我们准备了windows平台下的python开发环境，以及depthai示例，并且python环境中已为您安装好了运行depthai示例所需的所有依赖，做到开箱即用。点击查看
要允许 DepthAI 使用您的自定义训练模型，您需要将它们转换为 MyriadX blob 文件格式 - 以便它们针对 MyriadX VPU 处理器上的最佳推理进行优化。点击查看
在我们的 Github 存储库 depthai-ml-training 中，我们提供了几个在各种数据集上训练的ML训练笔记本. 您可以在 Google Colab 上运行这些笔记本-它们提供免费的CPU/GPU实例，非常适合原型设计甚至简单的生产模型。点击查看
Roboflow免费课程，6节课学习如何训练和部署计算机视觉模型到OAK上。 点击查看
所有模型来源以下网站
对象检测模型
| 人体检测 |
|---|
- person-detection-retail-0002
- person-detection-retail-0013
- person-detection-action-recognition-0005
- person-detection-action-recognition-0006
- person-detection-action-recognition-teacher-0002
- person-detection-raisinghand-recognition-0001
- person-detection-0200
- person-detection-0201
- person-detection-0202
- person-detection-0203
- person-detection-0106
- pedestrian-detection-adas-0002
- pedestrian-and-vehicle-detector-adas-0001
- person-detection-asl-0001
| 人车检测 |
|---|
- person-vehicle-bike-detection-crossroad-0078
- person-vehicle-bike-detection-crossroad-1016
- person-vehicle-bike-detection-crossroad-yolov3-1020
- person-vehicle-bike-detection-2000
- person-vehicle-bike-detection-2001
- person-vehicle-bike-detection-2002
- person-vehicle-bike-detection-2003
- person-vehicle-bike-detection-2004
| 多对象检测 |
|---|
- 以下模型无需转换格式可直接使用在OAK上
对象识别模型
其他识别模型
分割模型
文本类
| 文本识别 |
|---|
- text-recognition-0012
- text-recognition-0014
- text-recognition-0015 - encoder
- text-recognition-0015 - decoder
- handwritten-score-recognition-0003
- handwritten-japanese-recognition-0001
- handwritten-simplified-chinese-recognition-0001
- formula-recognition-medium-scan-0001 - encoder
- formula-recognition-medium-scan-0001 - decoder
- formula-recognition-polynomials-handwritten-0001 - encoder
- formula-recognition-polynomials-handwritten-0001 - decoder
分类模型
- AlexNet
- AntiSpoofNet
- CaffeNet
- DenseNet 121
- DenseNet 121 tf
- DenseNet 121 caffe2
- DenseNet 161
- DenseNet 161 tf
- DenseNet 169
- DenseNet 169 tf
- DenseNet 201
- DenseNet 201 tf
- DLA 34
- EfficientNet B0
- EfficientNet B0 pytorch
- EfficientNet B0 AutoAugment
- EfficientNet B5
- EfficientNet B5 pytorch
- EfficientNet B7 pytorch
- EfficientNet B7 AutoAugment
- HBONet 1.0
- HBONet 0.5
- HBONet 0.25
- Inception (GoogleNet) V1
- Inception (GoogleNet) V1 tf
- Inception (GoogleNet) V2
- Inception (GoogleNet) V2 tf
- Inception (GoogleNet) V3
- Inception (GoogleNet) V3 pytorch
- Inception (GoogleNet) V4 tf
- Inception-ResNet V2 tf
- MixNet L
- MobileNet V1 0.25 128
- MobileNet V1 0.5 160
- MobileNet V1 0.5 224
- MobileNet V1 0.5 224 tf
- MobileNet V2
- MobileNet V2 1.0 224
- MobileNet V2 1.0 224 pytorch
- MobileNet V2 1.4 224
- MobileNet V3 Small 1.0 tf
- MobileNet V3 Large 1.0 tf
- NFNet F0
- DenseNet 121, alpha=0.125
- RegNetX-3.2GF
- ResNet 26, alpha=0.25
- ResNet 50, alpha=0.125
- ResNet 101, alpha=0.125
- ResNet 200, alpha=0.125
- ResNeXt 50, alpha=0.25
- ResNeXt 101, alpha=0.25
- SE-ResNet 50, alpha=0.125
- open-closed-eye-0001
- RepVGG A0
- RepVGG B1
- RepVGG B3
- ResNeSt 50
- ResNet 18
- ResNet 34
- ResNet 50 pytorch
- ResNet 50 caffe2
- ResNet 50 tf
- ReXNet V1 x1.0
- se-inception
- SE-ResNet 50
- SE-ResNet 101
- SE-ResNet 152
- SE-ResNeXt 50
- SE-ResNeXt 101
- Shufflenet V2 x1.0
- SqueezeNet v1.0
- SqueezeNet V1.1
- SqueezeNet V1.1 caffe2
- VGG 16
- VGG 19
- VGG 19 caffe2