Video Classification

accuracy.py

# checking the accuracy of the predicted tags
from sklearn.metrics import accuracy_score
accuracy_score(predict, actual)*100

architecture.py

#defining the model architecture
model = Sequential()
model.add(Dense(1024, activation='relu', input_shape=(25088,)))
model.add(Dropout(0.5))
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(101, activation='softmax'))

architecture_2.py

#defining the model architecture
model = Sequential()
model.add(Dense(1024, activation='relu', input_shape=(25088,)))
model.add(Dropout(0.5))
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(101, activation='softmax'))

base_model.py

# creating the base model of pre-trained VGG16 model
base_model = VGG16(weights='imagenet', include_top=False)

base_model_2.py

base_model = VGG16(weights='imagenet', include_top=False)

checkpoint.py

# defining a function to save the weights of best model
from keras.callbacks import ModelCheckpoint
mcp_save = ModelCheckpoint('weight.hdf5', save_best_only=True, monitor='val_loss', mode='min')

compile.py

# compiling the model
model.compile(loss='categorical_crossentropy',optimizer='Adam',metrics=['accuracy'])

library1.py

import cv2     # for capturing videos
import math   # for mathematical operations
import matplotlib.pyplot as plt    # for plotting the images
%matplotlib inline
import pandas as pd
from keras.preprocessing import image   # for preprocessing the images
import numpy as np    # for mathematical operations
from keras.utils import np_utils
from skimage.transform import resize   # for resizing images
from sklearn.model_selection import train_test_split
from glob import glob
from tqdm import tqdm

library2.py

import keras
from keras.models import Sequential
from keras.applications.vgg16 import VGG16
from keras.layers import Dense, InputLayer, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D, GlobalMaxPooling2D
from keras.preprocessing import image
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from tqdm import tqdm
from sklearn.model_selection import train_test_split

library3.py

from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.preprocessing import image
import numpy as np
import pandas as pd
from tqdm import tqdm
from keras.applications.vgg16 import VGG16
import cv2
import math
import os
from glob import glob
from scipy import stats as s

loading_weights.py

# loading the trained weights
model.load_weights("weights.hdf5")

model_compile_2.py

# compiling the model
model.compile(loss='categorical_crossentropy',optimizer='Adam',metrics=['accuracy'])

normalize.py

# normalizing the pixel values
max = X_train.max()
X_train = X_train/max
X_test = X_test/max

prediction.py

# creating two lists to store predicted and actual tags
predict = []
actual = []

# for loop to extract frames from each test video
for i in tqdm(range(test_videos.shape[0])):
    count = 0
    videoFile = test_videos[i]
    cap = cv2.VideoCapture('UCF/'+videoFile.split(' ')[0].split('/')[1])   # capturing the video from the given path
    frameRate = cap.get(5) #frame rate
    x=1
    # removing all other files from the temp folder
    files = glob('temp/*')
    for f in files:
        os.remove(f)
    while(cap.isOpened()):
        frameId = cap.get(1) #current frame number
        ret, frame = cap.read()
        if (ret != True):
            break
        if (frameId % math.floor(frameRate) == 0):
            # storing the frames of this particular video in temp folder
            filename ='temp/' + "_frame%d.jpg" % count;count+=1
            cv2.imwrite(filename, frame)
    cap.release()
    
    # reading all the frames from temp folder
    images = glob("temp/*.jpg")
    
    prediction_images = []
    for i in range(len(images)):
        img = image.load_img(images[i], target_size=(224,224,3))
        img = image.img_to_array(img)
        img = img/255
        prediction_images.append(img)
        
    # converting all the frames for a test video into numpy array
    prediction_images = np.array(prediction_images)
    # extracting features using pre-trained model
    prediction_images = base_model.predict(prediction_images)
    # converting features in one dimensional array
    prediction_images = prediction_images.reshape(prediction_images.shape[0], 7*7*512)
    # predicting tags for each array
    prediction = model.predict_classes(prediction_images)
    # appending the mode of predictions in predict list to assign the tag to the video
    predict.append(y.columns.values[s.mode(prediction)[0][0]])
    # appending the actual tag of the video
    actual.append(videoFile.split('/')[1].split('_')[1])

read_train_frames.py

# creating an empty list
train_image = []

# for loop to read and store frames
for i in tqdm(range(train.shape[0])):
    # loading the image and keeping the target size as (224,224,3)
    img = image.load_img('train_1/'+train['image'][i], target_size=(224,224,3))
    # converting it to array
    img = image.img_to_array(img)
    # normalizing the pixel value
    img = img/255
    # appending the image to the train_image list
    train_image.append(img)
    
# converting the list to numpy array
X = np.array(train_image)

# shape of the array
X.shape

reshape.py

# reshaping the training as well as validation frames in single dimension
X_train = X_train.reshape(59075, 7*7*512)
X_test = X_test.reshape(14769, 7*7*512)

tags.py

# creating the tags
train = pd.read_csv('UCF/train_new.csv')
y = train['class']
y = pd.get_dummies(y)

target.py

# creating dummies of target variable for train and validation set
y_train = pd.get_dummies(y_train)
y_test = pd.get_dummies(y_test)

test_data.py

# open the .txt file which have names of test videos
f = open("testlist01.txt", "r")
temp = f.read()
videos = temp.split('\n')

# creating a dataframe having video names
test = pd.DataFrame()
test['video_name'] = videos
test = test[:-1]
test.head()

test_data_2.py

# getting the test list
f = open("testlist01.txt", "r")
temp = f.read()
videos = temp.split('\n')

# creating the dataframe
test = pd.DataFrame()
test['video_name'] = videos
test = test[:-1]
test_videos = test['video_name']
test.head()

train_csv.py

# getting the names of all the images
images = glob("train_1/*.jpg")
train_image = []
train_class = []
for i in tqdm(range(len(images))):
    # creating the image name
    train_image.append(images[i].split('/')[1])
    # creating the class of image
    train_class.append(images[i].split('/')[1].split('_')[1])
    
# storing the images and their class in a dataframe
train_data = pd.DataFrame()
train_data['image'] = train_image
train_data['class'] = train_class

# converting the dataframe into csv file 
train_data.to_csv('UCF/train_new.csv',header=True, index=False)

train_data.py

# open the .txt file which have names of training videos
f = open("trainlist01.txt", "r")
temp = f.read()
videos = temp.split('\n')

# creating a dataframe having video names
train = pd.DataFrame()
train['video_name'] = videos
train = train[:-1]
train.head()

train_features.py

# extracting features for training frames
X_train = base_model.predict(X_train)
X_train.shape

train_head.py

train = pd.read_csv('UCF/train_new.csv')
train.head()

train_shape.py

# shape of images
X_train.shape

training.py

# training the model
model.fit(X_train, y_train, epochs=200, validation_data=(X_test, y_test), callbacks=[mcp_save], batch_size=128)

training_frames.py

# storing the frames from training videos
for i in tqdm(range(train.shape[0])):
    count = 0
    videoFile = train['video_name'][i]
    cap = cv2.VideoCapture('UCF/'+videoFile.split(' ')[0].split('/')[1])   # capturing the video from the given path
    frameRate = cap.get(5) #frame rate
    x=1
    while(cap.isOpened()):
        frameId = cap.get(1) #current frame number
        ret, frame = cap.read()
        if (ret != True):
            break
        if (frameId % math.floor(frameRate) == 0):
            # storing the frames in a new folder named train_1
            filename ='train_1/' + videoFile.split('/')[1].split(' ')[0] +"_frame%d.jpg" % count;count+=1
            cv2.imwrite(filename, frame)
    cap.release()

training_tags.py

# creating tags for training videos
train_video_tag = []
for i in range(train.shape[0]):
    train_video_tag.append(train['video_name'][i].split('/')[0])
    
train['tag'] = train_video_tag

# creating tags for test videos
test_video_tag = []
for i in range(test.shape[0]):
    test_video_tag.append(test['video_name'][i].split('/')[0])
    
test['tag'] = test_video_tag

validation_feature.py

# extracting features for validation frames
X_test = base_model.predict(X_test)
X_test.shape

validation_set.py

# separating the target
y = train['class']

# creating the training and validation set
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42, test_size=0.2, stratify = y)

do you have an enviorment.txt for this?

didn't store frame in csv , can you help me please

# storing the frames from training videosfor i in tqdm(range(train.shape[0])): count = 0 videoFile = train['video_name'][i] cap = cv2.VideoCapture('UCF/'+videoFile.split(' ')[0].split('/')[1]) # capturing the video from the given path frameRate = cap.get(5) #frame rate x=1 while(cap.isOpened()): frameId = cap.get(1) #current frame number ret, frame = cap.read() if (ret != True): break if (frameId % math.floor(frameRate) == 0): # storing the frames in a new folder named train_1 filename ='train_1/' + videoFile.split('/')[1].split(' ')[0] +"_frame%d.jpg" % count;count+=1 cv2.imwrite(filename, frame) cap.release()

this code is not working
what is "UCF" in code "cv2.VideoCapture('UCF/'" ?

didn't store frame in csv

didn't store frame in csv
Hi @dipak5053,

I opened an issue a copule hours ago with the same issue of yours, but i deleted as i fixed the problem.

cv2.VideoCapture('UCF/'+videoFile.split(' ')[0].split('/')[1]) this line of code is missing (the full path of the working PC, folder name and a slash), as in the UCF file there are several files. So, you must include the path of each folder, by adding another term of split which is (videoFile.split('/')[0]). Therefore, the final path will be, for instance:
cap = cv2.VideoCapture('C:/Users/PC_name/..../UCF/' + videoFile.split('/')[0] + '/' + videoFile.split('/')[1].split(' ')[0])

Note: The missing terms in the original code are in bold.
hope it helps you,
Thanks,

Hello! what is the data or file in that "UFC" folder?

i also can't work on training_tags.py.
It didn't store the frames in train_1 folder.

i am not able to store the frames in train_1 folder.. Suggest an idea for this

@dipak5053

this code is not working what is "UCF" in code "cv2.VideoCapture('UCF/'" ?

It's called "Videos" earlier, the code needs some troubleshooting to get working. In-process myself.

@Jayamohan12

i am not able to store the frames in train_1 folder.. Suggest an idea for this

You'll need to create the directory