Perfect Half Million Beauty Product Image Recognition Challenge
This is our solution for Perfect Half Million Beauty Product Image Recognition Challenge , which obtained the 1st place (USTC_NELSLIP) with MAP@7 0.4086
Dependency
- python3.5
- pytorch(1.1.0)
- torchvision
- pretrainedmodels
- tqdm
- PIL
Preparation
For Image Database
1.Download all the images of dataset recorded in csvfile
2.Transform all the images to square form using 255 padding
3.Put all the images in the folder data_clean
For Query Images
Query images are put in the folder search/ori_images
For models
Download these two models and put them in the folder /code/pretrained
Usage
- Extract features of images in database(Perfect-500K)
$ python features.py
- Conduct image retrieval
$ python search.py
Note
All the models are all pretrained on the Imagenet. They can be downloaded from module pretrainedmodels.