Extract thumbnails

.gitignore

@@ -0,0 +1,5 @@
+config.py
+api_key.txt
+*.npy
+*.py.save
+

.keras/keras.json

@@ -0,0 +1,6 @@
+{
+    "floatx": "float32",
+    "epsilon": 1e-07,
+    "backend": "tensorflow",
+    "image_data_format": "channels_last"
+}

README.md

@@ -1 +1,17 @@
-# thumbnailr
+# thumbnailr
+
+
+The codes uploaded so far :
+
+1) yvue.py ( youtube video url extracter)
+
+This video takes in input the csv file of channel ids and gives out the thumbnails
+of the top videos for each YouTube Channel
+
+The csv file is also added named channel_list_top_500.csv
+
+2) scrap_sb : This code extracts the channel ids from the social blade site.
+This code is not inculcated in the main code so that the choice of videos for
+good thumbnails can be different and so we provide the downloaded dataset from
+the same code.
+

config.py

@@ -0,0 +1 @@
+api_key = 'AIzaSyBrg-tiQY2DcHZ8ixXm6ZqEPd1R8aEGrGE'

feedback_loop.py

@@ -0,0 +1,71 @@
+import cv2
+import os
+from PIL import Image
+import subprocess
+
+import numpy as np
+import requests
+#import urllib2
+
+import shutil
+from uuid import uuid4
+
+def create_directory(directory):
+    """
+        :param directory: folder path which needs to be created if not already present
+        :return: nothing
+    """
+    if not os.path.exists(directory):
+        os.makedirs(directory)
+
+def get_filecount(path_to_directory):
+    if os.path.exists(path_to_directory):
+        path,dirs,files = os.walk(path_to_directory).__next__()
+        file_count = len(files)
+        return file_count
+    else :
+        print("path does not exist")
+        return 0
+
+
+path = '/home/akhil/thumbnailr/overall/'   # change the path to directory
+if not os.path.isdir(path):
+    os.makedirs(path)
+
+# files = os.listdir(path)
+count = get_filecount(path)
+print(count)
+
+path1 = './' + 'folder1'
+create_directory(path1)
+path2 = './' + 'folder2'
+create_directory(path2)
+path3 = './' + 'folder3'
+create_directory(path3)
+path4 = './' + 'folder4'
+create_directory(path4)
+path5 = './' + 'folder5'
+create_directory(path5)
+path6 = './' + 'folder6'
+create_directory(path6)
+
+def feedback_loop():
+
+
+    path = './overall/'
+    create_directory(path)
+    for i in range(5):
+        print ("i = ",i)
+        image = Image.open(path + str(i + 1) + '.jpg',"r")
+        image.show()
+        folder = input()
+        cv2.imwrite(os.path.join(path + '/folder' + str(folder) + './'+ str (i + 1) + ".jpg"), image)
+        os.popen('killall display')
+        image.close()
+        i +=1
+
+feedback_loop()
+
+
+
+

feedback_loop_edit.py

@@ -0,0 +1,71 @@
+import cv2
+import os
+from PIL import Image
+import subprocess
+import numpy as np
+import requests
+#import urllib2
+
+import shutil
+from uuid import uuid4
+
+def create_directory(directory):
+    """
+        :param directory: folder path which needs to be created if not already present
+        :return: nothing
+    """
+    if not os.path.exists(directory):
+        os.makedirs(directory)
+
+def get_filecount(path_to_directory):
+    if os.path.exists(path_to_directory):
+        path,dirs,files = os.walk(path_to_directory).__next__()
+        file_count = len(files)
+        return file_count
+    else :
+        print("path does not exist")
+        return 0
+
+
+path = '/home/karthik/thumbnailr/overall/'   # change the path to directory
+if not os.path.isdir(path):
+    os.makedirs(path)
+
+files = os.listdir(path)
+count = get_filecount(path)
+print(count)
+
+path1 = './' + 'folder1'
+create_directory(path1)
+path2 = './' + 'folder2'
+create_directory(path2)
+path3 = './' + 'folder3'
+create_directory(path3)
+path4 = './' + 'folder4'
+create_directory(path4)
+path5 = './' + 'folder5'
+create_directory(path5)
+path6 = './' + 'folder6'
+create_directory(path6)
+
+
+def feedback_loop():
+
+    for i in range(5):
+        print ("i = ",i)
+        image = Image.open(path + str(i + 1) + '.jpg',"r")
+        image.show()
+        folder = input()
+        shutil.copy2(path + str(i + 1) + '.jpg','./'+ 'folder'+folder)
+        os.popen('killall display')
+        image.close()
+        i +=1
+
+
+
+
+feedback_loop()
+
+
+
+

first_model.py

@@ -0,0 +1,116 @@
+'''This script goes along the blog post
+"Building powerful image classification models using very little data"
+from blog.keras.io.
+It uses data that can be downloaded at:
+https://www.kaggle.com/c/dogs-vs-cats/data
+In our setup, we:
+- created a data/ folder
+- created train/ and validation/ subfolders inside data/
+- created cats/ and dogs/ subfolders inside train/ and validation/
+- put the cat pictures index 0-999 in data/train/cats
+- put the cat pictures index 1000-1400 in data/validation/cats
+- put the dogs pictures index 12500-13499 in data/train/dogs
+- put the dog pictures index 13500-13900 in data/validation/dogs
+So that we have 1000 training examples for each class, and 400 validation examples for each class.
+In summary, this is our directory structure:
+```
+data/
+    train/
+        dogs/
+            dog001.jpg
+            dog002.jpg
+            ...
+        cats/
+            cat001.jpg
+            cat002.jpg
+            ...
+    validation/
+        dogs/
+            dog001.jpg
+            dog002.jpg
+            ...
+        cats/
+            cat001.jpg
+            cat002.jpg
+            ...
+```
+'''
+from PIL import Image
+from keras.preprocessing.image import ImageDataGenerator
+from keras.models import Sequential
+from keras.layers import Conv2D, MaxPooling2D
+from keras.layers import Activation, Dropout, Flatten, Dense
+from keras import backend as K
+
+
+# dimensions of our images.
+img_width, img_height = 150, 150
+
+train_data_dir = '/home/rahul/th_data/train'
+validation_data_dir = '/home/rahul/th_data/validation'
+nb_train_samples = 2780
+nb_validation_samples = 740
+epochs = 16
+batch_size = 10
+
+if K.image_data_format() == 'channels_first':
+    input_shape = (3, img_width, img_height)
+else:
+    input_shape = (img_width, img_height, 3)
+
+model = Sequential()
+model.add(Conv2D(32, (3, 3), input_shape=input_shape))
+model.add(Activation('relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+
+model.add(Conv2D(32, (3, 3)))
+model.add(Activation('relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+
+model.add(Conv2D(64, (3, 3)))
+model.add(Activation('relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+
+model.add(Flatten())
+model.add(Dense(64))
+model.add(Activation('relu'))
+model.add(Dropout(0.5))
+model.add(Dense(1))
+model.add(Activation('sigmoid'))
+
+model.compile(loss='binary_crossentropy',
+              optimizer='rmsprop',
+              metrics=['accuracy'])
+
+# this is the augmentation configuration we will use for training
+train_datagen = ImageDataGenerator(
+    rescale=1. / 255,
+    shear_range=0.2,
+    zoom_range=0.2,
+    horizontal_flip=True)
+
+# this is the augmentation configuration we will use for testing:
+# only rescaling
+test_datagen = ImageDataGenerator(rescale=1. / 255)
+
+train_generator = train_datagen.flow_from_directory(
+    train_data_dir,
+    target_size=(img_width, img_height),
+    batch_size=batch_size,
+    class_mode='binary')
+
+validation_generator = test_datagen.flow_from_directory(
+    validation_data_dir,
+    target_size=(img_width, img_height),
+    batch_size=batch_size,
+    class_mode='binary')
+
+model.fit_generator(
+    train_generator,
+    steps_per_epoch=nb_train_samples // batch_size,
+    epochs=epochs,
+    validation_data=validation_generator,
+    validation_steps=nb_validation_samples // batch_size)
+
+model.save_weights('first_try.h5')
+model.save('first_try_model.h5')