AI Rank
EN
← 开源
qfgaohao

pytorch-ssd

MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.

Model DevelopmentArchitecturePython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
1.43k
Star
540
Fork
+0
本周
10
贡献者
创建于 2018-05-18 · 更新于 2026-09-28 · 今日第 10361 名
主要开发者
qfgaohaoaclexsqueakus

qfgaohao/pytorch-ssd 排名第 10,361，有 1,430 个星标。

同类别比较

qfgaohao/pytorch-ssd 排名第 10,361，此处有 8 个同类条目；openai/SWELancer-Benchmark 排名第 10,360。

同类别比较
名称排名指标
winedarksea/AutoTS10,353
语言:
Python
星标数:
1,431
分叉数:
127
简介:
Automated Time Series Forecasting
KaiyangZhou/Dassl.pytorch10,355
语言:
Python
星标数:
1,430
分叉数:
196
简介:
A PyTorch toolbox for domain generalization, domain adaptation and semi-supervised learning.
nianticlabs/simplerecon10,359
语言:
Python
星标数:
1,430
分叉数:
130
简介:
[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
openai/SWELancer-Benchmark10,360
星标数:
1,430
分叉数:
136
简介:
This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"
OpenLMLab/MOSS-RLHF10,366
语言:
Python
星标数:
1,427
分叉数:
103
简介:
Secrets of RLHF in Large Language Models Part I: PPO
google-research/disentanglement_lib10,371
语言:
Python
星标数:
1,425
分叉数:
202
简介:
disentanglement_lib is an open-source library for research on learning disentangled representations.
torchgan/torchgan10,379
语言:
Python
星标数:
1,423
分叉数:
167
简介:
Research Framework for easy and efficient training of GANs based on Pytorch
sfzhang15/RefineDet10,386
语言:
C++
星标数:
1,420
分叉数:
383
简介:
Single-Shot Refinement Neural Network for Object Detection, CVPR, 2018
关键参数与规格
关键参数与规格
参数值
语言Python
类别Model Development
子类别Architecture
星标数1,430
分叉数540
贡献者10
创建日期2018-05-18
更新日期2026-09-28
1 天星标数0
7 天星标数0
排名10,361
上次排名10,362
排名变化1
7 天星标排名12,600
上次 7 天星标排名12,635
7 天星标排名变化35
总星标排名8,413
上次总星标排名8,401
总星标排名变化-12
国家New Zealand
README 摘录

Single Shot MultiBox Detector Implementation in Pytorch This repo implements SSD (Single Shot MultiBox Detector). The implementation is heavily influenced by the projects ssd. The design goal is modularity and extensibility. Currently, it has MobileNetV1, MobileNetV2, and VGG based SSD/SSD-Lite implementations. It also has out-of-box support for retraining on Google Open Images dataset. Boto3 if you want to train models on the Google OpenImages Dataset. Download models **Please download the models and put them into the

folder ". ** URL: Run the demo Run the live MobilenetV1 SSD demo Run the live demo in Caffe2 You can see a decent speed boost by using Caffe2. Run the live MobileNetV2 SSD Lite demo The above MobileNetV2 SSD-Lite model is not ONNX-Compatible, as it uses Relu6 which is not supported by ONNX. The code supports the ONNX-Compatible version. Once I have trained a good enough MobileNetV2 model with Relu, I will upload the corresponding Pytorch and Caffe2

models. You may notice MobileNetV2 SSD/SSD-Lite is slower than MobileNetV1 SSD/Lite on PC. However, MobileNetV2 is faster on mobile devices. Pretrained Models Mobilenet V1 SSD If you haven't downloaded the models, please download from Model: mobilenet-v1-ssd-mp-0_675. pth MobileNetV2 SSD-Lite If you haven't downloaded the models, please download from Model: mb2-ssd-lite-mp-0_686. pth The code to re-produce the model: VGG SSD Model: vgg16-ssd-mp-0_7726

. pth The code to re-produce the model: Training The dataset path is the parent directory of the folders: Annotations, ImageSets, JPEGImages, SegmentationClass and SegmentationObject. Evaluation Convert models to ONNX and Caffe2 models The converted models are models/mobilenet-v1-ssd. pb and models/mobilenet-v1-ssd_predict_net. The models in the format of pbtxt are also saved for reference. Retrain on Open Images Dataset Let's we are building a model to detect guns for security purpose. If you

manage to get more annotated data, the accuracy could become much higher. Download data It will download data into the folder ~/data/open_images. The content of the data directory looks as follows. The folders train, test, validation contain the images. The files like sub-train-annotations-bbox. Retrain You can freeze the base net, or all the layers except the prediction heads. You can also use different learning rates for the base net, the extra layers and the prediction

heads. As subsets of open images data can be very unbalanced, it also provides a handy option to roughly balance the data. The model is not really ONNX-Friendly due the issue mentioned here " The Scaled L2 Norm Layer has been replaced with BatchNorm to make the net ONNX compatible. Train The pretrained based is borrowed from .

常见问题

记录了多少星标和分叉？

qfgaohao/pytorch-ssd 有 1,430 个星标和 540 个分叉。

仓库排名是多少？

qfgaohao/pytorch-ssd 排名第 10,361。

记录的语言和类别是什么？

qfgaohao/pytorch-ssd 有 1,430 个星标，语言为 Python，类别为 Model Development。

哪个仓库排名最接近？

qfgaohao/pytorch-ssd 与 openai/SWELancer-Benchmark 比较，后者排名第 10,360，有 1,430 个星标。

README

Single Shot MultiBox Detector Implementation in Pytorch

This repo implements SSD (Single Shot MultiBox Detector). The implementation is heavily influenced by the projects ssd.pytorch and Detectron. The design goal is modularity and extensibility.

Currently, it has MobileNetV1, MobileNetV2, and VGG based SSD/SSD-Lite implementations.

It also has out-of-box support for retraining on Google Open Images dataset.

Dependencies

  1. Python 3.6+
  2. OpenCV
  3. Pytorch 1.0 or Pytorch 0.4+
  4. Caffe2
  5. Pandas
  6. Boto3 if you want to train models on the Google OpenImages Dataset.

Download models

Please download the models and put them into the folder "./models". The following sections will need them. URL: https://drive.google.com/drive/folders/1pKn-RifvJGWiOx0ZCRLtCXM5GT5lAluu?usp=sharing

Run the demo

Run the live MobilenetV1 SSD demo

# If you haven't downloaded the models, please download from https://drive.google.com/drive/folders/1pKn-RifvJGWiOx0ZCRLtCXM5GT5lAluu?usp=sharing.
python run_ssd_live_demo.py mb1-ssd models/mobilenet-v1-ssd-mp-0_675.pth models/voc-model-labels.txt

Run the live demo in Caffe2

# If you haven't downloaded the models, please download from https://drive.google.com/drive/folders/1pKn-RifvJGWiOx0ZCRLtCXM5GT5lAluu?usp=sharing.
python run_ssd_live_caffe2.py models/mobilenet-v1-ssd_init_net.pb models/mobilenet-v1-ssd_predict_net.pb models/voc-model-labels.txt

You can see a decent speed boost by using Caffe2.

Run the live MobileNetV2 SSD Lite demo

# If you haven't downloaded the models, please download from https://drive.google.com/drive/folders/1pKn-RifvJGWiOx0ZCRLtCXM5GT5lAluu?usp=sharing.
python run_ssd_live_demo.py mb2-ssd-lite models/mb2-ssd-lite-mp-0_686.pth models/voc-model-labels.txt

The above MobileNetV2 SSD-Lite model is not ONNX-Compatible, as it uses Relu6 which is not supported by ONNX. The code supports the ONNX-Compatible version. Once I have trained a good enough MobileNetV2 model with Relu, I will upload the corresponding Pytorch and Caffe2 models.

You may notice MobileNetV2 SSD/SSD-Lite is slower than MobileNetV1 SSD/Lite on PC. However, MobileNetV2 is faster on mobile devices.

Pretrained Models

Mobilenet V1 SSD

If you haven't downloaded the models, please download from https://drive.google.com/drive/folders/1pKn-RifvJGWiOx0ZCRLtCXM5GT5lAluu?usp=sharing.

Model: mobilenet-v1-ssd-mp-0_675.pth

Average Precision Per-class:
aeroplane: 0.6742489426027927
bicycle: 0.7913672875238116
bird: 0.612096015101108
boat: 0.5616407126931772
bottle: 0.3471259064860268
bus: 0.7742298893362103
car: 0.7284171192326804
cat: 0.8360675520354323
chair: 0.5142295855384792
cow: 0.6244090341627014
diningtable: 0.7060035669312754
dog: 0.7849252606216821
horse: 0.8202146617282785
motorbike: 0.793578272243471
person: 0.7042670984734087
pottedplant: 0.40257147509774405
sheep: 0.6071252282334352
sofa: 0.7549120254763918
train: 0.8270992920206008
tvmonitor: 0.6459903029666852

Average Precision Across All Classes:0.6755

MobileNetV2 SSD-Lite

If you haven't downloaded the models, please download from https://drive.google.com/drive/folders/1pKn-RifvJGWiOx0ZCRLtCXM5GT5lAluu?usp=sharing.

Model: mb2-ssd-lite-mp-0_686.pth

Average Precision Per-class:
aeroplane: 0.6973327307871002
bicycle: 0.7823755921687233
bird: 0.6342429230125619
boat: 0.5478160937380846
bottle: 0.3564069147093762
bus: 0.7882037885117419
car: 0.7444122242934775
cat: 0.8198865557991936
chair: 0.5378973422880109
cow: 0.6186076149254742
diningtable: 0.7369559500950861
dog: 0.7848265495754562
horse: 0.8222948787839229
motorbike: 0.8057808854619948
person: 0.7176976451996411
pottedplant: 0.42802932547480066
sheep: 0.6259124005994047
sofa: 0.7840368059271103
train: 0.8331588002612781
tvmonitor: 0.6555051795079904
Average Precision Across All Classes:0.6860690100560214

The code to re-produce the model:

# If you haven't downloaded the models, please download from https://drive.google.com/drive/folders/1pKn-RifvJGWiOx0ZCRLtCXM5GT5lAluu?usp=sharing.
python train_ssd.py --dataset_type voc  --datasets ~/data/VOC0712/VOC2007 ~/data/VOC0712/VOC2012 --validation_dataset ~/data/VOC0712/test/VOC2007/ --net mb2-ssd-lite --base_net models/mb2-imagenet-71_8.pth  --scheduler cosine --lr 0.01 --t_max 200 --validation_epochs 5 --num_epochs 200

VGG SSD

Model: vgg16-ssd-mp-0_7726.pth

Average Precision Per-class:
aeroplane: 0.7957406334737802
bicycle: 0.8305351156180996
bird: 0.7570969203281721
boat: 0.7043869846367731
bottle: 0.5151666571756393
bus: 0.8375121237865507
car: 0.8581508869699901
cat: 0.8696185705648963
chair: 0.6165431194526735
cow: 0.8066422244852381
diningtable: 0.7629391213959706
dog: 0.8444541531856452
horse: 0.8691922094815812
motorbike: 0.8496564646906418
person: 0.793785185549561
pottedplant: 0.5233462463152305
sheep: 0.7786762429478917
sofa: 0.8024887701948746
train: 0.8713861172265407
tvmonitor: 0.7650514925384194
Average Precision Across All Classes:0.7726184620009084

The code to re-produce the model:

wget -P models https://s3.amazonaws.com/amdegroot-models/vgg16_reducedfc.pth
python train_ssd.py --datasets ~/data/VOC0712/VOC2007/ ~/data/VOC0712/VOC2012/ --validation_dataset ~/data/VOC0712/test/VOC2007/ --net vgg16-ssd --base_net models/vgg16_reducedfc.pth  --batch_size 24 --num_epochs 200 --scheduler "multi-step” —-milestones “120,160”

Training

python train_ssd.py --datasets ~/data/VOC0712/VOC2007/ ~/data/VOC0712/VOC2012/ --validation_dataset ~/data/VOC0712/test/VOC2007/ --net mb1-ssd --base_net models/mobilenet_v1_with_relu_69_5.pth  --batch_size 24 --num_epochs 200 --scheduler cosine --lr 0.01 --t_max 200

The dataset path is the parent directory of the folders: Annotations, ImageSets, JPEGImages, SegmentationClass and SegmentationObject. You can use multiple datasets to train.

Evaluation

python eval_ssd.py --net mb1-ssd  --dataset ~/data/VOC0712/test/VOC2007/ --trained_model models/mobilenet-v1-ssd-mp-0_675.pth --label_file models/voc-model-labels.txt

Convert models to ONNX and Caffe2 models

python convert_to_caffe2_models.py mb1-ssd models/mobilenet-v1-ssd-mp-0_675.pth models/voc-model-labels.txt

The converted models are models/mobilenet-v1-ssd.onnx, models/mobilenet-v1-ssd_init_net.pb and models/mobilenet-v1-ssd_predict_net.pb. The models in the format of pbtxt are also saved for reference.

Retrain on Open Images Dataset

Let's we are building a model to detect guns for security purpose.

Before you start you can try the demo.

python run_ssd_example.py mb1-ssd models/gun_model_2.21.pth models/open-images-model-labels.txt ~/Downloads/big.JPG

If you manage to get more annotated data, the accuracy could become much higher.

Download data

python open_images_downloader.py --root ~/data/open_images --class_names "Handgun,Shotgun" --num_workers 20

It will download data into the folder ~/data/open_images.

The content of the data directory looks as follows.

class-descriptions-boxable.csv       test                        validation
sub-test-annotations-bbox.csv        test-annotations-bbox.csv   validation-annotations-bbox.csv
sub-train-annotations-bbox.csv       train
sub-validation-annotations-bbox.csv  train-annotations-bbox.csv

The folders train, test, validation contain the images. The files like sub-train-annotations-bbox.csv is the annotation file.

Retrain

python train_ssd.py --dataset_type open_images --datasets ~/data/open_images --net mb1-ssd --pretrained_ssd models/mobilenet-v1-ssd-mp-0_675.pth --scheduler cosine --lr 0.01 --t_max 100 --validation_epochs 5 --num_epochs 100 --base_net_lr 0.001  --batch_size 5

You can freeze the base net, or all the layers except the prediction heads.

  --freeze_base_net     Freeze base net layers.
  --freeze_net          Freeze all the layers except the prediction head.

You can also use different learning rates for the base net, the extra layers and the prediction heads.

  --lr LR, --learning-rate LR
  --base_net_lr BASE_NET_LR
                        initial learning rate for base net.
  --extra_layers_lr EXTRA_LAYERS_LR

As subsets of open images data can be very unbalanced, it also provides a handy option to roughly balance the data.

  --balance_data        Balance training data by down-sampling more frequent
                        labels.

Test on image

python run_ssd_example.py mb1-ssd models/mobilenet-v1-ssd-Epoch-99-Loss-2.2184619531035423.pth models/open-images-model-labels.txt ~/Downloads/gun.JPG

ONNX Friendly VGG16 SSD

! The model is not really ONNX-Friendly due the issue mentioned here "https://github.com/qfgaohao/pytorch-ssd/issues/33#issuecomment-467533485"

The Scaled L2 Norm Layer has been replaced with BatchNorm to make the net ONNX compatible.

Train

The pretrained based is borrowed from https://s3.amazonaws.com/amdegroot-models/vgg16_reducedfc.pth .

python train_ssd.py --datasets ~/data/VOC0712/VOC2007/ ~/data/VOC0712/VOC2012/ --validation_dataset ~/data/VOC0712/test/VOC2007/ --net "vgg16-ssd" --base_net models/vgg16_reducedfc.pth  --batch_size 24 --num_epochs 150 --scheduler cosine --lr 0.0012 --t_max 150 --validation_epochs 5

Eval

python eval_ssd.py --net vgg16-ssd  --dataset ~/data/VOC0712/test/VOC2007/ --trained_model models/vgg16-ssd-Epoch-115-Loss-2.819455094383535.pth --label_file models/voc-model-labels.txt

TODO

  1. Resnet34 Based Model.
  2. BatchNorm Fusion.
排名相邻
同类项目