A baseline model ( PSPNet ) for single-person human parsing task, training and testing on Look into Person dataset.
We built model with PyTorch 0.4.1 and the implementation of PSPNet was based on Here.
Trained model weights can be downloaded from Google Drive or Baidu Drive (提取码:43cu).
To use our code, firstly you should download LIP dataset from Here.
Then, reorganize the dataset folder as below:
myLIP
│
└───train
│ │ id.txt
│ │
│ └───image
│ │ │ 77_471474.jpg
│ │ │ 113_1207747.jpg
│ │ │ ...
│ │
│ └───gt
│ │ │ 77_471474.png
│ │ │ 113_1207747.png
│ │ │ ...
│
└───val
│ │ id.txt
│ │
│ └───image
│ │ │ 100034_483681.jpg
│ │ │ 10005_205677.jpg
│ │ │ ...
│ │
│ └───gt
│ │ │ 100034_483681.png
│ │ │ 10005_205677.png
│ │ │ ...
│
└───test
│ │ id.txt
│ │
│ └───image
│ │ │ 100012_501646.jpg
│ │ │ ...
python3 train.py --data-path ~/myLIP
python3 eval.py --data-path ~/myLIP [--visualize]
model | overall acc. | mean acc. | mean IoU |
---|---|---|---|
resnet50 | 0.792 | 0.552 | 0.463 |
densenet121 | 0.826 | 0.606 | 0.519 |
squeezenet | 0.786 | 0.543 | 0.450 |