Git Product home page Git Product logo

pan-tensorflow's Introduction

Pixel Aggregation Network

This is an unofficial TensorFlow re-implementation of paper "Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network" published in ICCV 2019, with Tensorflow 2.

Task

  • Backbone model
  • FPEM model
  • FFM model
  • Integrated model
  • Loss Function
  • Data preprocessing
  • Data postprocessing
  • Training pipeline
  • Inference pipeline
  • Evaluation pipeline

Command

Training

python train.py --batch 16 --epoch 601 --dataset_type ctw --gpu True

Inference

python inference.py --input ./data/CTW1500/test/text_image --model ./outputs/model_epoch_600 --bbox_type poly

Results

*Default using ResNet-50 backbone model, also support ResNet-101 backbone model.

CTW1500

Model Precision Recall F score
PAN-320 0.8472 0.6939 0.7629

Supported Dataset

Source

[1] Original paper: https://arxiv.org/abs/1908.05900

[2] Official PyTorch code: https://github.com/whai362/pan_pp.pytorch

pan-tensorflow's People

Contributors

liuch37 avatar

Stargazers

 avatar

Watchers

 avatar

pan-tensorflow's Issues

Error

I am getting this error

Traceback (most recent call last):
File "train.py", line 136, in
for iter, data in enumerate(train_dataloader):
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/utils/data_utils.py", line 483, in iter
for item in (self[i] for i in range(len(self))):
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/utils/data_utils.py", line 483, in
for item in (self[i] for i in range(len(self))):
File "/content/drive/My Drive/pan-tensorflow/dataset/ctw1500.py", line 367, in getitem
data = self.prepare_train_data_single(global_idx)
File "/content/drive/My Drive/pan-tensorflow/dataset/ctw1500.py", line 252, in prepare_train_data_single
bboxes, words = get_ann(img, gt_path)
File "/content/drive/My Drive/pan-tensorflow/dataset/ctw1500.py", line 36, in get_ann
with open(gt_path, "r") as file:
FileNotFoundError: [Errno 2] No such file or directory: './data/train_labels/0390.txt'

pre-trained model weights

Hi,

Thanks for this code implementation, it is pretty amazing. Can you please link the pre-trained model weights for ctw1500 if possible.
Would be really helpful

Thanks

Text not detected after testing

Not getting any result after testing. The images are saved in the results folder but there is no bounding box on the image i.e, it is not detected also the .txt file that is saved after testing is empty for each of the image.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.