ronghanghu / Natural Language Object Retrieval
Licence: other
Code release for Hu et al. Natural Language Object Retrieval, in CVPR, 2016
Stars: ✭ 110
Labels
Projects that are alternatives of or similar to Natural Language Object Retrieval
Wifi activity recognition
Code for IEEE Communication Magazine (A Survey on Behaviour Recognition Using WiFi Channle State Information)
Stars: ✭ 109 (-0.91%)
Mutual labels: jupyter-notebook
Kubeflowdojo
Repository to hold code, instructions, demos and pointers to presentation assets for Kubeflow Dojo
Stars: ✭ 110 (+0%)
Mutual labels: jupyter-notebook
Hgn
Hierarchical Gating Networks for Sequential Recommendation
Stars: ✭ 110 (+0%)
Mutual labels: jupyter-notebook
Monetizing Machine Learning
Source code for 'Monetizing Machine Learning' by Manuel Amunategui and Mehdi Roopaei
Stars: ✭ 110 (+0%)
Mutual labels: jupyter-notebook
Credit score
data from the kaggle 'give me some credit" competition
Stars: ✭ 109 (-0.91%)
Mutual labels: jupyter-notebook
Introduction To Linear Programming
Introduction to Linear Programming with Python
Stars: ✭ 110 (+0%)
Mutual labels: jupyter-notebook
Nvidia Gpu Tensor Core Accelerator Pytorch Opencv
A complete machine vision container that includes Jupyter notebooks with built-in code hinting, Anaconda, CUDA-X, TensorRT inference accelerator for Tensor cores, CuPy (GPU drop in replacement for Numpy), PyTorch, TF2, Tensorboard, and OpenCV for accelerated workloads on NVIDIA Tensor cores and GPUs.
Stars: ✭ 110 (+0%)
Mutual labels: jupyter-notebook
Sklearn
Data & Code associated with my tutorial on the sci-kit learn machine learning library in python
Stars: ✭ 110 (+0%)
Mutual labels: jupyter-notebook
Mtcnn
MTCNN face detection implementation for TensorFlow, as a PIP package.
Stars: ✭ 1,689 (+1435.45%)
Mutual labels: jupyter-notebook
Cs231n Convolutional Neural Networks Solutions
Assignment solutions for the CS231n course taught by Stanford on visual recognition. Spring 2017 solutions are for both deep learning frameworks: TensorFlow and PyTorch.
Stars: ✭ 110 (+0%)
Mutual labels: jupyter-notebook
Spark R Notebooks
R on Apache Spark (SparkR) tutorials for Big Data analysis and Machine Learning as IPython / Jupyter notebooks
Stars: ✭ 109 (-0.91%)
Mutual labels: jupyter-notebook
Google Images Dataset
This repository provides the necessary code to create your own Google Images Dataset.
Stars: ✭ 110 (+0%)
Mutual labels: jupyter-notebook
Pymc3 vs pystan
Personal project to compare hierarchical linear regression in PyMC3 and PyStan, as presented at http://pydata.org/london2016/schedule/presentation/30/ video: https://www.youtube.com/watch?v=Jb9eklfbDyg
Stars: ✭ 110 (+0%)
Mutual labels: jupyter-notebook
Bigquery Tutorial
Google BigQuery Tutorial for Data Analyst
Stars: ✭ 110 (+0%)
Mutual labels: jupyter-notebook
Natural Language Object Retrieval
This repository contains the code for the following paper:
- R. Hu, H. Xu, M. Rohrbach, J. Feng, K. Saenko, T. Darrell, Natural Language Object Retrieval, in Computer Vision and Pattern Recognition (CVPR), 2016 (PDF)
@article{hu2016natural,
title={Natural Language Object Retrieval},
author={Hu, Ronghang and Xu, Huazhe and Rohrbach, Marcus and Feng, Jiashi and Saenko, Kate and Darrell, Trevor},
journal={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
year={2016}
}
Project Page: http://ronghanghu.com/text_obj_retrieval
Installation
- Download this repository or clone with Git, and then
cd
into the root directory of the repository. - Run
./external/download_caffe.sh
to download the SCRC Caffe version for this experiment. It will be downloaded and unzipped intoexternal/caffe-natural-language-object-retrieval
. This version is modified from the Caffe LRCN implementation. - Build the SCRC Caffe version in
external/caffe-natural-language-object-retrieval
, following the Caffe installation instruction. Remember to also build pycaffe.
SCRC demo
- Download the pretrained models with
./models/download_trained_models.sh
. - Run the SCRC demo in
./demo/retrieval_demo.ipynb
with Jupyter Notebook (IPython Notebook).
Train and evaluate SCRC model on ReferIt Dataset
- Download the ReferIt dataset:
./datasets/download_referit_dataset.sh
. - Download pre-extracted EdgeBox proposals:
./data/download_edgebox_proposals.sh
. - You may need to add the SRCR root directory to Python's module path:
export PYTHONPATH=.:$PYTHONPATH
. - Preprocess the ReferIt dataset to generate metadata needed for training and evaluation:
python ./exp-referit/preprocess_dataset.py
. - Cache the scene-level contextual features to disk:
python ./exp-referit/cache_referit_context_features.py
. - Build training image lists and HDF5 batches:
python ./exp-referit/cache_referit_training_batches.py
. - Initialize the model parameters and train with SGD:
python ./exp-referit/initialize_weights_scrc_full.py && ./exp-referit/train_scrc_full_on_referit.sh
. - Evaluate the trained model:
python ./exp-referit/test_scrc_on_referit.py
.
Optionally, you may also train a SCRC version without contextual feature, using python ./exp-referit/initialize_weights_scrc_no_context.py && ./exp-referit/train_scrc_no_context_on_referit.sh
.
Train and evaluate SCRC model on Kitchen Dataset
- Download the Kitchen dataset:
./datasets/download_kitchen_dataset.sh
. - You may need to add the SRCR root directory to Python's module path:
export PYTHONPATH=.:$PYTHONPATH
. - Build training image lists and HDF5 batches:
python exp-kitchen/cache_kitchen_training_batches.py
. - Train with SGD:
./exp-kitchen/train_scrc_kitchen.sh
. - Evaluate the trained model:
python exp-kitchen/test_scrc_on_kitchen.py
.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].