@@markxavior good Idea, I should admire you, finally you are here to learn something, a small step to learn something great, I admire your step. That's one small step for man, one giant leap for mankind.
The fact that this much knowledge is free is incredible. There is no excuse to be ignorant. These guys really care about educating the world in computer science. Mad respect, thank you.
Note for myself. ----------------------------- Stop watching at: 1:07:31 - 22.06 2:14:12 - 23.06 some problems - 24.06 2:48:52 - 25.06 (afternoon) | 3:00:00 - 25.06 (evening) 4:01:05 - 26.06 5:25:22 - 27.06 6:28:51 - 28.06 7:38:56 - 29.06 8:28:17 - 30.06 9:18:29 - 01.07 10:10:10 - 02.07 11:40:23 - 03.07 12:22:38 - 04.07 13:36:54 - 05.07 13:55:14 - 06.07 (A LOT of errors...) 14:07:11 - 07.07 (Finally fixed it) 14:43:57 - 08.07 14:56:59 - 09.07 15:21:05 - 10.07 15:48:30 - 11.07 16:12:16 - 12.07 16:26:30 - 13.07 16:34:20 - 14.07 16:39:12 - 15.07 17:14:22 - 16.07 17:14:42 - 19.07 (Fixed critical error named "broken pipe") 17:46:13 - 20.07 18:13:06 - 21.07 (Trying some experiments) 18:16:55 - 24.07 19:20:42 - 28.07 20:24:00- 30.07 (Problems with video card...) 20:30:05 - 01.08 21:34:54 - 03.08 21:46:47 - 06.08 (Fixed the main bug. Or didn't...) 22:30:33 - 15.08 22:54:54 - 16.08 23:34:57 - 21.08 (found another) 23:57:42 - 25.08 1:00:51:22 - 26.08 1:01:29:49 - 27.08 1:01:42:45 - 28.08 1:02:06:00 - 29.08 1:02:35:26 - 30.08,31.08 1:03:22:12 - 01.09 (from now I learn at nights, meaning it's not 01.09, but rather 01-02, 02-03 etc.) 1:03:58:32 - 02.09 1:04:30:14 - 03.09 1:05:23:37 - 04.09 1:06:51:37 - 11.09 1:07:30:47 - 14-15/09 1:07:58:33 - 16/09 1:08:26:54 - 17/09 1:08:32:47 - 18/09 1:09:02:25 - 19/09 (I will finish not later than early October.) 1:09:36:39 - 21/09 1:11:06:11 - 23/09 1:11:21:34 - 25/09 1:11:43:32 - 28/09 Done it. - 02/10 1:15 a.m. Calculator says it's been 3 months and 1 week, don't care actually, cause I've written down the whole code, which author showed. The only problem is that I hardly remember the start of the course. My tip for those who are only starting this course: if you have an error that brakes your entire code, and you struggle with it for days instead of actually learning, just use the author's colab code from the link in the description. It's a waste of time that isn't worth it, trust my word, I had a plenty of them. Value your time. ----------------------------- 11:15:00 (+-10) - Pretty useful info 20:05:09 - man literally said 'feature' nearly 100 times in 5 minutes
@@leoniff8987 Of course, it is! It's great to learn about something as interesting as machine learning in practice way. Now I want to get some python intermediate basics, and then practice on kaggle as much as possible as author suggested. And one more thing to note, I've finished this course quite a long time ago, so I've forgotten some stuff already, but I can easily review it all by going through code I've written with all my experiments and comments. Overall, this was very useful. Hope it will be useful for you too, just take note of tips I gave above.
Day 1: Introduction (0:00:00) Welcome (0:05:54) Prerequisite (0:06:11) What we shall Learn (0:12:12) Basics Day 2: Tensors and Variables - Part 1 (0:19:26) Initialization and Casting (1:07:31) Indexing Day 3: Tensors and Variables - Part 2 (1:16:15) Math Operations Day 4: Tensors and Variables - Part 3 (1:55:02) Linear Algebra Operations Day 5: Tensors and Variables - Part 4 (2:56:21) Common TensorFlow Functions Day 6: Tensors and Variables - Part 5 (3:50:15) Ragged Tensors (4:01:41) Sparse Tensors Day 7: Tensors and Variables - Part 6 (4:04:23) String Tensors (4:07:45) Variables Day 8: Building Neural Networks with TensorFlow [Car Price Prediction] - Part 1 (4:14:52) Task Understanding (4:19:47) Data Preparation Day 9: Building Neural Networks with TensorFlow [Car Price Prediction] - Part 2 (4:54:47) Linear Regression Model Day 10: Building Neural Networks with TensorFlow [Car Price Prediction] - Part 3 (5:10:18) Error Sanctioning Day 11: Building Neural Networks with TensorFlow [Car Price Prediction] - Part 4 (5:24:53) Training and Optimization Day 12: Building Neural Networks with TensorFlow [Car Price Prediction] - Part 5 (5:41:22) Performance Measurement (5:44:18) Validation and Testing Day 13: Building Neural Networks with TensorFlow [Car Price Prediction] - Part 6 (6:04:30) Corrective Measures Day 14: Building Convolutional Neural Networks with TensorFlow [Malaria Diagnosis] - Part 1 (6:28:50) Task Understanding (6:37:40) Data Preparation Day 15: Building Convolutional Neural Networks with TensorFlow [Malaria Diagnosis] - Part 2 (6:57:40) Data Visualization (7:00:20) Data Processing Day 16: Building Convolutional Neural Networks with TensorFlow [Malaria Diagnosis] - Part 3 (7:08:50) How and Why ConvNets Work Day 17: Building Convolutional Neural Networks with TensorFlow [Malaria Diagnosis] - Part 4 (7:56:15) Building Convnets with TensorFlow Day 18: Building Convolutional Neural Networks with TensorFlow [Malaria Diagnosis] - Part 5 (8:02:39) Binary Crossentropy Loss (8:10:15) Training Convnets Day 19: Building Convolutional Neural Networks with TensorFlow [Malaria Diagnosis] - Part 6 (8:23:33) Model Evaluation and Testing (8:29:15) Loading and Saving Models to Google Drive Day 20: Building More Advanced Models in TensorFlow [Malaria Diagnosis] - Part 1 (8:47:10) Functional API Day 21: Building More Advanced Models in TensorFlow [Malaria Diagnosis] - Part 2 (9:03:48) Model Subclassing Day 22: Building More Advanced Models in TensorFlow [Malaria Diagnosis] - Part 3 (9:19:05) Custom Layers Day 23: Evaluating Classification Models [Malaria Diagnosis] - Part 1 (9:36:45) Precision, Recall and Accuracy Day 24: Evaluating Classification Models [Malaria Diagnosis] - Part 2 (10:00:35) Confusion Matrix (10:10:10) ROC Plots Day 25: Improving Model Performance [Malaria Diagnosis] - Part 1 (10:18:10) TensorFlow Callbacks Day 26: Improving Model Performance [Malaria Diagnosis] - Part 2 (10:43:55) Learning Rate Scheduling Day 27: Improving Model Performance [Malaria Diagnosis] - Part 3 (11:01:25) Model Checkpointing (11:09:25) Mitigating Overfitting and Underfitting Day 28: Data Augmentation [Malaria Diagnosis] - Part 1 (11:38:50) Augmentation with tf.image and Keras Layers Day 29: Data Augmentation [Malaria Diagnosis] - Part 2 (12:38:00) Mixup Augmentation (12:56:35) Cutmix Augmentation Day 30: Data Augmentation [Malaria Diagnosis] - Part 3 (13:38:30) Data Augmentation with Albumentations Day 31: Advanced TensorFlow Topics [Malaria Diagnosis] - Part 1 (13:58:35) Custom Loss and Metrics Day 32: Advanced TensorFlow Topics [Malaria Diagnosis] - Part 2 (14:18:30) Eager and Graph Modes Day 33: Advanced TensorFlow Topics [Malaria Diagnosis] - Part 3 (14:31:23) Custom Training Loops Day 34: Tensorboard Integration [Malaria Diagnosis] - Part 1 (14:57:00) Data Logging Day 35: Tensorboard Integration [Malaria Diagnosis] - Part 2 (15:29:00) View Model Graphs (15:31:45) Hyperparameter Tuning Day 36: Tensorboard Integration [Malaria Diagnosis] - Part 3 (15:52:40) Profiling and Visualizations Day 37: MLOps with Weights and Biases [Malaria Diagnosis] - Part 1 (16:00:35) Experiment Tracking Day 38: MLOps with Weights and Biases [Malaria Diagnosis] - Part 2 (16:55:02) Hyperparameter Tuning Day 39: MLOps with Weights and Biases [Malaria Diagnosis] - Part 3 (17:17:15) Dataset Versioning Day 40: MLOps with Weights and Biases [Malaria Diagnosis] - Part 4 (18:00:23) Model Versioning Day 41: Human Emotions Detection - Part 1 (18:16:55) Data Preparation Day 42: Human Emotions Detection - Part 2 (18:45:38) Modeling and Training Day 43: Human Emotions Detection - Part 3 (19:36:42) Data Augmentation Day 44: Human Emotions Detection - Part 4 (19:54:30) TensorFlow Records Day 45: Modern Convolutional Neural Networks [Human Emotions Detection] - Part 1 (20:31:25) AlexNet (20:48:35) VGGNet Day 46: Modern Convolutional Neural Networks [Human Emotions Detection] - Part 2 (20:59:50) ResNet Day 47: Modern Convolutional Neural Networks [Human Emotions Detection] - Part 3 (21:34:07) Coding ResNet from Scratch Day 48: Modern Convolutional Neural Networks [Human Emotions Detection] - Part 4 (21:56:17) MobileNet (22:20:43) EfficientNet Day 49: Transfer Learning [Human Emotions Detection] - Part 1 (22:38:15) Feature Extraction Day 50: Transfer Learning [Human Emotions Detection] - Part 2 (23:02:25) Finetuning Day 51: Understanding the Blackbox [Human Emotions Detection] - Part 1 (23:15:33) Visualizing Intermediate Layers Day 52: Understanding the Blackbox [Human Emotions Detection] - Part 2 (23:36:20) Gradcam method Day 53: Transformers in Vision [Human Emotions Detection] - Part 1 (23:57:35) Understanding ViTs Day 54: Transformers in Vision [Human Emotions Detection] - Part 2 (24:51:17) Building ViTs from Scratch Day 55: Transformers in Vision [Human Emotions Detection] - Part 3 (25:42:39) FineTuning Huggingface ViT Day 56: Transformers in Vision [Human Emotions Detection] - Part 4 (26:05:52) Model Evaluation with Wandb Day 57: Model Deployment [Human Emotions Detection] - Part 1 (26:27:13) Converting TensorFlow Model to Onnx format Day 58: Model Deployment [Human Emotions Detection] - Part 2 (26:52:26) Understanding Quantization Day 59: Model Deployment [Human Emotions Detection] - Part 3 (27:13:08) Practical Quantization of Onnx Model (27:22:01) Quantization Aware Training Day 60: Model Deployment [Human Emotions Detection] - Part 4 (27:39:55) Conversion to TensorFlow Lite (27:58:28) How APIs work Day 61: Model Deployment [Human Emotions Detection] - Part 5 (28:18:28) Building an API with FastAPI Day 62: Model Deployment [Human Emotions Detection] - Part 6 (29:39:10) Deploying API to the Cloud (29:51:35) Load Testing with Locust Day 63: Object Detection with YOLO - Part 1 (30:05:29) Introduction to Object Detection Day 64: Object Detection with YOLO - Part 2 (30:11:39) Understanding YOLO Algorithm Day 65: Object Detection with YOLO - Part 3 (31:15:17) Dataset Preparation Day 66: Object Detection with YOLO - Part 4 (31:58:27) YOLO Loss Day 67: Object Detection with YOLO - Part 5 (33:02:58) Data Augmentation Day 68: Object Detection with YOLO - Part 6 (33:27:33) Testing Day 69: Image Generation - Part 1 (33:59:28) Introduction to Image Generation (34:03:18) Understanding Variational Autoencoders Day 70: Image Generation - Part 2 (34:20:46) VAE Training and Digit Generation Day 71: Image Generation - Part 3 (35:06:05) Latent Space Visualization Day 72: Image Generation - Part 4 (35:21:36) How GANs work Day 73: Image Generation - Part 5 (35:43:30) The GAN Loss Day 74: Image Generation - Part 6 (36:01:38) Improving GAN Training Day 75: Image Generation - Part 7 (36:25:02) Face Generation with GANs
kudos to you! I don't usually comment but I have to this time. I'm halfway through this course and I have 1 year of working experience in computer vision but still, there are a lot of new things I am learning in every lesson, and everything is perfectly explained.
Finally an AI/ML/DL course with my pace & knowledge levels. All the courses out there just throw out some numbers and fancy formulas w/o reference of what/why/how, using terminologies which I have to google again to understand. I just watched first 20 mins just to get the feel for and I assure every one that come in here looking to learn, would definitely benefit w/o feeling anxious and self-doubt whether they fit in. All the very best for the learners.
Start : 21 Dec 2023 Day 01 : 01:07:30 [Basics + Initialisation and Casting] Day 02 : No Progress Day 03 : 01:55:02 [Indexing + Maths Operations] Day 04 : 02:15:10 [Linear Algebra Operations : multiply, transpose] Day 05 : 04:07:46 [Linear Algebra Operations : det, adjoint, transpose, band_part, cholesky + Other types of Tensors like Ragged, Sparse, Strings] Day 06 : 04:14:53 [Tensorflow Variables] Day 07 : No Progress Project 01 : Car Price Predictor Day 08 : 04:54:47 [Data Preparation + Preprocessing] Day 09 : No Progress Day 10 : 06:28:52 [Completed Car Price Predictor] Start : 20 Jan 2024 Project 02 : Malaria Diagnosis
Awesome stuff.. This is my first tutorial towards getting into computer vision field so I'll be following along. Day 1 -> 1:07:31 Day 2 -> 2:15:16 Day 3 -> 2:56:21 Day 4 -> None Day 5 -> 3:50:15 Day 6 -> 4:15:00 Day 7 -> 5:10:20
As machine learning finds increasing use in virtually every industry, there’s a growing need for people to bring machine learning models into production...this course is making that possible, thanks a ton freecodecamp & Neaural learn
@@Nobody-co9dj if you give 2 hours every day making notes and coding side by side, you can finish it in 20 days. Thats 3 weeks. The only problem is distractions and poor time management which prevents us from learning so many useful things
This is the best course I watch ever! It is so detailed and everything is covered so much that I simply have no words. Well done guys. You have shown how to actually make a tutorial.
I simply cant thank you guys enough the whole team for sharing such content to the world!. Where institutions charge u 10s if thousands of dollars for such degree . You are practically giving it away for free. Thank you so much everyone . I can only imagine the less fortunate people finding this on the net would be a game changer for them
Thanks a lot. I have been planning to join a course somewhere online but now i don't need to. Still can't believe you guys just posted such content for free. Thanks again.
Awesome course and projects on CNN! Love your work. P.S. (8:29:15) Loading and Saving Models to Google Drive : This section is just still screen. There's no change.
Start 14 jan 2024 day 1- (0:12:12) Basics (0:19:26) Initialization and Casting day 2- (1:07:31) Indexing (1:16:15) Maths Operations day 3- (1:55:02) Linear Algebra Operations day 4- No progess day 5-(3:50:15) Ragged Tensors ⌨ (4:01:41) Sparse Tensors ⌨ (4:04:23) String Tensors ⌨ (4:07:45) Variables day 6- Revision
so I was searching for a course like this, finally found one! I aim to complete it before july end, today is 30th may, will start from tomorrow and update each time I open this video (maybe this motivation will help me continue) god, I wasted my one month of vacation , let me not waste this too! fighting!!
Day 1: 00:08:20 Day 2: 01:00:00 Day 3: 03:02:51 (key concepts, needs revisiting) Day 4: (29/08/24): 03:50:00 Day 5 : (01/09/24): 05:27:04 (model training) Day 6: (08/09/24): 06:58:50 (linear regression and dense, data visualization for malaria diagnosis) Day 7: (26/09/24): 08:20:45 (Malaria diagnosis) Day 8: (28/09/24): 09:01:10 (finished with functional API) Side note: does anyone else get a pay as you go issue on colab? any alternatives? Day 9: (30/09/24): 09:59:07 (Important theory on recall and precision) Day 10: (01/10/24): 10:44:50 (Calbacks)
Es la informacion que justo estaba buscando, ahi la llevo voy en el minuto 3.35 llevo 4 dias. Muchas Gracias por la informacion que compartes y lo facil que haces comprenderla.
I have a project at school related to Computer Vision which a field I have never learned. I WILL DECIDE TO COMPLETE THIS COURSE IN 2 WEEK. THIS COMMENT WAS WRITTEN TO SHARE MY EXPERIENCE SO THAT THOSE NEW TO THE VIDEO CAN WATCH IT FASTER. - If you have another laptop/PC or screen, you can watch and practise faster. Install microsoft mouse without borders in to workstation, if your workstation can't work with 2 screen. No one want ALT + TAB in 37 hours. - I think almost people decide practise with this video are not zero. If you are zero, you should watch another video to get some define and theory about machine learning and computer vison before watch this. Because you can learn deeper and faster when reviewing concepts a second time and practise better and you don't want to seeking back and forth this 37 hours video - Below the video description, there are work items. If you are determined, you should complete a item/subject/project before sleep. It will give you more motivation to survise these 37 hours of hell +) DAY 1: I don't learn much today ⌨ (0:00:00) Welcome: Skip or listen if you want ⌨ (0:05:54) Prerequisite: Skip or listen if you want ⌨ (0:06:11) What we shall Learn: Skip or listen if you want Tensors and Variables ⌨ (0:12:12) Basics : tf.constant, shape, ndim, dtype, cast, tf.zeros, tf.random ⌨ (0:19:26) Initialization and Casting: Nothing ⌨ (1:07:31) Indexing: All his code ⌨ (1:16:15) Maths Operations: tf.math.multi ⌨ (1:55:02) Linear Algebra Operations: tf.linalg.matmu, tf.transpose, tf.expand_dims ⌨ (2:56:21) Common TensorFlow Functions: learn all function ⌨ (3:50:15) Ragged Tensors: don't learn ⌨ (4:01:41) Sparse Tensors: learn ⌨ (4:04:23) String Tensors: don't learn. ⌨ (4:07:45) Variables: learn all - DON'T WATCH WASTE YOUR TIME if you already have a little knowledge of linear algebra, get the code of one in the description, combined with chatgpt you will automatically understand how to use tensorflow which he has achieved. This will save you a ton of time and actually the math is more detailed but don't break into the math because this is not linear algebra. If you still don't understand, look at the part you don't understand. - To me, these 4 hours of video are useless, it's really pointless to learn tensorflow because it is a library containing a lot of functions and you will only really need it when the project is relevant. And when problems occur, you will use chatgpt instead of the knowledge learned in these 4 hours. In my opinion, The above things are the most worth learning +) DAY 2: I have a big homework and can't learn today +) DAY 3: Building Neural Networks with TensorFlow [Car Price Prediction] ⌨ (4:14:52) Task Understanding ⌨ (4:19:47) Data Preparation ⌨ (4:54:47) Linear Regression Model ⌨ (5:10:18) Error Sanctioning ⌨ (5:24:53) Training and Optimization ⌨ (5:41:22) Performance Measurement ⌨ (5:44:18) Validation and Testing ⌨ (6:04:30) Corrective Measures Actually, I don't appreciate this project of his. He tried to introduce concepts to begginer, he integrated machine learning, linear regression, neutron network into one problem. The concepts of linear regression and how to train the model are explained quite well, but the neutron network is not very clear. I learned about neutron networks in college and it's actually a lot more detailed and easier to understand than here. This is an important topic and there is a lot of knowledge that needs to be imparted. It would be better if he taught the theory first and then practiced. The practice of both practicing and conveying is quite bad and has many shortcomings. In addition, dividing the dataset into 3 sets training_set, validation_set, test_set is usually done first but he puts it near the end, which upsets the logic. +) Day 4 + 5: Building Convolutional Neural Networks with TensorFlow [Malaria Diagnosis] ⌨ (6:28:50) Task Understanding ⌨ (6:37:40) Data Preparation ⌨ (6:57:40) Data Visualization: In his seaborn practise, visualization can give you information about dataset. You can detect more issue in your dataset and find orther method to solve ⌨ (7:00:20) Data Processing: ⌨ (7:08:50) How and Why ConvNets Work: Listen this carefully ⌨ (7:56:15) Building Convnets with TensorFlow ⌨ (8:02:39) Binary Crossentropy Loss ⌨ (8:10:15) Training Convnets ⌨ (8:23:33) Model Evaluation and Testing ⌨ (8:29:15) Loading and Saving Models to Google Drive: Colab is a virtual machine from Google and run linux os. You can save your model'architech (model layer -CNN/Dense/Pooling, loss function = RMSE, CrossEntropy, .... ) and model'weight after training. The worst thing in this section is it has only a image not video Overview this project is great for everyone start to learn about CNN like me Disadvantage: In fist section, he train model with 1 layer - 1 neutron to demonstrate linear regression. If he started with model has more dense layer, the project will be faster. Because the project is made to learn more theory, you must spent a little of time to complete this project My experience: - I was stuck at CNN concept a lot of time, I have read and watch more document to understand about it. This is my answer for everyone, don't understand after watch his CNN concept. In basic neutron, you have more input signal (X1, X2, ...XN) and a bias X0. It will come neutron, a neutron has 2 thing: Aggregate function and Activation Function. With basic neutron, the Aggregate function is Net = f(X) = w0*X0 + w1* X1 + .... + wn*Xn - Training a model is find W = [w0, w1, ... , wn] best fit with training set. If you choice that Aggrgate function, you must file a thousands parameter in training time with a neutron, and a huge parameter in model with more hidden layer, which has more netron in it. - You can image Convolution Layer is a fully-conected layer has more neutron. The Aggregate function offeach neutron is replaced by convolution calculus with tensor of image input and a kernel matrix has size (k*k*number of chanel of image). By the way, instead of find wi for each Xi input signal/bias, you just find the weight of kernel matrix => You just find (k*k*number of chanel of image + 1) parameter for each neutron. Finaly, each neutron in convolution layer is called "fliter" , the ouput of layer is called "feature map" - Google Colab limited time to use GPU, excecpt pay monney. When I train his model 2 times, I have reached limit. For everyone has a window laptop has NVIDIA GPU, install wsl 2 with Ubuntu distribution and install cuda+cdnn+clang+bazel in it. Note, you must install exactly version that fit with your tensorflow version (I have install tensorflow 2.16.1 with cland 17.0.2, bazel 6.5.0, cdnn 8..9 and cuda 12.3). Create a virrtual python environment 3.10 (if you install python 3.12 in it, you can't load dataset by his code. This is Dataset API of tensorflow 2.16.1 bug in the time I comment). Sea and following this video for sure th-cam.com/video/VE5OiQSfPLg/w-d-xo.html&pp=gAQBiAQ , you can create virtual python environment with anaconda like this video or use vevn model in python3 +) Day 6: Building More Advanced Models in Teno Convolutional Neural Networks with TensorFlow [Malaria Diagnosis] ⌨ (8:47:10) Functional API ⌨ (9:03:48) Model Subclassing ⌨ (9:19:05) Custom Layers First 2 parts, don't name function input, lenet_model, .... You will get errors when you call cell many time. In 9:18:26, the right is tf.zeros([1, IMSIZE, IMSIZE, 3]).
@@sarasalhi8 Hey, Is this course going to help for studying DQN or RL ,does it give an idea before jumping into libraries like Pytorch and OpenCV?, i mean ,if it's not , I can save my time :)
@@ajstatus9014 Honestly there's an incredibly complex field with many things in the video not explained well, I advice u to understand the basics before going for this tutorial
I bought the course on the site to support them. I do want to them to make more courses in the future and update their content. Anyone that can afford please do it? I just want them to be an incentive to teach more in the future.
@@Blackmamba77776 ML engineers are very in high demand. He is probably busy to be honest. It's really to edit and make videos with this quality he is making.
@@sonnguyen-t9r9d May be. But i think this course is a screen recording of an original video. At some times in the video i have seen the date on his computer and it would be 2020 i think or 2021
@@Blackmamba77776 sounds about right, during covid era. Libraries shouldn't have too much breaking changes. Luckily these videos are still relevant =D.
Forever grateful, I wish life was not so soul crushing for many of us who are intellectually curious yet find ourselves in an environment that is so limiting to the point that it’s become impossible to take advantage of these remarkable opportunities. If I make out, I’ll be a regular donor of this channel. I encourage those with mean to keep donating to this channel. If you are religious, this people are the modern day prophets and angels so pls show your gratitude and appreciations.
two hours and it is simple , good quality voice and complete , really complete , hope I can finish it I will update this comment untill finishing 37 hr
@@sathyamanikantabk4483 As this is free version of course so they don't teach maths that much deep, you have to learn Linear Algebra and Matrix Characteristics from other sources such as Khan's Academy. I haven't completed yet. Maybe i require more maths like Calculus, differential eqs etc.
@chris ibanez [GUITAR COVERS] and this is why you will not succeed in field of cs , just planning to binge it like its some overhyped netflix series arent you?
"Every expert was once a beginner. Don't be afraid to start at the bottom and work your way up." -unknown Week 1 (5 days Feb 4th to Feb 9th) ⌨ (0:12:12) Basics ⌨ (0:19:26) Initialization and Casting ⌨ (1:07:31) Indexing ⌨ (1:22:15) Starting Maths Operations Week 2 ( Feb12 ⌨ (2:58:15) Finished the linear algebra
I have some previous background in ML and Math, so for this course, it didn't take more than a week to finish, and no, I didn't sit all the day on it, just take what is important, read it, and keep moving on
This is insane! Two days of master class for free! This its changing the world. All you are creating the new under-professional workers, from thirds-world. Where wa cannot pay expansives university. Im really gatefull, i will put in my resume that Free Code Camp was my university (i cannot remember how much courses i allready make with you guys) Thanks a lot, starting this one today, lets see how much time takes me.
37 hours of course...ohh man... will take at least 37 days for me... amazing work Day 1: 09-01-2024: Start - 41:30 Day 2: 10-01-2024: 41:30 - 1:02:23 Day 3: 11-01-2024: 1:02:23 - 1:32:54 Day 4: 12-01-2024: 1:32:54 - 04:08:32
When the stars align in the exact right position... I am with you, sadly. I might have more YT playlists and LinkedIn Learning collections than hairs on my head... 😅😅😅😂 Ain't ever gonna happen "by itself" or "when you are motivated". You have to DO IT. Serious. The only way. JFDI! Good luck! 😊
Well bois.. So it begins. Goal is to get it done in 2 weeks. Day 1: 3 hours in! Day 3: 3 hours 10 mins in Day 7: 4 hrs and 30mins in! Day 9: 6:hrs 30mins in, completed car price prediction model
1:18:32 ,Below is the example in case you are wondering how to apply step in two dimension. tensor = tf.constant([[1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12]]) print(tensor[1:3:2, ::2])
I have finished the first 4 hrs and 15 min of the course (first part tensors and variables) I have to admit the instructor is amazing and explaining everything in details While I possess substantial knowledge in TensorFlow, I have derived significant benefits from it as well. thank you for this amazing content 33 hrs to go to complete the course
I watched it to Humans emotion detection part and am moving on. It was really impressive how you use technique. I hope I'll finish it even it will be in 2x speed. 🙂
@staggeredextreme8213 No, it's actually the best Deep Learning course with all sections. It teaches everything about deep learning. I just want to do some projects. Until YOLO it tells about CNN and its concept but after that it will tell about YOLO and GANs. So I want to do some projects about CNN. If I want to work on YOLO, I will come back and watch it again. Actually YOLO and GAN parts are like two separate small courses. I think the course ends at the 30th hour. If I want to be interested in YOLO and GAN, I think I will come and watch it later. That's why I said I'm not sure. Otherwise, the course is not bad.
@@isszadam5352 yeah thanks Adam! It's a great way of gaining 100% from the course and yeah i found it very useful till now, I'll make sure to cover all the basics and complete the lecture.
wait i have never saw this much ":" in a single timestamp of a video ........ Free Code Camp I am genuinely telling you guys ........ i have no words for appreciation I just wish you keep this always...........
I see lots of people putting their reading progress in the comments. To complete this course you will have to find the passion otherwise impossible (laziness because of the short formats). This is my 3rd time watching this course and I haven't quite grasped it all yet so don't expect to watch it just once.
"Sir can you please explain me the python..." Work through one good quality extensive course, code along, write down questions that come up, "google them" until you have the answers and then extend your knowledge from there using official documentation or SHORT very specific tutorials about very specific things. You will never learn and understand it YOURSELF, if you always ask for pre-chewed complete tutorials! Under each and every tutorial on youtube there are at least 10-20 "Sir can you please make a full toturial about x, y and z...." Comments.. 😑
I like how casually you guys upload a 37 Hours course. For free.
Vibhor singh you was not first, so you don't even try to claim that you are first in the comment section.
@@slip-shape994 when did I do that?
@@markxavior huh?
@@markxavior good Idea, I should admire you, finally you are here to learn something, a small step to learn something great, I admire your step. That's one small step for man, one giant leap for mankind.
@@thisbevibhor when did I say that you claimed.
The fact that this much knowledge is free is incredible. There is no excuse to be ignorant. These guys really care about educating the world in computer science. Mad respect, thank you.
It's free for sure, but useless too, can't understand what is happening
@@someshsaharan5813have you tried?
@@someshsaharan5813it means programming is not for you
@@someshsaharan5813 that means you need to pick a different career
@@alien_dev People like you are why people laugh at developers when we experience mass layoffs. And are you even working as a developer?
so far i have watched 13 hours of this video and i have learned so much more than any other courses. thank you so much for uploading this.
hi bro Is it worth seeing this course becoz I already seen videos from campus x deep learning playlist and I want to advance my knowledge
Note for myself.
-----------------------------
Stop watching at:
1:07:31 - 22.06
2:14:12 - 23.06
some problems - 24.06
2:48:52 - 25.06 (afternoon) | 3:00:00 - 25.06 (evening)
4:01:05 - 26.06
5:25:22 - 27.06
6:28:51 - 28.06
7:38:56 - 29.06
8:28:17 - 30.06
9:18:29 - 01.07
10:10:10 - 02.07
11:40:23 - 03.07
12:22:38 - 04.07
13:36:54 - 05.07
13:55:14 - 06.07 (A LOT of errors...)
14:07:11 - 07.07 (Finally fixed it)
14:43:57 - 08.07
14:56:59 - 09.07
15:21:05 - 10.07
15:48:30 - 11.07
16:12:16 - 12.07
16:26:30 - 13.07
16:34:20 - 14.07
16:39:12 - 15.07
17:14:22 - 16.07
17:14:42 - 19.07 (Fixed critical error named "broken pipe")
17:46:13 - 20.07
18:13:06 - 21.07
(Trying some experiments)
18:16:55 - 24.07
19:20:42 - 28.07
20:24:00- 30.07 (Problems with video card...)
20:30:05 - 01.08
21:34:54 - 03.08
21:46:47 - 06.08 (Fixed the main bug. Or didn't...)
22:30:33 - 15.08
22:54:54 - 16.08
23:34:57 - 21.08 (found another)
23:57:42 - 25.08
1:00:51:22 - 26.08
1:01:29:49 - 27.08
1:01:42:45 - 28.08
1:02:06:00 - 29.08
1:02:35:26 - 30.08,31.08
1:03:22:12 - 01.09 (from now I learn at nights, meaning it's not 01.09, but rather 01-02, 02-03 etc.)
1:03:58:32 - 02.09
1:04:30:14 - 03.09
1:05:23:37 - 04.09
1:06:51:37 - 11.09
1:07:30:47 - 14-15/09
1:07:58:33 - 16/09
1:08:26:54 - 17/09
1:08:32:47 - 18/09
1:09:02:25 - 19/09 (I will finish not later than early October.)
1:09:36:39 - 21/09
1:11:06:11 - 23/09
1:11:21:34 - 25/09
1:11:43:32 - 28/09
Done it. - 02/10 1:15 a.m.
Calculator says it's been 3 months and 1 week, don't care actually, cause I've written down the whole code, which author showed. The only problem is that I hardly remember the start of the course.
My tip for those who are only starting this course: if you have an error that brakes your entire code, and you struggle with it for days instead of actually learning, just use the author's colab code from the link in the description. It's a waste of time that isn't worth it, trust my word, I had a plenty of them.
Value your time.
-----------------------------
11:15:00 (+-10) - Pretty useful info
20:05:09 - man literally said 'feature' nearly 100 times in 5 minutes
is it really useful for you since you have put lot of effort into it
@@leoniff8987 Of course, it is! It's great to learn about something as interesting as machine learning in practice way. Now I want to get some python intermediate basics, and then practice on kaggle as much as possible as author suggested.
And one more thing to note, I've finished this course quite a long time ago, so I've forgotten some stuff already, but I can easily review it all by going through code I've written with all my experiments and comments.
Overall, this was very useful. Hope it will be useful for you too, just take note of tips I gave above.
Well come bruh ❤️
@@SourabhDey-yq7mr should i take this or not? i need your suggesation. i am new in CV
Can you share your code?
Day 1: Introduction
(0:00:00) Welcome
(0:05:54) Prerequisite
(0:06:11) What we shall Learn
(0:12:12) Basics
Day 2: Tensors and Variables - Part 1
(0:19:26) Initialization and Casting
(1:07:31) Indexing
Day 3: Tensors and Variables - Part 2
(1:16:15) Math Operations
Day 4: Tensors and Variables - Part 3
(1:55:02) Linear Algebra Operations
Day 5: Tensors and Variables - Part 4
(2:56:21) Common TensorFlow Functions
Day 6: Tensors and Variables - Part 5
(3:50:15) Ragged Tensors
(4:01:41) Sparse Tensors
Day 7: Tensors and Variables - Part 6
(4:04:23) String Tensors
(4:07:45) Variables
Day 8: Building Neural Networks with TensorFlow [Car Price Prediction] - Part 1
(4:14:52) Task Understanding
(4:19:47) Data Preparation
Day 9: Building Neural Networks with TensorFlow [Car Price Prediction] - Part 2
(4:54:47) Linear Regression Model
Day 10: Building Neural Networks with TensorFlow [Car Price Prediction] - Part 3
(5:10:18) Error Sanctioning
Day 11: Building Neural Networks with TensorFlow [Car Price Prediction] - Part 4
(5:24:53) Training and Optimization
Day 12: Building Neural Networks with TensorFlow [Car Price Prediction] - Part 5
(5:41:22) Performance Measurement
(5:44:18) Validation and Testing
Day 13: Building Neural Networks with TensorFlow [Car Price Prediction] - Part 6
(6:04:30) Corrective Measures
Day 14: Building Convolutional Neural Networks with TensorFlow [Malaria Diagnosis] - Part 1
(6:28:50) Task Understanding
(6:37:40) Data Preparation
Day 15: Building Convolutional Neural Networks with TensorFlow [Malaria Diagnosis] - Part 2
(6:57:40) Data Visualization
(7:00:20) Data Processing
Day 16: Building Convolutional Neural Networks with TensorFlow [Malaria Diagnosis] - Part 3
(7:08:50) How and Why ConvNets Work
Day 17: Building Convolutional Neural Networks with TensorFlow [Malaria Diagnosis] - Part 4
(7:56:15) Building Convnets with TensorFlow
Day 18: Building Convolutional Neural Networks with TensorFlow [Malaria Diagnosis] - Part 5
(8:02:39) Binary Crossentropy Loss
(8:10:15) Training Convnets
Day 19: Building Convolutional Neural Networks with TensorFlow [Malaria Diagnosis] - Part 6
(8:23:33) Model Evaluation and Testing
(8:29:15) Loading and Saving Models to Google Drive
Day 20: Building More Advanced Models in TensorFlow [Malaria Diagnosis] - Part 1
(8:47:10) Functional API
Day 21: Building More Advanced Models in TensorFlow [Malaria Diagnosis] - Part 2
(9:03:48) Model Subclassing
Day 22: Building More Advanced Models in TensorFlow [Malaria Diagnosis] - Part 3
(9:19:05) Custom Layers
Day 23: Evaluating Classification Models [Malaria Diagnosis] - Part 1
(9:36:45) Precision, Recall and Accuracy
Day 24: Evaluating Classification Models [Malaria Diagnosis] - Part 2
(10:00:35) Confusion Matrix
(10:10:10) ROC Plots
Day 25: Improving Model Performance [Malaria Diagnosis] - Part 1
(10:18:10) TensorFlow Callbacks
Day 26: Improving Model Performance [Malaria Diagnosis] - Part 2
(10:43:55) Learning Rate Scheduling
Day 27: Improving Model Performance [Malaria Diagnosis] - Part 3
(11:01:25) Model Checkpointing
(11:09:25) Mitigating Overfitting and Underfitting
Day 28: Data Augmentation [Malaria Diagnosis] - Part 1
(11:38:50) Augmentation with tf.image and Keras Layers
Day 29: Data Augmentation [Malaria Diagnosis] - Part 2
(12:38:00) Mixup Augmentation
(12:56:35) Cutmix Augmentation
Day 30: Data Augmentation [Malaria Diagnosis] - Part 3
(13:38:30) Data Augmentation with Albumentations
Day 31: Advanced TensorFlow Topics [Malaria Diagnosis] - Part 1
(13:58:35) Custom Loss and Metrics
Day 32: Advanced TensorFlow Topics [Malaria Diagnosis] - Part 2
(14:18:30) Eager and Graph Modes
Day 33: Advanced TensorFlow Topics [Malaria Diagnosis] - Part 3
(14:31:23) Custom Training Loops
Day 34: Tensorboard Integration [Malaria Diagnosis] - Part 1
(14:57:00) Data Logging
Day 35: Tensorboard Integration [Malaria Diagnosis] - Part 2
(15:29:00) View Model Graphs
(15:31:45) Hyperparameter Tuning
Day 36: Tensorboard Integration [Malaria Diagnosis] - Part 3
(15:52:40) Profiling and Visualizations
Day 37: MLOps with Weights and Biases [Malaria Diagnosis] - Part 1
(16:00:35) Experiment Tracking
Day 38: MLOps with Weights and Biases [Malaria Diagnosis] - Part 2
(16:55:02) Hyperparameter Tuning
Day 39: MLOps with Weights and Biases [Malaria Diagnosis] - Part 3
(17:17:15) Dataset Versioning
Day 40: MLOps with Weights and Biases [Malaria Diagnosis] - Part 4
(18:00:23) Model Versioning
Day 41: Human Emotions Detection - Part 1
(18:16:55) Data Preparation
Day 42: Human Emotions Detection - Part 2
(18:45:38) Modeling and Training
Day 43: Human Emotions Detection - Part 3
(19:36:42) Data Augmentation
Day 44: Human Emotions Detection - Part 4
(19:54:30) TensorFlow Records
Day 45: Modern Convolutional Neural Networks [Human Emotions Detection] - Part 1
(20:31:25) AlexNet
(20:48:35) VGGNet
Day 46: Modern Convolutional Neural Networks [Human Emotions Detection] - Part 2
(20:59:50) ResNet
Day 47: Modern Convolutional Neural Networks [Human Emotions Detection] - Part 3
(21:34:07) Coding ResNet from Scratch
Day 48: Modern Convolutional Neural Networks [Human Emotions Detection] - Part 4
(21:56:17) MobileNet
(22:20:43) EfficientNet
Day 49: Transfer Learning [Human Emotions Detection] - Part 1
(22:38:15) Feature Extraction
Day 50: Transfer Learning [Human Emotions Detection] - Part 2
(23:02:25) Finetuning
Day 51: Understanding the Blackbox [Human Emotions Detection] - Part 1
(23:15:33) Visualizing Intermediate Layers
Day 52: Understanding the Blackbox [Human Emotions Detection] - Part 2
(23:36:20) Gradcam method
Day 53: Transformers in Vision [Human Emotions Detection] - Part 1
(23:57:35) Understanding ViTs
Day 54: Transformers in Vision [Human Emotions Detection] - Part 2
(24:51:17) Building ViTs from Scratch
Day 55: Transformers in Vision [Human Emotions Detection] - Part 3
(25:42:39) FineTuning Huggingface ViT
Day 56: Transformers in Vision [Human Emotions Detection] - Part 4
(26:05:52) Model Evaluation with Wandb
Day 57: Model Deployment [Human Emotions Detection] - Part 1
(26:27:13) Converting TensorFlow Model to Onnx format
Day 58: Model Deployment [Human Emotions Detection] - Part 2
(26:52:26) Understanding Quantization
Day 59: Model Deployment [Human Emotions Detection] - Part 3
(27:13:08) Practical Quantization of Onnx Model
(27:22:01) Quantization Aware Training
Day 60: Model Deployment [Human Emotions Detection] - Part 4
(27:39:55) Conversion to TensorFlow Lite
(27:58:28) How APIs work
Day 61: Model Deployment [Human Emotions Detection] - Part 5
(28:18:28) Building an API with FastAPI
Day 62: Model Deployment [Human Emotions Detection] - Part 6
(29:39:10) Deploying API to the Cloud
(29:51:35) Load Testing with Locust
Day 63: Object Detection with YOLO - Part 1
(30:05:29) Introduction to Object Detection
Day 64: Object Detection with YOLO - Part 2
(30:11:39) Understanding YOLO Algorithm
Day 65: Object Detection with YOLO - Part 3
(31:15:17) Dataset Preparation
Day 66: Object Detection with YOLO - Part 4
(31:58:27) YOLO Loss
Day 67: Object Detection with YOLO - Part 5
(33:02:58) Data Augmentation
Day 68: Object Detection with YOLO - Part 6
(33:27:33) Testing
Day 69: Image Generation - Part 1
(33:59:28) Introduction to Image Generation
(34:03:18) Understanding Variational Autoencoders
Day 70: Image Generation - Part 2
(34:20:46) VAE Training and Digit Generation
Day 71: Image Generation - Part 3
(35:06:05) Latent Space Visualization
Day 72: Image Generation - Part 4
(35:21:36) How GANs work
Day 73: Image Generation - Part 5
(35:43:30) The GAN Loss
Day 74: Image Generation - Part 6
(36:01:38) Improving GAN Training
Day 75: Image Generation - Part 7
(36:25:02) Face Generation with GANs
You really work hard to write it 🙏🥺
Thank you 🙏
Thanks, this comment will provide a lot of help
This is what i need for becoming a self-taught machine learning engineer. Thank you all who made this possible.
how to get notes ?
kudos to you! I don't usually comment but I have to this time. I'm halfway through this course and I have 1 year of working experience in computer vision but still, there are a lot of new things I am learning in every lesson, and everything is perfectly explained.
It's impressive that knowledge like this is for free.
Finally an AI/ML/DL course with my pace & knowledge levels. All the courses out there just throw out some numbers and fancy formulas w/o reference of what/why/how, using terminologies which I have to google again to understand. I just watched first 20 mins just to get the feel for and I assure every one that come in here looking to learn, would definitely benefit w/o feeling anxious and self-doubt whether they fit in.
All the very best for the learners.
Start : 21 Dec 2023
Day 01 : 01:07:30 [Basics + Initialisation and Casting]
Day 02 : No Progress
Day 03 : 01:55:02 [Indexing + Maths Operations]
Day 04 : 02:15:10 [Linear Algebra Operations : multiply, transpose]
Day 05 : 04:07:46 [Linear Algebra Operations : det, adjoint, transpose, band_part, cholesky + Other types of Tensors like Ragged, Sparse, Strings]
Day 06 : 04:14:53 [Tensorflow Variables]
Day 07 : No Progress
Project 01 : Car Price Predictor
Day 08 : 04:54:47 [Data Preparation + Preprocessing]
Day 09 : No Progress
Day 10 : 06:28:52 [Completed Car Price Predictor]
Start : 20 Jan 2024
Project 02 : Malaria Diagnosis
come on bro, you do it!
@@youdontknow8729 yeah. but working on some other project right now.
did it go well?
Reminder to complete
Kar bhai
Awesome stuff.. This is my first tutorial towards getting into computer vision field so I'll be following along.
Day 1 -> 1:07:31
Day 2 -> 2:15:16
Day 3 -> 2:56:21
Day 4 -> None
Day 5 -> 3:50:15
Day 6 -> 4:15:00
Day 7 -> 5:10:20
what happend bro did u stopped this course? plz tell me
@@kelaelnolen7128 HE FELL!!!
@@kelaelnolen7128 lmao
This is super awesome. I have been studying tensorflow for a while and it's nice to have a revision this big. 🙏
😅😊😅
might as well stop studying
@@happyruimi-u3n yeah and turn into a nut job, nice advice there Hermit.
@@nocopyrightgameplaystockvi231you don't have any chance of thriving in this field
@@happyruimi-u3n that's exactly what I thought at first.
As machine learning finds increasing use in virtually every industry, there’s a growing need for people to bring machine learning models into production...this course is making that possible, thanks a ton freecodecamp & Neaural learn
Just by looking at the roadmap this is EXACTLY what I needed.
For now, I'm just impressed to see a 37 hr course for free. Will be back in a few weeks after I finish this.
how you are able to complete this long course in few weeks?
How far you reached in 4 days?
@@Nobody-co9dji wanna know too
@@Nobody-co9dj if you give 2 hours every day making notes and coding side by side, you can finish it in 20 days. Thats 3 weeks. The only problem is distractions and poor time management which prevents us from learning so many useful things
@@costamicaco That's not how it works.
Shre link kindly
Thank you for posting this. I recently signed up for computer engineering AI, this will surely help to get me ahead in college and the job interview.
This is insane!!! Hats off to your commitment to free education and knowledge sharing...
how to get notes ?
This is the best course I watch ever! It is so detailed and everything is covered so much that I simply have no words. Well done guys. You have shown how to actually make a tutorial.
This era need legend like you . Thank you
how to get notes ?
Day 1,2,3 - 11:38:50
Day-4,5 - 15:52:40
Coding Along is taking a lil bit more time, but doing till now.
where u at now
This is the dedication we all need
share ur notebook
At least you tried!
how to get notes ?
27:46 For wievers, you can use tf.random.uniform(shape, minval, maxval, dtype) to instantiate a 3d tensor.
I simply cant thank you guys enough the whole team for sharing such content to the world!. Where institutions charge u 10s if thousands of dollars for such degree . You are practically giving it away for free.
Thank you so much everyone . I can only imagine the less fortunate people finding this on the net would be a game changer for them
This channel is a blessing to the man kind
The level of technical knowledge is awesome. Never seen videos to go that much in depth for something like YOLO. Amazing work!
Starting: feb 9 2024 at 9:32 pm
Day2: no progress
Day3: 3:26:06
Day4: 5:02:49
Day5:no progress
Day6: 6:04:10
keep going bro
@@nguyentienanh5769 He probably left the course because his comment is 1 month old
Duality of men
Bro died trying
@@equalizer9923 RIP
Thanks a lot. I have been planning to join a course somewhere online but now i don't need to. Still can't believe you guys just posted such content for free. Thanks again.
Awesome course and projects on CNN! Love your work. P.S. (8:29:15) Loading and Saving Models to Google Drive : This section is just still screen. There's no change.
Start 14 jan 2024
day 1- (0:12:12) Basics
(0:19:26) Initialization and Casting
day 2- (1:07:31) Indexing
(1:16:15) Maths Operations
day 3- (1:55:02) Linear Algebra Operations
day 4- No progess
day 5-(3:50:15) Ragged Tensors
⌨ (4:01:41) Sparse Tensors
⌨ (4:04:23) String Tensors
⌨ (4:07:45) Variables
day 6- Revision
keep going bro
so I was searching for a course like this, finally found one! I aim to complete it before july end, today is 30th may, will start from tomorrow and update each time I open this video (maybe this motivation will help me continue)
god, I wasted my one month of vacation , let me not waste this too! fighting!!
Day 1: 00:08:20
Day 2: 01:00:00
Day 3: 03:02:51 (key concepts, needs revisiting)
Day 4: (29/08/24): 03:50:00
Day 5 : (01/09/24): 05:27:04 (model training)
Day 6: (08/09/24): 06:58:50 (linear regression and dense, data visualization for malaria diagnosis)
Day 7: (26/09/24): 08:20:45 (Malaria diagnosis)
Day 8: (28/09/24): 09:01:10 (finished with functional API)
Side note: does anyone else get a pay as you go issue on colab? any alternatives?
Day 9: (30/09/24): 09:59:07 (Important theory on recall and precision)
Day 10: (01/10/24): 10:44:50 (Calbacks)
Es la informacion que justo estaba buscando, ahi la llevo voy en el minuto 3.35 llevo 4 dias. Muchas Gracias por la informacion que compartes y lo facil que haces comprenderla.
No words. Hats off for this. Thanks a lot.
how to get notes ?
It is super helpful. Thank you very much. I have a lot of respect for free access.
I have a project at school related to Computer Vision which a field I have never learned. I WILL DECIDE TO COMPLETE THIS COURSE IN 2 WEEK.
THIS COMMENT WAS WRITTEN TO SHARE MY EXPERIENCE SO THAT THOSE NEW TO THE VIDEO CAN WATCH IT FASTER.
- If you have another laptop/PC or screen, you can watch and practise faster. Install microsoft mouse without borders in to workstation, if your workstation can't work with 2 screen. No one want ALT + TAB in 37 hours.
- I think almost people decide practise with this video are not zero. If you are zero, you should watch another video to get some define and theory about machine learning and computer vison before watch this. Because you can learn deeper and faster when reviewing concepts a second time and practise better and you don't want to seeking back and forth this 37 hours video
- Below the video description, there are work items. If you are determined, you should complete a item/subject/project before sleep. It will give you more motivation to survise these 37 hours of hell
+) DAY 1: I don't learn much today
⌨ (0:00:00) Welcome: Skip or listen if you want
⌨ (0:05:54) Prerequisite: Skip or listen if you want
⌨ (0:06:11) What we shall Learn: Skip or listen if you want
Tensors and Variables
⌨ (0:12:12) Basics : tf.constant, shape, ndim, dtype, cast, tf.zeros, tf.random
⌨ (0:19:26) Initialization and Casting: Nothing
⌨ (1:07:31) Indexing: All his code
⌨ (1:16:15) Maths Operations: tf.math.multi
⌨ (1:55:02) Linear Algebra Operations: tf.linalg.matmu, tf.transpose, tf.expand_dims
⌨ (2:56:21) Common TensorFlow Functions: learn all function
⌨ (3:50:15) Ragged Tensors: don't learn
⌨ (4:01:41) Sparse Tensors: learn
⌨ (4:04:23) String Tensors: don't learn.
⌨ (4:07:45) Variables: learn all
- DON'T WATCH WASTE YOUR TIME if you already have a little knowledge of linear algebra, get the code of one in the description, combined with chatgpt you will automatically understand how to use tensorflow which he has achieved. This will save you a ton of time and actually the math is more detailed but don't break into the math because this is not linear algebra. If you still don't understand, look at the part you don't understand.
- To me, these 4 hours of video are useless, it's really pointless to learn tensorflow because it is a library containing a lot of functions and you will only really need it when the project is relevant. And when problems occur, you will use chatgpt instead of the knowledge learned in these 4 hours. In my opinion, The above things are the most worth learning
+) DAY 2: I have a big homework and can't learn today
+) DAY 3:
Building Neural Networks with TensorFlow [Car Price Prediction]
⌨ (4:14:52) Task Understanding
⌨ (4:19:47) Data Preparation
⌨ (4:54:47) Linear Regression Model
⌨ (5:10:18) Error Sanctioning
⌨ (5:24:53) Training and Optimization
⌨ (5:41:22) Performance Measurement
⌨ (5:44:18) Validation and Testing
⌨ (6:04:30) Corrective Measures
Actually, I don't appreciate this project of his. He tried to introduce concepts to begginer, he integrated machine learning, linear regression, neutron network into one problem. The concepts of linear regression and how to train the model are explained quite well, but the neutron network is not very clear. I learned about neutron networks in college and it's actually a lot more detailed and easier to understand than here. This is an important topic and there is a lot of knowledge that needs to be imparted. It would be better if he taught the theory first and then practiced. The practice of both practicing and conveying is quite bad and has many shortcomings. In addition, dividing the dataset into 3 sets training_set, validation_set, test_set is usually done first but he puts it near the end, which upsets the logic.
+) Day 4 + 5:
Building Convolutional Neural Networks with TensorFlow [Malaria Diagnosis]
⌨ (6:28:50) Task Understanding
⌨ (6:37:40) Data Preparation
⌨ (6:57:40) Data Visualization: In his seaborn practise, visualization can give you information about dataset. You can detect more issue in your dataset and find orther method to solve
⌨ (7:00:20) Data Processing:
⌨ (7:08:50) How and Why ConvNets Work: Listen this carefully
⌨ (7:56:15) Building Convnets with TensorFlow
⌨ (8:02:39) Binary Crossentropy Loss
⌨ (8:10:15) Training Convnets
⌨ (8:23:33) Model Evaluation and Testing
⌨ (8:29:15) Loading and Saving Models to Google Drive: Colab is a virtual machine from Google and run linux os. You can save your model'architech (model layer -CNN/Dense/Pooling, loss function = RMSE, CrossEntropy, .... ) and model'weight after training. The worst thing in this section is it has only a image not video
Overview this project is great for everyone start to learn about CNN like me
Disadvantage: In fist section, he train model with 1 layer - 1 neutron to demonstrate linear regression. If he started with model has more dense layer, the project will be faster. Because the project is made to learn more theory, you must spent a little of time to complete this project
My experience:
- I was stuck at CNN concept a lot of time, I have read and watch more document to understand about it. This is my answer for everyone, don't understand after watch his CNN concept. In basic neutron, you have more input signal (X1, X2, ...XN) and a bias X0. It will come neutron, a neutron has 2 thing: Aggregate function and Activation Function. With basic neutron, the Aggregate function is
Net = f(X) = w0*X0 + w1* X1 + .... + wn*Xn
- Training a model is find W = [w0, w1, ... , wn] best fit with training set. If you choice that Aggrgate function, you must file a thousands parameter in training time with a neutron, and a huge parameter in model with more hidden layer, which has more netron in it.
- You can image Convolution Layer is a fully-conected layer has more neutron. The Aggregate function offeach neutron is replaced by convolution calculus with tensor of image input and a kernel matrix has size (k*k*number of chanel of image). By the way, instead of find wi for each Xi input signal/bias, you just find the weight of kernel matrix => You just find (k*k*number of chanel of image + 1) parameter for each neutron. Finaly, each neutron in convolution layer is called "fliter" , the ouput of layer is called "feature map"
- Google Colab limited time to use GPU, excecpt pay monney. When I train his model 2 times, I have reached limit. For everyone has a window laptop has NVIDIA GPU, install wsl 2 with Ubuntu distribution and install cuda+cdnn+clang+bazel in it. Note, you must install exactly version that fit with your tensorflow version (I have install tensorflow 2.16.1 with cland 17.0.2, bazel 6.5.0, cdnn 8..9 and cuda 12.3). Create a virrtual python environment 3.10 (if you install python 3.12 in it, you can't load dataset by his code. This is Dataset API of tensorflow 2.16.1 bug in the time I comment). Sea and following this video for sure th-cam.com/video/VE5OiQSfPLg/w-d-xo.html&pp=gAQBiAQ , you can create virtual python environment with anaconda like this video or use vevn model in python3
+) Day 6:
Building More Advanced Models in Teno Convolutional Neural Networks with TensorFlow [Malaria Diagnosis]
⌨ (8:47:10) Functional API
⌨ (9:03:48) Model Subclassing
⌨ (9:19:05) Custom Layers
First 2 parts, don't name function input, lenet_model, .... You will get errors when you call cell many time. In 9:18:26, the right is tf.zeros([1, IMSIZE, IMSIZE, 3]).
Thank you very much!
day1 : 37:00
day2 : 1:55:05
day3 : 3:02:42
day4 : 4:15:02
day5 : break
day6 : 4:54:49
day7 : 6:28:50
day7 : 7:37:44
day8 : 9:03:55
bro gave up💀
@@sckolver1361
nooo I just go back to the maching learning course of Andrew Ng + time is tight cuz university studies have begun
@@sarasalhi8 Hey, Is this course going to help for studying DQN or RL ,does it give an idea before jumping into libraries like Pytorch and OpenCV?, i mean ,if it's not , I can save my time :)
@@ajstatus9014
Honestly there's an incredibly complex field with many things in the video not explained well, I advice u to understand the basics before going for this tutorial
how can i get dataset of those that has been used in this video??
I bought the course on the site to support them. I do want to them to make more courses in the future and update their content. Anyone that can afford please do it? I just want them to be an incentive to teach more in the future.
I really like this gentleman's way of teaching and I would also like him to be active...
@@Blackmamba77776 ML engineers are very in high demand. He is probably busy to be honest. It's really to edit and make videos with this quality he is making.
@@sonnguyen-t9r9d May be. But i think this course is a screen recording of an original video. At some times in the video i have seen the date on his computer and it would be 2020 i think or 2021
@@Blackmamba77776 sounds about right, during covid era. Libraries shouldn't have too much breaking changes. Luckily these videos are still relevant =D.
Forever grateful, I wish life was not so soul crushing for many of us who are intellectually curious yet find ourselves in an environment that is so limiting to the point that it’s become impossible to take advantage of these remarkable opportunities. If I make out, I’ll be a regular donor of this channel. I encourage those with mean to keep donating to this channel. If you are religious, this people are the modern day prophets and angels so pls show your gratitude and appreciations.
two hours and it is simple , good quality voice and complete , really complete , hope I can finish it
I will update this comment untill finishing 37 hr
Prerequisites to take-up this course???
@@sathyamanikantabk4483 As this is free version of course so they don't teach maths that much deep, you have to learn Linear Algebra and Matrix Characteristics from other sources such as Khan's Academy. I haven't completed yet. Maybe i require more maths like Calculus, differential eqs etc.
How did it go?
After following it for the first 10 hours, I decided to buy it since I had gotten already so much value
Merci beaucoup pour votre cours, c'est un sujet super important que je voulais appréhender depuis longtemps❤
You just save us fcc ❤you guys are real heroes
Starting: APR 2, 2024, at 6:42 PM
Day01: --
Day02: 29:44
And?
How did it go?
This is exactly what i need , 3 hours of my day for the next 18 days
Sorry sir but 3 x 18 = 54 !!! You better start with a 'Basic Calculations' course first !!! 😂😂😂😂😂😂
@@ibanezjem1980 not necessarily, maybe he will repeat some chapters for better understanding
@chris ibanez [GUITAR COVERS] and this is why you will not succeed in field of cs , just planning to binge it like its some overhyped netflix series arent you?
@@antianti4331 yep , case on point
@@YourLocalCafe Certainly!!! This way they someday may improve!!!
Right in time. This is what I need. Thanks.
"Every expert was once a beginner. Don't be afraid to start at the bottom and work your way up." -unknown
Week 1 (5 days Feb 4th to Feb 9th)
⌨ (0:12:12) Basics
⌨ (0:19:26) Initialization and Casting
⌨ (1:07:31) Indexing
⌨ (1:22:15) Starting Maths Operations
Week 2 ( Feb12
⌨ (2:58:15) Finished the linear algebra
awesome video, you will be remember forever.😍
Thank you Steve jobs for this wonderful course.
I have some previous background in ML and Math, so for this course, it didn't take more than a week to finish, and no, I didn't sit all the day on it, just take what is important, read it, and keep moving on
Thank you for this free course
Tips for anyone who is going to starting this out.... play in 2X it can be completed in 17hours :)
This is insane! Two days of master class for free! This its changing the world. All you are creating the new under-professional workers, from thirds-world. Where wa cannot pay expansives university.
Im really gatefull, i will put in my resume that Free Code Camp was my university (i cannot remember how much courses i allready make with you guys)
Thanks a lot, starting this one today, lets see how much time takes me.
37 hours is like a semester of learning, not two days.
Really thankful for what you guys do 🙇🏻
this tutorial helped me how to use documentation
37 hours of course...ohh man... will take at least 37 days for me... amazing work
Day 1: 09-01-2024: Start - 41:30
Day 2: 10-01-2024: 41:30 - 1:02:23
Day 3: 11-01-2024: 1:02:23 - 1:32:54
Day 4: 12-01-2024: 1:32:54 - 04:08:32
u stopped ?
You failed
I’ve saved so many of these long full course videos, and I’m gonna watch them, eventually.
😂 sure
When the stars align in the exact right position...
I am with you, sadly. I might have more YT playlists and LinkedIn Learning collections than hairs on my head... 😅😅😅😂
Ain't ever gonna happen "by itself" or "when you are motivated". You have to DO IT. Serious. The only way. JFDI! Good luck! 😊
Just unbelievable, we can get this free!!!
Long live, bro!
You are amazing Sir.
You just upload hours in a simple way❤❤❤❤❤❤.
I Olivier committed to start this course on Tuesday 20/2/204 until I'm going to finish,
see you and the end date.
Are you still up to it?
Well bois.. So it begins. Goal is to get it done in 2 weeks.
Day 1: 3 hours in!
Day 3: 3 hours 10 mins in
Day 7: 4 hrs and 30mins in!
Day 9: 6:hrs 30mins in, completed car price prediction model
Wat is the prerequisites??
@@sathyamanikantabk4483 Nothing bro, he kinda seems to be explaining everything he does.. so you should be fine.
If it is a really in depth course that warrants a runtime of 37 hours, then thank you.
Is it for complete beginners?
@@neoreign Certainly not
You guys are heroes man... seriously
1:18:32 ,Below is the example in case you are wondering how to apply step in two dimension.
tensor = tf.constant([[1, 2, 3],
[4, 5, 6],
[7, 8, 9],
[10, 11, 12]])
print(tensor[1:3:2, ::2])
SIS YOU COMPLETED IT ? the whole course ?
Day 1: 1:07:31
Day 2: 1:55:02
Day 3: 4:54:47
us k agay?
this is really perfect
This channel provides more value than any other channel without a doubt
FIRST TIME WITH DEEP LEARNING
day1 - 2:56:21
day2-nil
day3 - 4:14:52
day4-nil
day5- 6:28:50
day6- 8:47:10
day7-10:00:00
did you find any error while doing project 1 of car price prediction ? i am getting an error
@@hasrat_ali No, i did not find any error
I can share my github repo if needed
The Good teacher ever i seen ❤
love from Bangladesh, thanks for giving 37hr free course❤
I have finished the first hour of this video, I hope I can be consistent and complete it :)
I finished the first 2 hr of the course now, 35 hrs to go💪
Great Explanation, a lot of useful functions to deal with tensors
I have finished the first 4 hrs and 15 min of the course (first part tensors and variables)
I have to admit the instructor is amazing and explaining everything in details
While I possess substantial knowledge in TensorFlow, I have derived significant benefits from it as well.
thank you for this amazing content 33 hrs to go to complete the course
Are you still up to it?
This is very nice!
Thanks for this people
This Channel is making an Ocean of Skills
Thanks!
I watched it to Humans emotion detection part and am moving on. It was really impressive how you use technique. I hope I'll finish it even it will be in 2x speed. 🙂
How much you finished it?
@@staggeredextreme8213 I finished 24 hours now. But I'm not sure I keep watching. Maybe I'll watch until the YOLO part.
@@selcukozdemir8941 hey why you aren't sure ? Is it worth watching?
@staggeredextreme8213 No, it's actually the best Deep Learning course with all sections. It teaches everything about deep learning. I just want to do some projects. Until YOLO it tells about CNN and its concept but after that it will tell about YOLO and GANs. So I want to do some projects about CNN. If I want to work on YOLO, I will come back and watch it again. Actually YOLO and GAN parts are like two separate small courses. I think the course ends at the 30th hour. If I want to be interested in YOLO and GAN, I think I will come and watch it later. That's why I said I'm not sure. Otherwise, the course is not bad.
@@isszadam5352 yeah thanks Adam! It's a great way of gaining 100% from the course and yeah i found it very useful till now, I'll make sure to cover all the basics and complete the lecture.
Thanks for your program and information
Is this course right choice for begineers?
Love it. Anything is possible with the internet.
جااااامدددد اجدعاااااان
Hello sir and a great thank for this wonderful course which will help me in my research
7:12:30 receptive field
I feel thankful for this video
wait i have never saw this much ":" in a single timestamp of a video ........
Free Code Camp I am genuinely telling you guys ........ i have no words for appreciation I just wish you keep this always...........
We need Artificial Intelligence, Machine learning, deep learning courses
Check out this machine learning playlist: th-cam.com/play/PLWKjhJtqVAblStefaz_YOVpDWqcRScc2s.html
aint no way they released such a detailed course for free that's over a day!
I see lots of people putting their reading progress in the comments. To complete this course you will have to find the passion otherwise impossible (laziness because of the short formats). This is my 3rd time watching this course and I haven't quite grasped it all yet so don't expect to watch it just once.
want to learn as fast as possible, hence skipping the first part , and starting from 4:14:52.
day1: 4:14:52
day2: 5:10:00
The 33 hours was worth it. Thanks for the tutorial
but there was 37. did you mean that first 4 hours with introducing to tensorflow basics was excess?
This is great!
Day 1, 2 - 6:42:18
Till now its just amazing.
Nice dude so fast u did let's connect
@@notacoder2159 sure
but i was busy for these days so started again today
are you just watching the video? or coding along also?
@@anonymoustechnopath1138 great r u on LinkedIn
@@improv2736 coding along is mandatory for learning
Many thanks to you!
Hi, thanka for such an amazing course. Can you please make a complete course on human activity detection, video classification using RNN and CNNs.
"Sir can you please explain me the python..."
Work through one good quality extensive course, code along, write down questions that come up, "google them" until you have the answers and then extend your knowledge from there using official documentation or SHORT very specific tutorials about very specific things.
You will never learn and understand it YOURSELF, if you always ask for pre-chewed complete tutorials!
Under each and every tutorial on youtube there are at least 10-20 "Sir can you please make a full toturial about x, y and z...." Comments.. 😑
First when I saw the title i got really excited. 37hrs really sucked all the energy out.
Detailed course on complex subject = bad
ok
i prefer the longer ones cause it means that is more in depth and detailed... i really hate when they only scratch the basics and just copy paste code
Seriously, everyone praises a free 37 hour course like that’s a good thing. Sometimes, less is more.
@@erniea5843 sometimes you can just move on instead of bashing someone doing tremendous job for free
thank you very much!!
What is the prerequisites for starting this course?
Thankyou so much❤
amazing course!
waiting for NLP long videos on freecodecamp. thanks neuralearn and freecodecamp.
Great 🎉 Thank you
FreeCodeCamp are heroes!