FCHarDNet

Fully Convolutional HarDNet for Segmentation in Pytorch

• Implementaion based on Harmonic DenseNet: A low memory traffic network (ICCV 2019)
• Refer to Pytorch-HarDNet for more information about the backbone model
• This repo was forked from meetshah1995/pytorch-semseg

Architecture

• Simple U-shaped encoder-decoder structure
• Conv3x3/Conv1x1 only (including the first layer)
• No self-attention layer or Pyramid Pooling
  

Results

| Method | #Param
(M) | GMACs /
GFLOPs | Cityscapes
mIoU | fps on Titan-V
@1024x2048 | fps on 1080ti
@1024x2048 | | :---: | :---: | :---: | :---: | :---: | :---: | | ICNet | 7.7 | 30.7 | 69.5 | 63 | 48 | | SwiftNetRN-18 | 11.8 | 104 | 75.5 | - | 39.9 | | BiSeNet (1024x2048) | 13.4 | 119 | 77.7 | 36 | 27 | | BiSeNet (768x1536) | 13.4 | 66.8 | 74.7 | 72** | 54** | | FC-HarDNet-70 | 4.1 | 35.4 | 76.0 | 70 | 53 |

- ** Speed tested in 1536x768 instead of full resolution.

DataLoaders implemented

• CamVid
• Pascal VOC
• ADE20K
• MIT Scene Parsing Benchmark
• Cityscapes
• NYUDv2
• Sun-RGBD

Requirements

• pytorch >=0.4.0
• torchvision ==0.2.0
• scipy
• tqdm
• tensorboardX

Usage

Setup config file

Please see the usage section in meetshah1995/pytorch-semseg

To train the model :

python train.py [-h] [--config [CONFIG]]

--config                Configuration file to use (default: hardnet.yml)

To validate the model :

usage: validate.py [-h] [--config [CONFIG]] [--model_path [MODEL_PATH]] [--save_image]
                       [--eval_flip] [--measure_time]

  --config              Config file to be used
  --model_path          Path to the saved model
  --eval_flip           Enable evaluation with flipped image | False by default
  --measure_time        Enable evaluation with time (fps) measurement | True by default
  --save_image          Enable writing result images to out_rgb (pred label blended images) and out_predID

Pretrained Weights

• Cityscapes pretrained weights: Download
  (Val mIoU: 77.7, Test mIoU: 75.9)
• Cityscapes pretrained with color jitter augmentation: Download
  (Val mIoU: 77.4, Test mIoU: 76.0)
• HarDNet-Petite weights pretrained by ImageNet:
  included in weights/hardnetpetitebase.pth

Prediction Samples