RNN

01- RNN_Classification

Simple RNN training for classification task of 3 signal: Sine, Square, Triangle.

02- RNN_Regression

Simple RNN training for sine wave estimation.

03- RNN_vs_GRU_Classification

Comparison of RNN model and GRU model for classification task of 3 signal: Sine, Square and Triangle, after 100 epoch training.

04- RNN_vs_GRU_Regression

Comparison of RNN model and GRU model for regression task of sine wave estimation after 100 epoch training.

05- Ball_Move_Data_Generation

Generate data for ball move direction

06- GRU_Implementation_from_Scratch

GRU implementation from scratch + inference

07-LSTM_Implementation_from_Scrat

LSTM implementation from scratch + inference

08- Ball_Move_Direction_Classification

• Generate data for ball move direction

• Classification of direction using RNN, GRU and LSTM

09- VideoClassificationCRNN

• 09- Video_Classification_CRNN.ipynb(train)
• inference.py
• models.py (gru, lstm, rnn)
• load_video.py
• requirements.txt

Model

Backbone: ResNet50V2 and my vgg base model for feature extraction

RNN modules: RNN, GRU and LSTM are tested

The performance of GRU module was better than other madules

Dataset

Dataset contains videos from 2 classes

Due to insufficient data, the training was not done well. but this project can be used for other video classification tasks using CRNNs

10- Video_Classification_CRNN

• Video classificatio nusing CRNN on ucf101_top5 dataset

Model

Backbone: my vgg base model for feature extraction

RNN modules: RNN, GRU are tested

The performance of GRU module was better than RNN madules

Dataset

• ucf101_top5 dataset containing 573 video from 5 classes

Result