All Projects → AlexHex7 → Spatial-Transformer-Networks_pytorch

AlexHex7 / Spatial-Transformer-Networks_pytorch

Licence: other
Spatial Transformer Networks. Refer to daviddao/spatial-transformer-tensorflow.

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Spatial-Transformer-Networks pytorch

CRNN-OCR-lite
Lightweight CRNN for OCR (including handwritten text) with depthwise separable convolutions and spatial transformer module [keras+tf]
Stars: ✭ 130 (+75.68%)
Mutual labels:  spatial-transformer-network, stn
Spatial-Transformer-Nets
Spatial Transformer Nets in TensorFlow/ TensorLayer
Stars: ✭ 38 (-48.65%)
Mutual labels:  spatial-transformer-network
Spatial-Transformer-Networks-with-Keras
This repository provides a Colab Notebook that shows how to use Spatial Transformer Networks inside CNNs in Keras.
Stars: ✭ 23 (-68.92%)
Mutual labels:  spatial-transformer-network
nemar
[CVPR2020] Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation
Stars: ✭ 120 (+62.16%)
Mutual labels:  stn
GTSRB Keras STN
German Traffic Sign Recognition Benchmark, Keras implementation with Spatial Transformer Networks
Stars: ✭ 48 (-35.14%)
Mutual labels:  stn
cluttered-mnist
Experiments on cluttered mnist dataset with Tensorflow.
Stars: ✭ 20 (-72.97%)
Mutual labels:  spatial-transformer-network

Tpatial-Transformer-Networks-pytorch

Statement

  • Do the Experiments on the cluttered MNIST dataset of daviddao.
  • The accuracy and loss records can be find in cnn.out & stn.out.
  • The transform img can be find in transform_img/.
  • py35_pytorch03_version contains the old version code

Environment

  • python3.6
  • pytorch 0.4.0

Accuracy

CNN

  • Testing: epoch[195/200] loss:0.5264 acc:0.9211
  • Testing: epoch[196/200] loss:0.5185 acc:0.9194
  • Testing: epoch[197/200] loss:0.5160 acc:0.9158
  • Testing: epoch[198/200] loss:0.5053 acc:0.9183
  • Testing: epoch[199/200] loss:0.5057 acc:0.9153

STN

  • Testing: epoch[195/200] loss:0.0880 acc:0.9762
  • Testing: epoch[196/200] loss:0.0961 acc:0.9757
  • Testing: epoch[197/200] loss:0.0893 acc:0.9742
  • Testing: epoch[198/200] loss:0.1015 acc:0.9740
  • Testing: epoch[199/200] loss:0.0938 acc:0.9738

Transform Image

(input|transform|input|transform)

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].