Watch Deep Learning Tensorflow Video Tutorials & Courses

Learn TensorFlow by BUILDING, not just watching someone else. Join ML Engineer Daniel Bourke in this hands-on crash course to go from a total beginner to becoming a Deep Learning Expert. 👨‍💻 Source Code: https://github.com/mrdbourke/tensorflow-deep-learning/ 📓 Course Materials: https://dev.mrdbourke.com/tensorflow-deep-learning/ As a special bonus, we’re also giving you exclusive access to the official ZTM Discord. Normally just for ZTM members, you’ll be able to join 1,000s of other learners, mentors and instructors (including Dan!!) to get help when you’re stuck and connect directly with others on the same journey. Exclusive invite link → https://discord.gg/BJCzQ7zsjh ========= 🤖 If you get through all 23 hours here (WOW!), then you'll love the additional 41 hours in Dan's full TensorFlow Bootcamp → https://zerotomastery.io/courses/learn-tensorflow/ 🎁 Use code YTTF10 to get 10% OFF Dan's Bootcamp or any ZTM membership ========== ⏰ Timestamps ⏰ 00:00 Intro 01:22 Deep Learning 101 06:10 Why DL 15:57 Neural nets 101 26:32 DL use cases 35:18 Why TensorFlow 43:23 Tensors 47:09 Outline 51:47 How to follow 57:30 First tensors (tf.constant) 1:16:24 Tensors (tf.Variable) 1:23:41 Random tensors 1:33:30 Shuffle tensors 1:43:19 NumPy → tensors 1:55:23 Tensor attrs 2:07:29 Index & expand 2:20:12 Tensor ops 2:25:55 MatMul P1 2:37:57 MatMul P2 2:51:36 MatMul P3 3:01:48 Change dtypes 3:57:33 Aggregation 4:07:31 Dtype troubleshooting 4:13:54 Argmin/Argmax 4:23:34 Squeeze 4:26:43 One-hot 4:32:38 More math 4:37:35 TF ↔ NumPy 4:43:26 GPU accel 4:53:55 Regression intro 5:01:37 Inputs/outputs 5:10:45 Architecture 5:18:49 Sample data 5:31:44 TF 2.7.0 update (https://dev.mrdbourke.com/tensorflow-deep-learning/) 5:31:53 Modelling steps 5:52:18 Improve P1 5:58:29 Improve P2 6:08:04 Improve P3 6:20:46 Eval P1 (viz) 6:28:19 Eval P2 (3 sets) 6:39:30 Eval P3 (summary) 6:56:57 Eval P4 (layers) 7:04:20 Eval P5 (preds) 7:13:45 Eval P6 (metrics) 7:21:59 Eval P7 (MAE) 7:28:01 Eval P8 (MSE) 7:31:29 Experiments P1 7:45:28 Experiments P2 7:57:06 Compare exps 8:07:35 Save model 8:16:04 Load model 8:26:28 Save/download (Colab) 8:32:56 Put it together P1 8:46:36 Put it together P2 9:00:06 Put it together P3 9:16:01 Feature scaling P1 9:25:45 Feature scaling P2 9:36:51 Feature scaling P3 9:44:40 Classification intro 9:53:14 Classification examples 10:00:01 Clf I/O tensors 10:06:32 Clf model arch 10:16:17 Create/view clf data 10:28:00 Check shapes 10:32:47 Baseline clf model 10:45:07 Improve baseline 10:54:29 View bad preds (func) 11:09:46 TF 2.7.0 update (https://dev.mrdbourke.com/tensorflow-deep-learning/) 11:09:55 Clf model on regression 11:22:22 Non-lin P1 (lines vs curves) 11:32:10 Non-lin P2 (first NN) 11:38:07 Non-lin P3 (more layers) 11:48:34 Non-lin P4 (final model) 12:11:57 Tune learning rate 12:26:53 Plot loss (History) 12:33:14 Callbacks for LR 12:50:55 Train/eval w/ ideal LR 13:00:24 More clf eval 13:06:38 Accuracy 13:11:04 Confusion matrix (basic) 13:19:41 Confusion matrix (better) 13:33:51 Multiclass P1 (data) 13:44:37 Multiclass P2 (prep) 13:51:54 Multiclass P3 (build) 14:07:41 Multiclass P4 (normalise) 14:20:33 Multiclass P5 (norm vs non) 14:24:56 Multiclass P6 (find LR) 14:35:43 Multiclass P7 (eval) 14:49:09 Multiclass P8 (confusion) 14:53:44 Multiclass P9 (viz preds) 15:04:35 What patterns learned 15:20:17 CV intro 15:30:01 CNNs intro 15:38:10 Download Food Vision 15:46:46 Know the data P1 15:52:00 Know the data P2 16:04:35 Know the data P3 16:09:07 End-to-end CNN 16:27:34 CNN on GPU (5×) 16:37:00 Try non-CNN 16:46:00 Improve non-CNN 16:56:01 CNN breakdown P1 (data) 17:05:13 CNN breakdown P2 (prep load) 17:17:08 CNN breakdown P3 (ImageDataGenerator) 17:27:12 CNN breakdown P4 (baseline) 17:35:24 CNN breakdown P5 (inside Conv2D) 17:50:53 CNN breakdown P6 (compile/fit) 17:58:16 CNN breakdown P7 (train curves) 18:10:11 CNN breakdown P8 (max pooling) 18:24:00 CNN breakdown P9 (data aug) 18:31:00 CNN breakdown P10 (viz aug) 18:46:14 CNN breakdown P11 (train on aug) 18:55:12 CNN breakdown P12 (shuffle) 19:05:22 CNN breakdown P13 (improve) 19:10:53 Download custom image 19:15:56 Helper: load/preprocess 19:26:06 Predict custom image 19:36:23 Multi-class CNN P1 (data) 19:51:32 Multi-class CNN P2 (prep tensors) 19:58:19 Multi-class CNN P3 (build) 20:05:52 Multi-class CNN P4 (fit) 20:12:04 Multi-class CNN P5 (eval) 20:17:04 Multi-class CNN P6 (fix overfit: remove) 20:29:33 Multi-class CNN P7 (fix overfit: aug) 20:41:27 Multi-class CNN P8 (improve) 20:46:00 Multi-class CNN P9 (custom preds) 20:55:31 Save/load CNN 21:02:01 Transfer learning intro 21:12:22 Data prep (TL) 21:27:11 Callbacks (tracking) 21:37:21 Explore TF Hub (pretrained) 21:47:21 Build/compile Hub feature extractor 22:01:30 TL over previous models 22:10:53 ResNet loss curves 22:18:37 Train EfficientNet 22:28:29 Types of TL 22:40:18 Compare results 22:55:43 Final takeaway ========== Dan's TensorFlow Bootcamp 👉 https://zerotomastery.io/courses/learn-tensorflow/ Key Highlights & Overview: Mastering <strong>Deep Learning Tensorflow</strong> requires clear step-by-step guidance and practical hands-on visual demonstrations. Explore curated video courses, expert walkthroughs, and detailed lesson notes today on <strong>TutorTube</strong>.