Spatial Transformer Nets in TensorFlow/ TensorLayer

Last update: Nov 23, 2022

Overview

MOVED TO HERE

Spatial Transformer Networks

Spatial Transformer Networks (STN) is a dynamic mechanism that produces transformations of input images (or feature maps)including scaling, cropping, rotations, as well as non-rigid deformations. This enables the network to not only select regions of an image that are most relevant (attention), but also to transform those regions to simplify recognition in the following layers.

Video for different transformation click me.

In this repositary, we implemented a STN for 2D Affine Transformation on MNIST dataset. We generated images with size of 40x40 from the original MNIST dataset, and distorted the images by random rotation, shifting, shearing and zoom in/out. The STN was able to learn to automatically apply transformations on distorted images via classification task.

Fig 1：Transformation

Fig 2：Network

Fig 3：Formula

Result

After classification task, the STN is able to transform the distorted image from Fig 4 back to Fig 5.

Fig 4: Input

Fig 5: Output

Comments

Export graph

Hello,

I'm trying to export this model and its weights into a frozen graph. So far I did this in the "save images" part of the training loop:

saver = tf.train.Saver() saver.save(sess, 'my_stn_model_' + str(epoch)) tf.train.write_graph(sess.graph_def, ".", "test.pb", False) #proto

Then I have my pb and the weights. But I am unable to generate a frozen graph from this because I cannot guess the output node in the graph (which is a really complex one it seems).

I attached the pb which I am able to visualize using Netron:

test.zip

Thanks in advance.

opened by hvico 0
Unexpected Output

I'm trying to train the STN. The training dataset which I've provided contains MNIST dataset images which are rotated 90 degree and the testing dataset contains simple MNIST dataset images. The output I'm getting is straight MNIST images. I was expecting the output to contain characters which are rotated 90 degrees. Can you please guide me on how this works?

opened by nabeel3133 4

Spatial Transformer Nets in TensorFlow/ TensorLayer

Related tags

Overview

MOVED TO HERE

Spatial Transformer Networks

Result

You might also like...

Group Activity Recognition with Clustered Spatial Temporal Transformer

VSR-Transformer - This paper proposes a new Transformer for video super-resolution (called VSR-Transformer).

Python implementation of cover trees, near-drop-in replacement for scipy.spatial.kdtree

data/code repository of "C2F-FWN: Coarse-to-Fine Flow Warping Network for Spatial-Temporal Consistent Motion Transfer"

Unofficial implementation of "TTNet: Real-time temporal and spatial video analysis of table tennis" (CVPR 2020)

Official PyTorch implementation of Spatial Dependency Networks.

Spatial Intention Maps for Multi-Agent Mobile Manipulation (ICRA 2021)

The open source code of SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation.

Spatial Action Maps for Mobile Manipulation (RSS 2020)

Comments

Export graph

Unexpected Output

Releases(0.0.1)

0.0.1(Jun 26, 2017)

Owner

Hao

Official implementation for paper Render In-between: Motion Guided Video Synthesis for Action Interpolation

Torch Implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"

PyTorch implementation of spectral graph ConvNets, NIPS’16

Select, weight and analyze complex sample data

CenterNet:Objects as Points目标检测模型在Pytorch当中的实现

P-Tuning v2: Prompt Tuning Can Be Comparable to Finetuning Universally Across Scales and Tasks

Running Google MoveNet Multipose Tracking models on OpenVINO.

FaceAnon - Anonymize people in images and videos using yolov5-crowdhuman

🕵 Artificial Intelligence for social control of public administration

Trading and Backtesting environment for training reinforcement learning agent or simple rule base algo.

Machine Learning Model deployment for Container (TensorFlow Serving)

TensorFlow implementation of "Learning from Simulated and Unsupervised Images through Adversarial Training"

git《USD-Seg:Learning Universal Shape Dictionary for Realtime Instance Segmentation》(2020) GitHub: [fig2]

Creating a Linear Program Solver by Implementing the Simplex Method in Python with NumPy

Computational Methods Course at UdeA. Forked and size reduced from:

A user-friendly research and development tool built to standardize RL competency assessment for custom agents and environments.

Code used for the results in the paper "ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning"

Resources related to EMNLP 2021 paper "FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations"

Backend code to use MCPI's python API to make infinite worlds with custom generation

Nest Protect integration for Home Assistant. This will allow you to integrate your smoke, heat, co and occupancy status real-time in HA.