Видео

In this video, we will take up a question asked by one of the subscribers. The question has four parts, basically, what is attention with LSTM and what is the use of that. We also delve into the aspect of Transformers and how is it better than LSTMs.

In this video, we are going to see how to do language classification using Mediapipe. Basically, we are going to give a text to the model and the model is expected to find out which language does the text belong to. There are 110 languages that the model can classify. Code: github.com/DatumLearning/Mediapipe-playlist/blob/main/Language_detector.ipynb

In this video, we are going to cover the text embedder in Mediapipe. This model can also be used to convert a sentence of any length to a fixed vector of 512 length. This task can help take two sentences and then find the cosine similarity between the two sentences. The sentences focusing on similar ideas have a higher degree of similarity. Code: github.com/DatumLearning/Mediapipe-playlist/blob...

In this video, we are going to cover the text classification using Mediapipe. The model is based on BERT and can do sentiment analysis. Code: github.com/DatumLearning/Mediapipe-playlist/blob/main/text_classification.ipynb

In this video, we are going to see how can we stylize a face in Mediapipe. This is an experimental feature but a powerful one. It can be used for creating avatars. Code: github.com/DatumLearning/Mediapipe-playlist/blob/main/face_stylization.ipynb

In this video, we are going to see how can we find the pose landmarks of an individual in an image using the Pose Landmark Detection functionality in Mediapipe. We will also see how can we plot the points on an image. Code: github.com/DatumLearning/Mediapipe-playlist/blob/main/Pose_Landmarks.ipynb

In this video, we are going to see the next function in PyTorch which is the MaxPool2d function. We will also be looking into its parameters. The Maxpool2d operation is used in CNNs to reduce the height and width of the feature maps. Code: github.com/DatumLearning/PyTorch_functions/blob/main/17_maxpool2d.ipynb

In this video, we are going to see the last remaining parameters of the Convolution operation in PyTorch. We will be focusing on groups, bias the formula for finding the shape of the output of the convolution operation. Groups will be discussed in convolution and we will also see depthwise convolution. We will also see what bias is in the convolution operation. Lastly, we will also see the form...

In this video, we are going to see the some more parameters of the nn.Conv2d function in the torch.nn module. We will looking into the padding, padding_mode and the dilation parameters of torch.nn. We will go in detail into understanding the padding parameter of nn.conv2d. We will understand what values it can take and what do they mean. Secondly, we will understand the different padding_modes ...

In this video, we are going to see how can we implement face landmarks detection and facial expression classification in Mediapipe. We will find the correct facial expression and also the coordinates of the landmarks in the face of a person. Code: github.com/DatumLearning/Mediapipe-playlist/blob/main/face_landmarks.ipynb

In this video, we are going to see how to detect faces in images using the Face detection module of the Mediapipe. We will also see how to get the keypoints in an image and also to see how to plot the bounding box. Code: github.com/DatumLearning/Mediapipe-playlist/blob/main/face_detection.ipynb

In this video, we are going to see how can we find the hand landmarks in the Hand Landmarks Detection task in Mediapipe. We will also see how to interpret the result of the detections. We will see how to isolate a particular point in the image and plot it. Code: github.com/DatumLearning/Mediapipe-playlist/blob/main/hand_landmark_detection.ipynb

In this video, we are going to find the gesture of the hand as shown in the image. We will also see how to find the co-ordinates of the different points on the hand. Code: github.com/DatumLearning/Mediapipe-playlist/blob/main/gesture_recognition.ipynb

In this video, we are going to see how can we find the image embedding of an image using Mediapipe. This will be useful to find the similar images from an image database. We will be using the cosine similarity to find the similar images. Code: github.com/DatumLearning/Mediapipe-playlist/blob/main/gesture_recognition.ipynb

#AskDL Will Mediapipe and OpenCV be relevant? | Ask your questions on the daily #AskDL post hashtag

nn.Conv2d | Part - 1 fully discussed | in & out channels, stride, kernel_size | PyTorch functions

Ep - 1 | Intro and Data | Audio Classification in PyTorch Project | Urban Sound classification CNN

Instance image segmentation using Mediapipe | Segment one object in an image

Discussion on ChatBots in AI | Simple to Advanced Chatbots.

Coding and AI in College | Useful tips for someone starting with AI and Coding in College.

Yolov10 object on a video using CLI.

Ep - 7 | Results and Test function| Bird Classification project in Deep Learning using PyTorch

YOLOv10 Object Detection in Python | Object detection using YOLO in Python

Ep - 6 | Writing the validation fn | Bird Classification project in Deep Learning using PyTorch

Ep - 5 | Writing the train function | Bird Classification project in Deep Learning using PyTorch

Ep - 4 | Writing the model | Bird Classification project in Deep Learning using PyTorch

Ep - 3 | transforms and DataLoader | Bird Classification project in Deep Learning using PyTorch

#AskDL Can we use pretrained word embedding in PyTorch | Discussion on nn.Embedding in PyTorch

Ep - 2 | Setting up - libraries & paths | Bird Classification project in Deep Learning using PyTorch