Download Latest Version
Software.zip (89.7 MB)
Get an email when there's a new version of SSD in PyTorch 1.0
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| Software.zip | 2024-01-13 | 89.7 MB | |
| mobilenet_v3_ssd320_voc0712.pth | 2020-08-15 | 31.3 MB | |
| mobilenet_v2_ssd320_voc0712_v2.pth | 2020-03-13 | 26.8 MB | |
| vgg_ssd512_coco_trainval35k.pth | 2019-07-14 | 288.3 MB | |
| vgg_ssd512_voc0712.pth | 2019-07-02 | 217.5 MB | |
| vgg_ssd300_coco_trainval35k.pth | 2019-07-01 | 274.5 MB | |
| vgg_ssd300_voc0712.pth | 2019-07-01 | 210.3 MB | |
| efficient_net_b3_ssd300_voc0712.pth | 2019-07-01 | 101.8 MB | |
| More modular! source code.tar.gz | 2019-07-01 | 606.2 kB | |
| More modular! source code.zip | 2019-07-01 | 632.5 kB | |
| README.md | 2019-07-01 | 1.3 kB | |
| Totals: 11 Items | 1.2 GB | 0 | |
- PyTorch 1.0: Support PyTorch 1.0 or higher.
- Multi-GPU training and inference: We use
DistributedDataParallel, you can train or test with arbitrary GPU(s), the training schema will change accordingly. - Modular: Add your own modules without pain. We abstract
backbone,Detector,BoxHead,BoxPredictor, etc. You can replace every component with your own code without change the code base. For example, You can add EfficientNet as backbone, just addefficient_net.py(ALREADY ADDED) and register it, specific it in the config file, It's done! - CPU support for inference: runs on CPU in inference time.
- Smooth and enjoyable training procedure: we save the state of model, optimizer, scheduler, training iter, you can stop your training and resume training exactly from the save point without change your training
CMD. - Batched inference: can perform inference using multiple images per batch per GPU.
- Evaluating during training: eval you model every
eval_stepto check performance improving or not. - Metrics Visualization: visualize metrics details in tensorboard, like AP, APl, APm and APs for COCO dataset or mAP and 20 categories' AP for VOC dataset.
- Auto download: load pre-trained weights from URL and cache it.