Deep-Learning_projects

1. #####HimanshuLa1.ipynb##### Housing clasification problem floated on kaggle language- python3 dependancy- jupyter notebook, numpy, pandas, scipy and skit-learn.

2. ######Tiny ImageNetClassification ######## language- python3 dependancy- jupyter notebook, numpy, pandas, scipy, open-cv and skit-learn. dataset link- https://www.kaggle.com/c/tiny-imagenet/data the desingned network is developed for general purpose computer. Dataset contains 200 object classes and each object has 500 images for training purpose. model is developed on tensorflow framework contains convolution layer for extracting the feature from an image and fullyconnected layer with softmax regression in order to choose appropriate features.

3. #######Audio Analysis using deep learning######///[Himanshu kumar], [Chetan Chawla]. reference link- https://www.analyticsvidhya.com/blog/2017/08/audio-voice-processing-deep-learning/ The Urban Sound challenge was floated and the problem is meant to introduce for audio processing in the usual classification scenario. -model is implemented on keras framework and librose librairy is used for loding .wav file in the model. Step 1: Load audio files Step 2: Extract features from audio Step 3: Convert the data to pass it in our deep learning model Step 4: Run a deep learning model and get results

The dataset contains 8732 sound excerpts (<=4s) of urban sounds from 10 classes, namely:

air conditioner, car horn, children playing, dog bark, drilling, engine idling, gun shot, jackhammer, siren, and street music

4. #####NLP(multi_classification)###### dataset link-https://drive.google.com/drive/folders/13TuJvgEcWlUY7-q7TSld6P4K7J0C1R1U the objective is to Train models to predict gender, category,sub_cat,sub_sub_cat of the product. In the given dataset "title" and "desciption" use as input for pridiction of several categories. generated_output links-https://drive.google.com/file/d/1ievkLH2Zy7_C4HXpWBfIumn5xi_mUzwM/view?usp=sharing https://drive.google.com/file/d/1cNrj_i3r40T7938dSFvc_GXtmisbf8kb/view?usp=sharing https://drive.google.com/file/d/1ruWPQHwyzNRVvupbAMnstTJCsI-0EEub/view?usp=sharing https://drive.google.com/file/d/1Z5wAXpyGtfIZR2GLTfST1OmGIWw1u3xQ/view?usp=sharing

5. ######NLP(multi-text-classification)#### dataset link-https://drive.google.com/open?id=1xOLj5hcJ9E_h_CGCi0J13ZUA_u5sRHf5 categories- tech, business, sport label, politics, entertainment model- tensorflow used in backend of keras and RNN is used to predict the category accuracy achieved- 80.003% notebook link- https://colab.research.google.com/drive/1m_CkbBm5EdKCRjAL-tmGUWVdQbqCNQAk