{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"Image_colorization.ipynb","version":"0.3.2","provenance":[],"collapsed_sections":[]},"kernelspec":{"name":"python3","display_name":"Python 3"},"accelerator":"GPU"},"cells":[{"metadata":{"id":"DMrlFt9mdFHQ","colab_type":"code","outputId":"1b358de3-d946-4509-e495-fd3bae9609c9","colab":{"base_uri":"https://localhost:8080/","height":34}},"cell_type":"code","source":["from keras.datasets import cifar100\n","(x_train,_), (x_test,_) = cifar100.load_data()"],"execution_count":0,"outputs":[{"output_type":"stream","text":["Using TensorFlow backend.\n"],"name":"stderr"}]},{"metadata":{"id":"lAPwBpSwdJ1g","colab_type":"code","colab":{}},"cell_type":"code","source":["import cv2\n","import numpy as np"],"execution_count":0,"outputs":[]},{"metadata":{"id":"sirX-_SVdKxt","colab_type":"code","colab":{}},"cell_type":"code","source":["x_traing=[]\n","x_testg=[]\n","for i in range(50000):\n","   x_traing.append(cv2.cvtColor(x_train[i], cv2.COLOR_BGR2GRAY))\n","for i in range(10000):\n","   x_testg.append(cv2.cvtColor(x_test[i], cv2.COLOR_BGR2GRAY))"],"execution_count":0,"outputs":[]},{"metadata":{"id":"MonZ25bQdMKQ","colab_type":"code","colab":{}},"cell_type":"code","source":["x_traing=np.array(x_traing)\n","x_testg=np.array(x_testg)\n","x_traing=x_traing.reshape(50000,32,32,1)\n","x_testg=x_testg.reshape(10000,32,32,1)"],"execution_count":0,"outputs":[]},{"metadata":{"id":"9tg_scxTdNGd","colab_type":"code","outputId":"9868c2fa-553e-45d0-8fc4-2d6808c03226","colab":{"base_uri":"https://localhost:8080/","height":34}},"cell_type":"code","source":["x_traing = x_traing/255.0\n","x_testg = x_testg/255.0\n","\n","x_train = x_train/255.0\n","x_test = x_test/255.0\n","\n","x_testg.shape\n"],"execution_count":0,"outputs":[{"output_type":"execute_result","data":{"text/plain":["(10000, 32, 32, 1)"]},"metadata":{"tags":[]},"execution_count":5}]},{"metadata":{"id":"EHOIteGrdOTX","colab_type":"code","colab":{}},"cell_type":"code","source":["from keras.layers import Input, Dense, Conv2D, MaxPooling2D, UpSampling2D\n","from keras.models import Model\n","from keras import backend as K\n","\n","input_img = Input(shape=(32,32,1))\n","\n","x = Conv2D(32, (3, 3), activation='relu', padding='same')(input_img) \n","x = MaxPooling2D((2, 2), padding='same')(x) \n","x= Conv2D(64, (3, 3), activation='relu', padding='same')(x) \n","x= Conv2D(64, (3, 3), activation='relu', padding='same')(x) \n","x= MaxPooling2D((2, 2), padding='same')(x) # 8x8x128\n","encoded = Conv2D(128, (3, 3), activation='relu', padding='same')(x)\n","\n","\n","\n","x = UpSampling2D((2, 2))(encoded) \n","x = Conv2D(128, (3, 3), activation='relu', padding='same')(x) \n","x = Conv2D(128, (3, 3), activation='relu', padding='same')(x) \n","x = UpSampling2D((2, 2))(x) \n","x= Conv2D(64, (3, 3), activation='relu', padding='same')(x) \n","decoded = Conv2D(3, (3, 3), activation='linear', padding='same')(x)\n","\n","autoencoder = Model(input_img, decoded)\n","autoencoder.compile(optimizer='adam', loss='mean_squared_error',metrics=['accuracy'])"],"execution_count":0,"outputs":[]},{"metadata":{"id":"il27APdEdPwJ","colab_type":"code","outputId":"d8bae355-e114-40e7-bb1c-50ca8ebafe00","colab":{"base_uri":"https://localhost:8080/","height":571}},"cell_type":"code","source":["autoencoder.summary()"],"execution_count":0,"outputs":[{"output_type":"stream","text":["_________________________________________________________________\n","Layer (type)                 Output Shape              Param #   \n","=================================================================\n","input_6 (InputLayer)         (None, 32, 32, 1)         0         \n","_________________________________________________________________\n","conv2d_35 (Conv2D)           (None, 32, 32, 32)        320       \n","_________________________________________________________________\n","max_pooling2d_11 (MaxPooling (None, 16, 16, 32)        0         \n","_________________________________________________________________\n","conv2d_36 (Conv2D)           (None, 16, 16, 64)        18496     \n","_________________________________________________________________\n","conv2d_37 (Conv2D)           (None, 16, 16, 64)        36928     \n","_________________________________________________________________\n","max_pooling2d_12 (MaxPooling (None, 8, 8, 64)          0         \n","_________________________________________________________________\n","conv2d_38 (Conv2D)           (None, 8, 8, 128)         73856     \n","_________________________________________________________________\n","up_sampling2d_11 (UpSampling (None, 16, 16, 128)       0         \n","_________________________________________________________________\n","conv2d_39 (Conv2D)           (None, 16, 16, 128)       147584    \n","_________________________________________________________________\n","conv2d_40 (Conv2D)           (None, 16, 16, 128)       147584    \n","_________________________________________________________________\n","up_sampling2d_12 (UpSampling (None, 32, 32, 128)       0         \n","_________________________________________________________________\n","conv2d_41 (Conv2D)           (None, 32, 32, 64)        73792     \n","_________________________________________________________________\n","conv2d_42 (Conv2D)           (None, 32, 32, 3)         1731      \n","=================================================================\n","Total params: 500,291\n","Trainable params: 500,291\n","Non-trainable params: 0\n","_________________________________________________________________\n"],"name":"stdout"}]},{"metadata":{"id":"CZYsS1dOdReo","colab_type":"code","outputId":"ac84ea91-8da0-4f78-f20d-2e4878e8b641","colab":{"base_uri":"https://localhost:8080/","height":202}},"cell_type":"code","source":["autoencoder.fit(x_traing,x_train,epochs=5,batch_size=256)"],"execution_count":0,"outputs":[{"output_type":"stream","text":["Epoch 1/5\n","50000/50000 [==============================] - 27s 549us/step - loss: 0.0095 - acc: 0.5086\n","Epoch 2/5\n","50000/50000 [==============================] - 27s 548us/step - loss: 0.0094 - acc: 0.5101\n","Epoch 3/5\n","50000/50000 [==============================] - 27s 549us/step - loss: 0.0094 - acc: 0.5113\n","Epoch 4/5\n","50000/50000 [==============================] - 27s 549us/step - loss: 0.0093 - acc: 0.5142\n","Epoch 5/5\n","50000/50000 [==============================] - 27s 548us/step - loss: 0.0093 - acc: 0.5141\n"],"name":"stdout"},{"output_type":"execute_result","data":{"text/plain":["<keras.callbacks.History at 0x7f7798d939e8>"]},"metadata":{"tags":[]},"execution_count":43}]},{"metadata":{"id":"BnaA8fkOdS2b","colab_type":"code","outputId":"4e8468c3-50f6-4d46-d320-aeb528b7b1f5","colab":{"base_uri":"https://localhost:8080/","height":285}},"cell_type":"code","source":[" import matplotlib.pyplot as plt #test image in black and white\n","%matplotlib inline\n","t_imgg=x_traing[50]\n","t_imgg = t_imgg.reshape(32,32)\n","\n","plt.subplot(2,1,1)\n","plt.imshow(t_imgg,cmap='gray')\n","\n","t_colorimg = x_train[50]\n","t_colorimg = t_colorimg.reshape(32,32,3)\n","plt.subplot(2,1,2)\n","plt.imshow(t_colorimg)"],"execution_count":0,"outputs":[{"output_type":"execute_result","data":{"text/plain":["<matplotlib.image.AxesImage at 0x7f77988ab358>"]},"metadata":{"tags":[]},"execution_count":54},{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAIMAAAD7CAYAAABJ7CfKAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nDAoH3QwKh/8Hfu76AKgVvdEAAAAASUVORK5CYII=\n","text/plain":["<Figure size 432x288 with 2 Axes>"]},"metadata":{"tags":[]}}]},{"metadata":{"id":"59mPqKwMdT0V","colab_type":"code","outputId":"ac83ee0a-b91c-46f8-a732-be7b65652e9f","colab":{"base_uri":"https://localhost:8080/","height":193}},"cell_type":"code","source":["t_imgg = t_imgg.reshape(1,32,32,1)\n","result = autoencoder.predict(t_imgg)\n","result = result[0]\n","# result\n","plt.figure(figsize=(2,2))\n","plt.imshow(result)"],"execution_count":0,"outputs":[{"output_type":"stream","text":["Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).\n"],"name":"stderr"},{"output_type":"execute_result","data":{"text/plain":["<matplotlib.image.AxesImage at 0x7f77987bc0b8>"]},"metadata":{"tags":[]},"execution_count":55},{"output_type":"display_data","data":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAI0AAACOCAYAAAAMyosLAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nhjGNoTT+H8g9J60tih1lAAAAAElFTkSuQmCC\n","text/plain":["<Figure size 144x144 with 1 Axes>"]},"metadata":{"tags":[]}}]},{"metadata":{"id":"8ZkvtLAqdU8F","colab_type":"code","colab":{}},"cell_type":"code","source":[""],"execution_count":0,"outputs":[]}]}