!mkdir -p ~/.

kaggle
!cp kaggle.json ~/.kaggle/

!kaggle datasets download -d salader/dogs-vs-cats

import zipfile
zip_ref = zipfile.ZipFile('/content/dogs-vs-cats.zip', 'r')
zip_ref.extractall('/content')
zip_ref.close()

import tensorflow as tf
from tensorflow import keras
from keras import Sequential
from keras.layers import Dense,Conv2D,MaxPooling2D,Flatten, BatchNormalization, Dropout

train_ds = keras.utils.image_dataset_from_directory(
directory = '/content/train',
labels="inferred",
label_mode="int",#assigns 0 for cat and 1 for dogs
batch_size=32,
image_size=(256, 256),
)
validation_ds = keras.utils.image_dataset_from_directory(
directory = '/content/test',
labels="inferred",
label_mode="int",
batch_size=32,
image_size=(256, 256),
)

Found 20000 files belonging to 2 classes.

def process(image,label):
image = tf.cast(image/255. ,tf.float32)
return image,label

train_ds = train_ds.map(process)
validation_ds = validation_ds.map(process)
# Dataset is ready
# CNN model
# Contains 3 layers
# First layer - 32 filters, Second layer - 64 filters, Third layer - 128 filters

model = Sequential()

model.add(Conv2D(32,kernel_size=(3,3),padding='valid',activation='relu',input_shape=(256,256,3)))
model.add(BatchNormalization())

model.add(MaxPooling2D(pool_size=(2,2),strides=2,padding='valid'))
model.add(Conv2D(64,kernel_size=(3,3),padding='valid',activation='relu'))
model.add(BatchNormalization())

model.add(MaxPooling2D(pool_size=(2,2),strides=2,padding='valid'))
model.add(Conv2D(128,kernel_size=(3,3),padding='valid',activation='relu'))
model.add(BatchNormalization())

model.add(MaxPooling2D(pool_size=(2,2),strides=2,padding='valid'))
model.add(Flatten())

model.add(Dense(128,activation='relu'))
model.add(Dropout(0.1))

model.add(Dense(64,activation='relu'))
model.add(Dropout(0.1))

model.add(Dense(1,activation='sigmoid'))

model.summary()
 Model: "sequential_3"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓
┃ Layer (type) ┃ Output Shape ┃ Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩
│ conv2d_9 (Conv2D) │ (None, 254, 254, 32) │ 896 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ batch_normalization_9 │ (None, 254, 254, 32) │ 128 │
│ (BatchNormalization) │ │ │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ max_pooling2d_9 (MaxPooling2D) │ (None, 127, 127, 32) │ 0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ conv2d_10 (Conv2D) │ (None, 125, 125, 64) │ 18,496 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ batch_normalization_10 │ (None, 125, 125, 64) │ 256 │
│ (BatchNormalization) │ │ │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ max_pooling2d_10 (MaxPooling2D) │ (None, 62, 62, 64) │ 0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ conv2d_11 (Conv2D) │ (None, 60, 60, 128) │ 73,856 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ batch_normalization_11 │ (None, 60, 60, 128) │ 512 │
│ (BatchNormalization) │ │ │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ max_pooling2d_11 (MaxPooling2D) │ (None, 30, 30, 128) │ 0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ flatten_3 (Flatten) │ (None, 115200) │ 0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_9 (Dense) │ (None, 128) │ 14,745,728 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dropout_6 (Dropout) │ (None, 128) │ 0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_10 (Dense) │ (None, 64) │ 8,256 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dropout_7 (Dropout) │ (None, 64) │ 0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_11 (Dense) │ (None, 1) │ 65 │
└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘

model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])

history=model.fit(train_ds,epochs=10,validation_data=validation_ds)

Epoch 1/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 66s 84ms/step - accuracy: 0.5642 - loss: 2.9611 - val_accuracy: 0.6682 - val_loss: 0.6055
Epoch 2/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 51s 81ms/step - accuracy: 0.6814 - loss: 0.5940 - val_accuracy: 0.7160 - val_loss: 0.5469
 Epoch 3/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 80s 79ms/step - accuracy: 0.7408 - loss: 0.5248 - val_accuracy: 0.7642 - val_loss: 0.4932
Epoch 4/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 83s 80ms/step - accuracy: 0.7867 - loss: 0.4594 - val_accuracy: 0.7652 - val_loss: 0.4840
Epoch 5/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 82s 81ms/step - accuracy: 0.8223 - loss: 0.3985 - val_accuracy: 0.7996 - val_loss: 0.4521
Epoch 6/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 82s 80ms/step - accuracy: 0.8445 - loss: 0.3536 - val_accuracy: 0.7688 - val_loss: 0.5311
Epoch 7/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 54s 86ms/step - accuracy: 0.8825 - loss: 0.2690 - val_accuracy: 0.7700 - val_loss: 0.7174
Epoch 8/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 82s 86ms/step - accuracy: 0.9285 - loss: 0.1817 - val_accuracy: 0.8040 - val_loss: 0.6982
Epoch 9/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 49s 79ms/step - accuracy: 0.9482 - loss: 0.1387 - val_accuracy: 0.8240 - val_loss: 0.7026
Epoch 10/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 84s 82ms/step - accuracy: 0.9643 - loss: 0.0989 - val_accuracy: 0.8272 - val_loss: 0.8087

from google.colab import drive

Mounted at /content/drive

import cv2
test_img = cv2.imread('/content/dog2.jpg')
plt.imshow(test_img)

<matplotlib.image.AxesImage at 0x7d9ebe0cabf0>
test_img.shape

(430, 710, 3)

test_img = cv2.resize(test_img,(256,256))

test_input = test_img.reshape((1,256,256,3))

#1 means dog, 0 means cat

1/1 ━━━━━━━━━━━━━━━━━━━━ 1s 917ms/step