All Projects → huseinzol05 → Yolo Object Detection Tensorflow

huseinzol05 / Yolo Object Detection Tensorflow

Licence: mit
YOLO: Real-Time Object Detection using Tensorflow and easy to use

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Yolo Object Detection Tensorflow

Tracking With Darkflow
Real-time people Multitracker using YOLO v2 and deep_sort with tensorflow
Stars: ✭ 515 (+1044.44%)
Mutual labels:  convolutional-neural-networks, yolo
Carnd Vehicle Detection
Vehicle detection using YOLO in Keras runs at 21FPS
Stars: ✭ 367 (+715.56%)
Mutual labels:  convolutional-neural-networks, yolo
Yolo tensorflow
🚖 Object Detection (YOLOv1) implentation in tensorflow, with training, testing and video features.
Stars: ✭ 45 (+0%)
Mutual labels:  convolutional-neural-networks, yolo
Dmsmsgrcg
A photo OCR project aims to output DMS messages contained in sign structure images.
Stars: ✭ 18 (-60%)
Mutual labels:  convolutional-neural-networks, yolo
Gender Age Classification
gender/age classification
Stars: ✭ 39 (-13.33%)
Mutual labels:  yolo
Teacher Student Training
This repository stores the files used for my summer internship's work on "teacher-student learning", an experimental method for training deep neural networks using a trained teacher model.
Stars: ✭ 34 (-24.44%)
Mutual labels:  convolutional-neural-networks
Deepmodels
TensorFlow Implementation of state-of-the-art models since 2012
Stars: ✭ 33 (-26.67%)
Mutual labels:  convolutional-neural-networks
Lane Detector
This repository is for my article "Tutorial: Build a lane detector" published on Medium.
Stars: ✭ 31 (-31.11%)
Mutual labels:  convolutional-neural-networks
Efficientnas
Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search https://arxiv.org/abs/1807.06906
Stars: ✭ 44 (-2.22%)
Mutual labels:  convolutional-neural-networks
Dynamic Gcnn
Dynamic Graph Convolutional Neural Network for 3D point cloud semantic segmentation
Stars: ✭ 42 (-6.67%)
Mutual labels:  convolutional-neural-networks
Tensorflowhandwritingrecognition
Using Tensorflow to classify the NIST Dataset 19 (Handwriting)
Stars: ✭ 39 (-13.33%)
Mutual labels:  convolutional-neural-networks
Constrained attention filter
(ECCV 2020) Tensorflow implementation of A Generic Visualization Approach for Convolutional Neural Networks
Stars: ✭ 36 (-20%)
Mutual labels:  convolutional-neural-networks
Hardhat Detector
A convolutional neural network implementation of a script that detects whether an individual is wearing a hardhat or not.
Stars: ✭ 41 (-8.89%)
Mutual labels:  convolutional-neural-networks
Tensorflow Srgan
Tensorflow implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network" (Ledig et al. 2017)
Stars: ✭ 33 (-26.67%)
Mutual labels:  convolutional-neural-networks
Computervision Recipes
Best Practices, code samples, and documentation for Computer Vision.
Stars: ✭ 8,214 (+18153.33%)
Mutual labels:  convolutional-neural-networks
Pathology Images Analysis Using Cnn
Scripts for https://www.nature.com/articles/s41598-018-27707-4, using Convolutional Neural Network to detect lung cancer tumor area
Stars: ✭ 31 (-31.11%)
Mutual labels:  convolutional-neural-networks
Pro gan pytorch Examples
Examples trained using the python pytorch package pro-gan-pth
Stars: ✭ 39 (-13.33%)
Mutual labels:  convolutional-neural-networks
Jsi Gan
Official repository of JSI-GAN (Accepted at AAAI 2020).
Stars: ✭ 42 (-6.67%)
Mutual labels:  convolutional-neural-networks
Textclassifier
Text classifier for Hierarchical Attention Networks for Document Classification
Stars: ✭ 985 (+2088.89%)
Mutual labels:  convolutional-neural-networks
Reading comprehension tf
Machine Reading Comprehension in Tensorflow
Stars: ✭ 37 (-17.78%)
Mutual labels:  convolutional-neural-networks

YOLO-Object-Detection-Tensorflow

YOLO: Real-Time Object Detection using Tensorflow and easy to use.

Information

  • I will get back soon for the issues, pretty busy.

  • I found it this YOLO not able to train.

Results

alt text alt text

Instructions

  1. Make sure check settings.py before start to train
# remove elements that you don't want
# default objects from VOC 2012
classes_name =  ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
classes_no = [i for i in xrange(len(classes_name))]
classes_dict = dict(zip(classes_name, classes_no))

image_size = 448
cell_size = 7
box_per_cell = 2
alpha_relu = 0.2
object_scale = 2.0
no_object_scale = 1.0
class_scale = 2.0
coordinate_scale = 5.0
flipped = True

decay_step = 30000
decay_rate = 0.1
learning_rate = 0.0001
dropout = 0.5
batch_size = 3
epoch = 1000
checkpoint = 1000

# For main
threshold = 0.2
IOU_threshold = 0.5
test_percentage = 0.05

# 1 for read a picture
# 2 to read from testing dataset
# 3 to read from webcam / video
output = 1
# let empty if want to capture from webcam
picture_name = ''
video_name = ''
  1. You must download VOC 2012 and put in the same folder for multibox dataset
  2. You need to put YOLO_small.ckpt in the same folder (optional) if you want to use pretrained model, but if you want to train the model by your own, follow 3.*
    1. You can train your own model from scratch in train-classification folder
    2. Put your images that you want to classify in train-classification/data/ (need to create it)
    3. If you satisfied enough your model, copy model.ckpt into main folder
/
/train-classification
/train-classification/data/
/train-classification/data/fish/
/train-classification/data/cow/
.. so on
python train.py
  1. you must train.py in main directory first before main.py (unless if you downloaded YOLO_small.ckpt)
python train.py
  1. test in main
python main.py

More results

alt text alt text alt text

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].