sachin-212-dtu/Image-Classification-using-CNN ? reverse-engineered prompt

Build me a simple notebook project that trains a CNN to tell cats and dogs apart using the Kaggle Dogs vs Cats dataset.

I want it to download or load the data, prepare the images, resize everything to 256 by 256, normalize the pixels, and split it into training and validation data. Then build a straightforward TensorFlow and Keras model with a few convolution layers, batch normalization, max pooling, dense layers, and dropout, and train it for 10 epochs with binary crossentropy and Adam.

Please also add code to show the training and validation accuracy and loss charts, and include a quick way to test the model on a sample image. Make it easy to run in Google Colab or a normal Jupyter notebook, and if you need current setup details, look up the latest docs online.