenize(caption_str)

        caption = torch.Tensor([vocab(vocab.start_token())] +

                                   [vocab(token) for token in tokens] +

                                   [vocab(vocab.end_token())])



        return image,caption



    def __len__(self):

        return len(self.all_imgs_path)

+++++++++++++++++++++++++++++++++

First, using str() to convert the list of captions into a single string (caption_str = str(caption_all_for_a_image)) is a bad idea:

cap = ['a sentence', 'bla bla bla']

str(cap)

Returns this sting:

"['a sentence', 'bla bla bla']"

Note that [', and ', ' are part of the resulting string!

You can pick one of the captions at random:

import random

...

cap_idx = random.randi(0, len(caption_all_for_a_image)-1)  # pick one at random

caption_str = caption_all_for_a_image[cap_idx].lower()  # actual selection