Google Colaboratory and Python: Deep Learning basics for CV tasks
summary
Demonstrates how to build, train and test a simple CNN end to end using Google Colaboratory, Python, OpenCV, matplotlib, TensorFlow and Keras, including saving a .h5 model and running predictions on a custom image. Uses the CIFAR-10-style dataset of 60,000 color images (50,000 train / 10,000 test), images sized 32x32x3. Model: two conv blocks (32→64 filters, 3x3), 2x2 max‑pool, dropout (0.25/0.5), flatten, Dense 512, softmax; trained 15 epochs, achieves ~76% test accuracy.
AI-written summary · about
chapters (7)
- 0:00Google Colab and Python intro
- 2:58Colab basics and setup
- 13:18Python for image manipulation
- 34:06Convolutional neural networks overview
- 47:01Creating and training CNN
- 1:20:06Model evaluation and testing
- 1:50:31Summary and Q&A
related talks
01h 39mGoogle Colaboratory and Python: Deep Learning basics for CV tasks
47mDeep Learning with PyTorch
01h 27mHands-On Computer Vision with PyTorch
47mDeep Learning in Computer Vision
15mMy first steps on Deep Learning with Keras
51mA Practical Introduction to Convnets for Image Classification
21mRecognizing Human features using Deep Networks
01h 57mUsing CNTKs Python Interface for Deep Learning