Python based Project – Learn to Build Image Caption Generator with CNN & LSTM

Project based on Python – Image Caption Generator 

You saw an image and your brain can easily tell what the image is about, but can a computer tell what the image is representing? Computer vision researchers worked on this a lot and they considered it impossible until now! With the advancement in Deep learning techniques, availability of huge datasets and computer power, we can build models that can generate captions for an image.

This is what we are going to implement in this Python based project where we will use deep learning techniques of Convolutional Neural Networks and a type of Recurrent Neural Network (LSTM) together.

Below are some of the Python Data Science projects on which you can work later on:

  1. Fake News Detection Python Project
  2. Parkinson’s Disease Detection Python Project
  3. Color Detection Python Project
  4. Speech Emotion Recognition Python Project
  5. Breast Cancer Classification Python Project
  6. Age and Gender Detection Python Project
  7. Handwritten Digit Recognition Python Project
  8. Chatbot Python Project
  9. Driver Drowsiness Detection Python Project
  10. Traffic Signs Recognition Python Project
  11. Image Caption Generator Python Project

Now, let’s quickly start the Python based project by defining the image caption generator.

Keeping you updated with latest technology trends, Join DataFlair on Telegram

What is Image Caption Generator?

Image caption generator is a task that involves computer vision and natural language processing concepts to recognize the context of an image and describe them in a natural language like English.

Image Caption Generator with CNN – About the Python based Project

The objective of our project is to learn the concepts of a CNN and LSTM model and build a working model of Image caption generator by implementing CNN with LSTM.

In this Python project, we will be implementing the caption generator using CNN (Convolutional Neural Networks) and LSTM (Long short term memory). The image features will be extracted from Xception which is a CNN model trained on the imagenet dataset and then we feed the features into the LSTM model which will be responsible for generating the image captions.

The Dataset of Python based Project

For the image caption generator, we will be using the Flickr_8K dataset. There are also other big datasets like Flickr_30K and MSCOCO dataset but it can take weeks just to train the network so we will be using a small Flickr8k dataset. The advantage of a huge dataset is that we can build better models.

Thanks to Jason Brownlee for providing a direct link to download the dataset (Size: 1GB).

The Flickr_8k_text folder contains file Flickr8k.token which is the main file of our dataset that contains image name and their respective captions separated by newline(“\n”).


This project requires good knowledge of Deep learning, Python, working on Jupyter notebooks, Keras library, Numpy, and Natural language processing.

Make sure you have installed all the following necessary libraries:

  • pip install tensorflow
  • keras
  • pillow
  • numpy
  • tqdm
  • jupyterlab

Image Caption Generator – Python based Project

What is CNN?

Convolutional Neural networks are specialized deep neural networks which can process the data that has input shape like a 2D matrix. Images are easily represented as a 2D matrix and CNN is very useful in working with images.

CNN is basically used for image classifications and identifying if an image is a bird, a plane or Superman, etc.

working of Deep CNN - Python based project

It scans images from left to right and top to bottom to pull out important features from the image and combines the feature to classify images. It can handle the images that have been translated, rotated, scaled and changes in perspective.

Practise the important Python topics

Check out the 240+ Python Tutorials

What is LSTM?

LSTM stands for Long short term memory, they are a type of RNN (recurrent neural network) which is well suited for sequence prediction problems. Based on the previous text, we can predict what the next word will be. It has proven itself effective from the traditional RNN by overcoming the limitations of RNN which had short term memory. LSTM can carry out relevant information throughout the processing of inputs and with a forget gate, it discards non-relevant information.

This is what an LSTM cell looks like –

LSTM Cell Structure - simple python project

Image Caption Generator Model

So, to make our image caption generator model, we will be merging these architectures. It is also called a CNN-RNN model.

  • CNN is used for extracting features from the image. We will use the pre-trained model Xception.
  • LSTM will use the information from CNN to help generate a description of the image.

Model of Image Caption Generator - python based project

Project File Structure

Downloaded from dataset:

  • Flicker8k_Dataset – Dataset folder which contains 8091 images.
  • Flickr_8k_text – Dataset folder which contains text files and captions of images.

The below files will be created by us while making the project.

  • Models – It will contain our trained models.
  • Descriptions.txt – This text file contains all image names and their captions after preprocessing.
  • Features.p – Pickle object that contains an image and their feature vector extracted from the Xception pre-trained CNN model.
  • Tokenizer.p – Contains tokens mapped with an index value.
  • Model.png – Visual representation of dimensions of our project.
  • – Python file for generating a caption of any image.
  • Training_caption_generator.ipynb – Jupyter notebook in which we train and build our image caption generator.

You can download all the files from the link:

Image Caption Generator – Python Project Files

structure - python based project

Want to become a Python expert?

Enroll for the Certified Python Training Course

Building the Python based Project

Let’s start by initializing the jupyter notebook server by typing jupyter lab in the console of your project folder. It will open up the interactive Python notebook where you can run your code. Create a Python3 notebook and name it training_caption_generator.ipynb

jupyter lab - python based project

1. First, we import all the necessary packages

import string
import numpy as np
from PIL import Image
import os
from pickle import dump, load
import numpy as np

from keras.applications.xception import Xception, preprocess_input
from keras.preprocessing.image import load_img, img_to_array
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
from keras.utils import to_categorical
from keras.layers.merge import add
from keras.models import Model, load_model
from keras.layers import Input, Dense, LSTM, Embedding, Dropout

# small library for seeing the progress of loops.
from tqdm import tqdm_notebook as tqdm

2. Getting and performing data cleaning

The main text file which contains all image captions is Flickr8k.token in our Flickr_8k_text folder.

Have a look at the file –

token file - project in python

The format of our file is image and caption separated by a new line (“\n”).

Each image has 5 captions and we can see that #(0 to 5)number is assigned for each caption.

We will define 5 functions:

  • load_doc( filename ) – For loading the document file and reading the contents inside the file into a string.
  • all_img_captions( filename ) – This function will create a descriptions dictionary that maps images with a list of 5 captions. The descriptions dictionary will look something like this:

descriptions - python based project

  • cleaning_text( descriptions) – This function takes all descriptions and performs data cleaning. This is an important step when we work with textual data, according to our goal, we decide what type of cleaning we want to perform on the text. In our case, we will be removing punctuations, converting all text to lowercase and removing words that contain numbers.
    So, a caption like “A man riding on a three-wheeled wheelchair” will be transformed into “man riding on three wheeled wheelchair”
  • text_vocabulary( descriptions ) – This is a simple function that will separate all the unique words and create the vocabulary from all the descriptions.
  • save_descriptions( descriptions, filename ) – This function will create a list of all the descriptions that have been preprocessed and store them into a file. We will create a descriptions.txt file to store all the captions. It will look something like this:

save descriptions - python project

Code :

# Loading a text file into memory
def load_doc(filename):
    # Opening the file as read only
    file = open(filename, 'r')
    text =
    return text

# get all imgs with their captions
def all_img_captions(filename):
    file = load_doc(filename)
    captions = file.split('\n')
    descriptions ={}
    for caption in captions[:-1]:
        img, caption = caption.split('\t')
        if img[:-2] not in descriptions:
            descriptions[img[:-2]] = [ caption ]
    return descriptions

#Data cleaning- lower casing, removing puntuations and words containing numbers
def cleaning_text(captions):
    table = str.maketrans('','',string.punctuation)
    for img,caps in captions.items():
        for i,img_caption in enumerate(caps):

            img_caption.replace("-"," ")
            desc = img_caption.split()

            #converts to lowercase
            desc = [word.lower() for word in desc]
            #remove punctuation from each token
            desc = [word.translate(table) for word in desc]
            #remove hanging 's and a 
            desc = [word for word in desc if(len(word)>1)]
            #remove tokens with numbers in them
            desc = [word for word in desc if(word.isalpha())]
            #convert back to string

            img_caption = ' '.join(desc)
            captions[img][i]= img_caption
    return captions

def text_vocabulary(descriptions):
    # build vocabulary of all unique words
    vocab = set()

    for key in descriptions.keys():
        [vocab.update(d.split()) for d in descriptions[key]]

    return vocab

#All descriptions in one file 
def save_descriptions(descriptions, filename):
    lines = list()
    for key, desc_list in descriptions.items():
        for desc in desc_list:
            lines.append(key + '\t' + desc )
    data = "\n".join(lines)
    file = open(filename,"w")

# Set these path according to project folder in you system
dataset_text = "D:\dataflair projects\Project - Image Caption Generator\Flickr_8k_text"
dataset_images = "D:\dataflair projects\Project - Image Caption Generator\Flicker8k_Dataset"

#we prepare our text data
filename = dataset_text + "/" + "Flickr8k.token.txt"
#loading the file that contains all data
#mapping them into descriptions dictionary img to 5 captions
descriptions = all_img_captions(filename)
print("Length of descriptions =" ,len(descriptions))

#cleaning the descriptions
clean_descriptions = cleaning_text(descriptions)

#building vocabulary 
vocabulary = text_vocabulary(clean_descriptions)
print("Length of vocabulary = ", len(vocabulary))

#saving each description to file 
save_descriptions(clean_descriptions, "descriptions.txt")

3. Extracting the feature vector from all images 

This technique is also called transfer learning, we don’t have to do everything on our own, we use the pre-trained model that have been already trained on large datasets and extract the features from these models and use them for our tasks. We are using the Xception model which has been trained on imagenet dataset that had 1000 different classes to classify. We can directly import this model from the keras.applications . Make sure you are connected to the internet as the weights get automatically downloaded. Since the Xception model was originally built for imagenet, we will do little changes for integrating with our model. One thing to notice is that the Xception model takes 299*299*3 image size as input. We will remove the last classification layer and get the 2048 feature vector.

model = Xception( include_top=False, pooling=’avg’ )

The function extract_features() will extract features for all images and we will map image names with their respective feature array. Then we will dump the features dictionary into a “features.p” pickle file.


def extract_features(directory):
        model = Xception( include_top=False, pooling='avg' )
        features = {}
        for img in tqdm(os.listdir(directory)):
            filename = directory + "/" + img
            image =
            image = image.resize((299,299))
            image = np.expand_dims(image, axis=0)
            #image = preprocess_input(image)
            image = image/127.5
            image = image - 1.0

            feature = model.predict(image)
            features[img] = feature
        return features

#2048 feature vector
features = extract_features(dataset_images)
dump(features, open("features.p","wb"))

extracting features - python based project

This process can take a lot of time depending on your system. I am using an Nvidia 1050 GPU for training purpose so it took me around 7 minutes for performing this task. However, if you are using CPU then this process might take 1-2 hours. You can comment out the code and directly load the features from our pickle file.

features = load(open("features.p","rb"))

4. Loading dataset for Training the model

In our Flickr_8k_test folder, we have Flickr_8k.trainImages.txt file that contains a list of 6000 image names that we will use for training.

For loading the training dataset, we need more functions:

  • load_photos( filename ) – This will load the text file in a string and will return the list of image names.
  • load_clean_descriptions( filename, photos ) – This function will create a dictionary that contains captions for each photo from the list of photos. We also append the <start> and <end> identifier for each caption. We need this so that our LSTM model can identify the starting and ending of the caption.
  • load_features(photos) – This function will give us the dictionary for image names and their feature vector which we have previously extracted from the Xception model.

Code :

#load the data 
def load_photos(filename):
    file = load_doc(filename)
    photos = file.split("\n")[:-1]
    return photos

def load_clean_descriptions(filename, photos): 
    #loading clean_descriptions
    file = load_doc(filename)
    descriptions = {}
    for line in file.split("\n"):

        words = line.split()
        if len(words)<1 :

        image, image_caption = words[0], words[1:]

        if image in photos:
            if image not in descriptions:
                descriptions[image] = []
            desc = '<start> ' + " ".join(image_caption) + ' <end>'

    return descriptions

def load_features(photos):
    #loading all features
    all_features = load(open("features.p","rb"))
    #selecting only needed features
    features = {k:all_features[k] for k in photos}
    return features

filename = dataset_text + "/" + "Flickr_8k.trainImages.txt"

#train = loading_data(filename)
train_imgs = load_photos(filename)
train_descriptions = load_clean_descriptions("descriptions.txt", train_imgs)
train_features = load_features(train_imgs)

5. Tokenizing the vocabulary 

Computers don’t understand English words, for computers, we will have to represent them with numbers. So, we will map each word of the vocabulary with a unique index value. Keras library provides us with the tokenizer function that we will use to create tokens from our vocabulary and save them to a “tokenizer.p” pickle file.


#converting dictionary to clean list of descriptions
def dict_to_list(descriptions):
    all_desc = []
    for key in descriptions.keys():
        [all_desc.append(d) for d in descriptions[key]]
    return all_desc

#creating tokenizer class 
#this will vectorise text corpus
#each integer will represent token in dictionary

from keras.preprocessing.text import Tokenizer

def create_tokenizer(descriptions):
    desc_list = dict_to_list(descriptions)
    tokenizer = Tokenizer()
    return tokenizer

# give each word an index, and store that into tokenizer.p pickle file
tokenizer = create_tokenizer(train_descriptions)
dump(tokenizer, open('tokenizer.p', 'wb'))
vocab_size = len(tokenizer.word_index) + 1

Our vocabulary contains 7577 words.

We calculate the maximum length of the descriptions. This is important for deciding the model structure parameters. Max_length of description is 32.

#calculate maximum length of descriptions
def max_length(descriptions):
    desc_list = dict_to_list(descriptions)
    return max(len(d.split()) for d in desc_list)
max_length = max_length(descriptions)

6. Create Data generator

Let us first see how the input and output of our model will look like. To make this task into a supervised learning task, we have to provide input and output to the model for training. We have to train our model on 6000 images and each image will contain 2048 length feature vector and caption is also represented as numbers. This amount of data for 6000 images is not possible to hold into memory so we will be using a generator method that will yield batches.

The generator will yield the input and output sequence.

For example:

The input to our model is [x1, x2] and the output will be y, where x1 is the 2048 feature vector of that image, x2 is the input text sequence and y is the output text sequence that the model has to predict.

x1(feature vector) x2(Text sequence) y(word to predict)
feature start, two
feature start, two dogs
feature start, two, dogs drink
feature start, two, dogs, drink water
feature start, two, dogs, drink, water end
#create input-output sequence pairs from the image description.

#data generator, used by model.fit_generator()
def data_generator(descriptions, features, tokenizer, max_length):
    while 1:
        for key, description_list in descriptions.items():
            #retrieve photo features
            feature = features[key][0]
            input_image, input_sequence, output_word = create_sequences(tokenizer, max_length, description_list, feature)
            yield [[input_image, input_sequence], output_word]

def create_sequences(tokenizer, max_length, desc_list, feature):
    X1, X2, y = list(), list(), list()
    # walk through each description for the image
    for desc in desc_list:
        # encode the sequence
        seq = tokenizer.texts_to_sequences([desc])[0]
        # split one sequence into multiple X,y pairs
        for i in range(1, len(seq)):
            # split into input and output pair
            in_seq, out_seq = seq[:i], seq[i]
            # pad input sequence
            in_seq = pad_sequences([in_seq], maxlen=max_length)[0]
            # encode output sequence
            out_seq = to_categorical([out_seq], num_classes=vocab_size)[0]
            # store
    return np.array(X1), np.array(X2), np.array(y)

#You can check the shape of the input and output for your model
[a,b],c = next(data_generator(train_descriptions, features, tokenizer, max_length))
a.shape, b.shape, c.shape
#((47, 2048), (47, 32), (47, 7577))

7. Defining the CNN-RNN model

To define the structure of the model, we will be using the Keras Model from Functional API. It will consist of three major parts:

  • Feature Extractor – The feature extracted from the image has a size of 2048, with a dense layer, we will reduce the dimensions to 256 nodes.
  • Sequence Processor – An embedding layer will handle the textual input, followed by the LSTM layer.
  • Decoder – By merging the output from the above two layers, we will process by the dense layer to make the final prediction. The final layer will contain the number of nodes equal to our vocabulary size.

Visual representation of the final model is given below –

final model - python data science project

from keras.utils import plot_model

# define the captioning model
def define_model(vocab_size, max_length):

    # features from the CNN model squeezed from 2048 to 256 nodes
    inputs1 = Input(shape=(2048,))
    fe1 = Dropout(0.5)(inputs1)
    fe2 = Dense(256, activation='relu')(fe1)

    # LSTM sequence model
    inputs2 = Input(shape=(max_length,))
    se1 = Embedding(vocab_size, 256, mask_zero=True)(inputs2)
    se2 = Dropout(0.5)(se1)
    se3 = LSTM(256)(se2)

    # Merging both models
    decoder1 = add([fe2, se3])
    decoder2 = Dense(256, activation='relu')(decoder1)
    outputs = Dense(vocab_size, activation='softmax')(decoder2)

    # tie it together [image, seq] [word]
    model = Model(inputs=[inputs1, inputs2], outputs=outputs)
    model.compile(loss='categorical_crossentropy', optimizer='adam')

    # summarize model
    plot_model(model, to_file='model.png', show_shapes=True)

    return model

8. Training the model

To train the model, we will be using the 6000 training images by generating the input and output sequences in batches and fitting them to the model using model.fit_generator() method. We also save the model to our models folder. This will take some time depending on your system capability.

# train our model
print('Dataset: ', len(train_imgs))
print('Descriptions: train=', len(train_descriptions))
print('Photos: train=', len(train_features))
print('Vocabulary Size:', vocab_size)
print('Description Length: ', max_length)

model = define_model(vocab_size, max_length)
epochs = 10
steps = len(train_descriptions)
# making a directory models to save our models
for i in range(epochs):
    generator = data_generator(train_descriptions, train_features, tokenizer, max_length)
    model.fit_generator(generator, epochs=1, steps_per_epoch= steps, verbose=1)"models/model_" + str(i) + ".h5")

9. Testing the model

The model has been trained, now, we will make a separate file which will load the model and generate predictions. The predictions contain the max length of index values so we will use the same tokenizer.p pickle file to get the words from their index values.


import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
import argparse

ap = argparse.ArgumentParser()
ap.add_argument('-i', '--image', required=True, help="Image Path")
args = vars(ap.parse_args())
img_path = args['image']

def extract_features(filename, model):
            image =

            print("ERROR: Couldn't open image! Make sure the image path and extension is correct")
        image = image.resize((299,299))
        image = np.array(image)
        # for images that has 4 channels, we convert them into 3 channels
        if image.shape[2] == 4: 
            image = image[..., :3]
        image = np.expand_dims(image, axis=0)
        image = image/127.5
        image = image - 1.0
        feature = model.predict(image)
        return feature

def word_for_id(integer, tokenizer):
for word, index in tokenizer.word_index.items():
     if index == integer:
         return word
return None

def generate_desc(model, tokenizer, photo, max_length):
    in_text = 'start'
    for i in range(max_length):
        sequence = tokenizer.texts_to_sequences([in_text])[0]
        sequence = pad_sequences([sequence], maxlen=max_length)
        pred = model.predict([photo,sequence], verbose=0)
        pred = np.argmax(pred)
        word = word_for_id(pred, tokenizer)
        if word is None:
        in_text += ' ' + word
        if word == 'end':
    return in_text

#path = 'Flicker8k_Dataset/111537222_07e56d5a30.jpg'
max_length = 32
tokenizer = load(open("tokenizer.p","rb"))
model = load_model('models/model_9.h5')
xception_model = Xception(include_top=False, pooling="avg")

photo = extract_features(img_path, xception_model)
img =

description = generate_desc(model, tokenizer, photo, max_length)


image caption generator - man standing on rock

image caption generator - girls playing

python project on image caption generator - man on kayak


In this advanced Python project, we have implemented a CNN-RNN model by building an image caption generator. Some key points to note are that our model depends on the data, so, it cannot predict the words that are out of its vocabulary. We used a small dataset consisting of 8000 images. For production-level models, we need to train on datasets larger than 100,000 images which can produce better accuracy models.

Rock the Python interview round

Practise 150+ Python Interview Questions

Hope you enjoyed making this Python based project with us. You can ask your doubts in the comment section below.

68 Responses

  1. Altaf says:

    hey Everything works fine but atlast it’s showing this error its a raw code but I am using tensorflow as a backend—–
    ValueError Traceback (most recent call last)
    13 for i in range(epochs):
    14 generator = data_generator(train_descriptions, train_features, tokenizer, max_length)
    —> 15 model.fit_generator(generator, epochs=1, steps_per_epoch= steps, verbose=1)
    16“models/model_” + str(i) + “.h5”)

    ~/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/ in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
    1295 shuffle=shuffle,
    1296 initial_epoch=initial_epoch,
    -> 1297 steps_name=’steps_per_epoch’)
    1299 def evaluate_generator(self,

    ~/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/ in model_iteration(model, data, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch, mode, batch_size, steps_name, **kwargs)
    264 is_deferred = not model._is_compiled
    –> 265 batch_outs = batch_function(*batch_data)
    266 if not isinstance(batch_outs, list):
    267 batch_outs = [batch_outs]

    ~/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/ in train_on_batch(self, x, y, sample_weight, class_weight, reset_metrics)
    971 outputs = training_v2_utils.train_on_batch(
    972 self, x, y=y, sample_weight=sample_weight,
    –> 973 class_weight=class_weight, reset_metrics=reset_metrics)
    974 outputs = (outputs[‘total_loss’] + outputs[‘output_losses’] +
    975 outputs[‘metrics’])

    ~/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/ in train_on_batch(model, x, y, sample_weight, class_weight, reset_metrics)
    251 x, y, sample_weights = model._standardize_user_data(
    252 x, y, sample_weight=sample_weight, class_weight=class_weight,
    –> 253 extract_tensors_from_dataset=True)
    254 batch_size = array_ops.shape(nest.flatten(x, expand_composites=True)[0])[0]
    255 # If `model._distribution_strategy` is True, then we are in a replica context

    ~/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/ in _standardize_user_data(self, x, y, sample_weight, class_weight, batch_size, check_steps, steps_name, steps, validation_split, shuffle, extract_tensors_from_dataset)
    2470 feed_input_shapes,
    2471 check_batch_axis=False, # Don’t enforce the batch size.
    -> 2472 exception_prefix=’input’)
    2474 # Get typespecs for the input data and sanitize it if necessary.

    ~/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/ in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
    504 elif isinstance(data, (list, tuple)):
    505 if isinstance(data[0], (list, tuple)):
    –> 506 data = [np.asarray(d) for d in data]
    507 elif len(names) == 1 and isinstance(data[0], (float, int)):
    508 data = [np.asarray(data)]

    ~/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/ in (.0)
    504 elif isinstance(data, (list, tuple)):
    505 if isinstance(data[0], (list, tuple)):
    –> 506 data = [np.asarray(d) for d in data]
    507 elif len(names) == 1 and isinstance(data[0], (float, int)):
    508 data = [np.asarray(data)]

    ~/anaconda3/lib/python3.7/site-packages/numpy/core/ in asarray(a, dtype, order)
    537 “””
    –> 538 return array(a, dtype, copy=False, order=order)

    ValueError: could not broadcast input array from shape (47,2048) into shape (47)

  2. Pranshi Garg says:

    PermissionError Traceback (most recent call last)
    1 directory =”D:\Flickr8k_Dataset”
    —-> 2 features = extract_features(directory)
    3 print(‘Extracted Features: %d’ % len(features))
    4 # save to file
    5 dump(features, open(r’features.pkl’, ‘rb’))

    in extract_features(directory)
    13 # load an image from file
    14 filename = directory + ‘/’ + name
    —> 15 image = load_img(filename, target_size=(224, 224))
    16 # convert the image pixels to a numpy array
    17 image = img_to_array(image)

    ~\anaconda3\lib\site-packages\keras_preprocessing\image\ in load_img(path, grayscale, color_mode, target_size, interpolation)
    108 raise ImportError(‘Could not import PIL.Image. ‘
    109 ‘The use of `load_img` requires PIL.’)
    –> 110 img =
    111 if color_mode == ‘grayscale’:
    112 if img.mode != ‘L’:

    ~\anaconda3\lib\site-packages\PIL\ in open(fp, mode)
    2808 if filename:
    -> 2809 fp =, “rb”)
    2810 exclusive_fp = True

    PermissionError: [Errno 13] Permission denied: ‘D:\\Flickr8k_Dataset/Flicker8k_Dataset’

    why is this error showing?can you please help me?

  3. Nandan Kalaria says:

    How to measure the accuracy of the given model/project?


    how do use this program using bleu score for testing the accuracy of image

  5. Sumedh says:

    The captions that are being generated are not accurate enough as shown in the result section of this page. What can i do to improve?

  6. Ojo says:

    This is the error I keep getting. I am running the model on Google Colab.

    FileNotFoundError Traceback (most recent call last)
    in ()
    61 #loading the file that contains all data
    62 #mapping them into descriptions dictionary img to 5 captions
    —> 63 descriptions = all_img_captions(filename)
    64 print(“Length of descriptions =” ,len(descriptions))
    65 #cleaning the descriptions

    1 frames
    in load_doc(filename)
    1 def load_doc(filename):
    2 # Opening the file as read only
    —-> 3 file = open(filename, ‘r’)
    4 text =
    5 file.close()

    FileNotFoundError: [Errno 2] No such file or directory: ‘C:\\Users\\USER\\Documents\\ImageCaptionGenerator\\Flickr_8k_text/Flickr8k.token.txt’

    • Harsh Chaudhary says:

      If you’re running it in Colab you need to upload the files for each session of the runtime, or upload all the files to Google Drive and then mount the drive.

  7. SVKSRJL Priyanka says:

    What do we need to keep instead of directory and filename

  8. Abhinav Kumar says:

    ValueError: No gradients provided for any variable: [’embedding_4/embeddings:0′, ‘dense_12/kernel:0’, ‘dense_12/bias:0’, ‘lstm_4/lstm_cell_4/kernel:0’, ‘lstm_4/lstm_cell_4/recurrent_kernel:0’, ‘lstm_4/lstm_cell_4/bias:0’, ‘dense_13/kernel:0’, ‘dense_13/bias:0’, ‘dense_14/kernel:0’, ‘dense_14/bias:0’].

    • Piyush Bhatia says:

      Bro, Did you found a solution to this error. I am encountering the same problem. If you could give me a heads up about it .

    • siddhant kandge says:

      Hey, do you find a solution to this issue?
      because I am also getting the same error.

      • Aayush Jain says:

        For anyone who is getting this error on google colab, I have a temporary fix for it. Simply downgrade the version of keras and tensorflow. Use pip for this.
        Run the following code:

        pip uninstall keras
        pip install keras == 2.3.1
        pip uninstall tensorflow
        pip install tensorflow == 2.2

        After running the above codes in different cells, simply restart your runtime and your error will be solved.

  9. Shahzad Ahmed says:

    Hello Everyone i am getting this error every time i run the code. Please help

    WARNING:tensorflow:From :14: Model.fit_generator (from is deprecated and will be removed in a future version.
    Instructions for updating:
    Please use, which supports generators.
    ValueError Traceback (most recent call last)
    12 for i in range(epochs):
    13 generator = data_generator(train_descriptions, train_features, tokenizer, max_length)
    —> 14 model.fit_generator(generator, epochs=1, steps_per_epoch= steps, verbose=1)
    15“models/model_” + str(i) + “.h5”)

    ~/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/util/ in new_func(*args, **kwargs)
    322 ‘in a future version’ if date is None else (‘after %s’ % date),
    323 instructions)
    –> 324 return func(*args, **kwargs)
    325 return tf_decorator.make_decorator(
    326 func, new_func, ‘deprecated’,

    ~/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/keras/engine/ in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, validation_freq, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
    1813 “””
    1814 _keras_api_gauge.get_cell(‘fit_generator’).set(True)
    -> 1815 return
    1816 generator,
    1817 steps_per_epoch=steps_per_epoch,

    ~/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/keras/engine/ in _method_wrapper(self, *args, **kwargs)
    106 def _method_wrapper(self, *args, **kwargs):
    107 if not self._in_multi_worker_mode(): # pylint: disable=protected-access
    –> 108 return method(self, *args, **kwargs)
    110 # Running inside `run_distribute_coordinator` already.

    ~/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/keras/engine/ in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
    1096 batch_size=batch_size):
    1097 callbacks.on_train_batch_begin(step)
    -> 1098 tmp_logs = train_function(iterator)
    1099 if data_handler.should_sync:
    1100 context.async_wait()

    ~/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/eager/ in __call__(self, *args, **kwds)
    778 else:
    779 compiler = “nonXla”
    –> 780 result = self._call(*args, **kwds)
    782 new_tracing_count = self._get_tracing_count()

    ~/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/eager/ in _call(self, *args, **kwds)
    821 # This is the first call of __call__, so we have to initialize.
    822 initializers = []
    –> 823 self._initialize(args, kwds, add_initializers_to=initializers)
    824 finally:
    825 # At this point we know that the initialization is complete (or less

    ~/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/eager/ in _initialize(self, args, kwds, add_initializers_to)
    694 self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph)
    695 self._concrete_stateful_fn = (
    –> 696 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
    697 *args, **kwds))

    ~/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/eager/ in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
    2853 args, kwargs = None, None
    2854 with self._lock:
    -> 2855 graph_function, _, _ = self._maybe_define_function(args, kwargs)
    2856 return graph_function

    ~/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/eager/ in _maybe_define_function(self, args, kwargs)
    3212 self._function_cache.missed.add(call_context_key)
    -> 3213 graph_function = self._create_graph_function(args, kwargs)
    3214 self._function_cache.primary[cache_key] = graph_function
    3215 return graph_function, args, kwargs

    ~/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/eager/ in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
    3063 arg_names = base_arg_names + missing_arg_names
    3064 graph_function = ConcreteFunction(
    -> 3065 func_graph_module.func_graph_from_py_func(
    3066 self._name,
    3067 self._python_function,

    ~/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/framework/ in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
    984 _, original_func = tf_decorator.unwrap(python_func)
    –> 986 func_outputs = python_func(*func_args, **func_kwargs)
    988 # invariant: `func_outputs` contains only Tensors, CompositeTensors,

    ~/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/eager/ in wrapped_fn(*args, **kwds)
    598 # __wrapped__ allows AutoGraph to swap in a converted function. We give
    599 # the function a weak reference to itself to avoid a reference cycle.
    –> 600 return weak_wrapped_fn().__wrapped__(*args, **kwds)
    601 weak_wrapped_fn = weakref.ref(wrapped_fn)

    ~/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/framework/ in wrapper(*args, **kwargs)
    971 except Exception as e: # pylint:disable=broad-except
    972 if hasattr(e, “ag_error_metadata”):
    –> 973 raise e.ag_error_metadata.to_exception(e)
    974 else:
    975 raise

    ValueError: in user code:

    /home/shahzad/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/keras/engine/ train_function *
    return step_function(self, iterator)
    /home/shahzad/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/keras/engine/ step_function **
    outputs =, args=(data,))
    /home/shahzad/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/distribute/ run
    return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /home/shahzad/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/distribute/ call_for_each_replica
    return self._call_for_each_replica(fn, args, kwargs)
    /home/shahzad/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/distribute/ _call_for_each_replica
    return fn(*args, **kwargs)
    /home/shahzad/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/keras/engine/ run_step **
    outputs = model.train_step(data)
    /home/shahzad/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/keras/engine/ train_step
    _minimize(self.distribute_strategy, tape, self.optimizer, loss,
    /home/shahzad/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/keras/engine/ _minimize
    gradients = optimizer._aggregate_gradients(zip(gradients, # pylint: disable=protected-access
    /home/shahzad/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/keras/optimizer_v2/ _aggregate_gradients
    filtered_grads_and_vars = _filter_grads(grads_and_vars)
    /home/shahzad/anaconda3/envs/nust1/lib/python3.8/site-packages/tensorflow/python/keras/optimizer_v2/ _filter_grads
    raise ValueError(“No gradients provided for any variable: %s.” %

    ValueError: No gradients provided for any variable: [’embedding/embeddings:0′, ‘dense/kernel:0’, ‘dense/bias:0’, ‘lstm/lstm_cell/kernel:0’, ‘lstm/lstm_cell/recurrent_kernel:0’, ‘lstm/lstm_cell/bias:0’, ‘dense_1/kernel:0’, ‘dense_1/bias:0’, ‘dense_2/kernel:0’, ‘dense_2/bias:0’].

  10. neha choudhary says:

    m also getting the same error do anyone have the solution?

  11. Akash Kapoor says:

    While conducting feature extraction on the dataset,

    features = extract_features(dataset_images)

    The extraction commences, goes on for around 2 hours and the spyder crashes and shuts down abruptly.
    Could anybody please help me with this?
    Thanks in advance!

  12. Sandeep Sharma says:

    During importing of libraries
    I am getting ther error
    Though I have installed the keras .
    Please help to resolve this issue

Leave a Reply

Your email address will not be published. Required fields are marked *

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.