GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → utsavgarg → tensorflow-classification

utsavgarg / tensorflow-classification

Licence: other
A unified program to check predictions of different convolutional neural networks for image classification.

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Labels

deep-learningtensorflowimage-classification

Projects that are alternatives of or similar to tensorflow-classification

pytorch-cifar-model-zoo
Implementation of Conv-based and Vit-based networks designed for CIFAR.
Stars: ✭ 62 (-8.82%)
Mutual labels:  image-classification
metric-transfer.pytorch
Deep Metric Transfer for Label Propagation with Limited Annotated Data
Stars: ✭ 49 (-27.94%)
Mutual labels:  image-classification
sinkhorn-label-allocation
Sinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms. The SLA algorithm is described in full in this ICML 2021 paper: https://arxiv.org/abs/2102.08622.
Stars: ✭ 49 (-27.94%)
Mutual labels:  image-classification
Image-Classification
Pre-trained VGG-Net Model for image classification using tensorflow
Stars: ✭ 29 (-57.35%)
Mutual labels:  image-classification
TensorFlow-Multiclass-Image-Classification-using-CNN-s
Balanced Multiclass Image Classification with TensorFlow on Python.
Stars: ✭ 57 (-16.18%)
Mutual labels:  image-classification
MixNet-PyTorch
Concise, Modular, Human-friendly PyTorch implementation of MixNet with Pre-trained Weights.
Stars: ✭ 16 (-76.47%)
Mutual labels:  image-classification
head-network-distillation
[IEEE Access] "Head Network Distillation: Splitting Distilled Deep Neural Networks for Resource-constrained Edge Computing Systems" and [ACM MobiCom HotEdgeVideo 2019] "Distilled Split Deep Neural Networks for Edge-assisted Real-time Systems"
Stars: ✭ 27 (-60.29%)
Mutual labels:  image-classification
serving-pytorch-models
Serving PyTorch models with TorchServe 🔥
Stars: ✭ 91 (+33.82%)
Mutual labels:  image-classification
KerasUI
UI for Keras to implement image classification written in python and django
Stars: ✭ 40 (-41.18%)
Mutual labels:  image-classification
jpetstore-kubernetes
Modernize and Extend: JPetStore on IBM Cloud Kubernetes Service
Stars: ✭ 21 (-69.12%)
Mutual labels:  image-classification
aitlas
AiTLAS implements state-of-the-art AI methods for exploratory and predictive analysis of satellite images.
Stars: ✭ 134 (+97.06%)
Mutual labels:  image-classification
subwAI
Scripts for training an AI to play the endless runner Subway Surfers using a supervised machine learning approach by imitation and a convolutional neural network (CNN) for image classification
Stars: ✭ 86 (+26.47%)
Mutual labels:  image-classification
UniFormer
[ICLR2022] official implementation of UniFormer
Stars: ✭ 574 (+744.12%)
Mutual labels:  image-classification
shake-drop pytorch
PyTorch implementation of shake-drop regularization
Stars: ✭ 50 (-26.47%)
Mutual labels:  image-classification
Alturos.ImageAnnotation
A collaborative tool for labeling image data for yolo
Stars: ✭ 47 (-30.88%)
Mutual labels:  image-classification
tensorflow-image-classifier
image classifier, retrained for specific classes
Stars: ✭ 58 (-14.71%)
Mutual labels:  image-classification
imannotate
Image annotation tool to make Machine Learning or others stuffs
Stars: ✭ 44 (-35.29%)
Mutual labels:  image-classification
Tensorflow-Dog-Breed-Classifier
Tensorflow Image classifier that can predict the breed of a dog from it photo. Trained on image dataset of 5 different breed of dogs (rottweiler, bulldog, pug, german shepherds, labrador). Interestingly the classifier was able to predict the breed of the dogs even from images of their toys.
Stars: ✭ 14 (-79.41%)
Mutual labels:  image-classification
Paper-Notes
Paper notes in deep learning/machine learning and computer vision
Stars: ✭ 37 (-45.59%)
Mutual labels:  image-classification
Skin Lesions Classification DCNNs
Transfer Learning with DCNNs (DenseNet, Inception V3, Inception-ResNet V2, VGG16) for skin lesions classification
Stars: ✭ 47 (-30.88%)
Mutual labels:  image-classification
View All Similar Projects ➔

tensorflow-classification

Different neural network architechtures implemented in tensorflow for image classification. Weights converted from caffemodels. Some weights were converted using misc/convert.py others using caffe-tensorflow. The weights can be downloaded from here. Tested with Tensorflow 1.0. Weights for inception-V3 taken from Keras implementation provided here. Contributions are welcome!

Features

  • A single call program to classify images using different architechtures (vgg-f, caffenet, vgg-16, vgg-19, googlenet, resnet-50, resnet-152, inception-V3)
  • Returns networks as a dictionary of layers, so accessing activations at intermediate layers is easy
  • Functions to classify single image or evaluate on whole validation set

Usage

  • For classification of a single image, python classify.py --network 'resnet152' --img_path 'misc/sample.jpg'
  • For evaluation over whole ilsvrc validation set python classify.py --network 'resnet152' --img_list '<list with image names>' --gt_labels '<list with gt labels corresponding to images>'
  • Currently the --network argument can take vggf, caffenet, vgg16, vgg19, googlenet, resnet50, resnet152, inceptionv3.

Performance

These converted models have the following performance on the ilsvrc validation set, with each image resized to 224x224 (227 or 299 depending on architechture), and per channel mean subtraction.

Network Top-1 Accuracy Top-5 Accuracy
VGG-F 58.33% 80.75%
CaffeNet 56.77% 79.98%
VGG-16 70.93% 89.82%
VGG-19 71.02% 89.85%
GoogLeNet 68.69% 89.01%
ResNet-50 74.71% 92.00%
ResNet-152 76.33% 92.93%
Inception-V3 76.85% 93.39%
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].