FCHarDNet
Aug-15-2021 Update
-
Added a new v2_transform() method to replace torch.cat + nn.Conv2d combinations with CatConv2d, an all-in-1 fused cuda kernel combining Concat and Conv2d.
-
Inference on TitanV speedup from 70 fps to 99 fps
-
CatConv2d Installation
cd CatConv2d/ python setup.py install(Please note that backward path for CatConv2d hasn't been implemented)
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 |
| FC-HarDNet-70 V2 (with CatConv2d) |
4.1 | 35.4 | 76.0 | 99 | 63 |
-
** Speed tested in 1536x768 instead of full resolution.
DataLoaders implemented
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/hardnet_petite_base.pth
Prediction Samples
