1. Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg. [SSD: Single shot multibox detector](https://arxiv.org/abs/1512.02325). European conference on computer vision. Springer, Cham, 2016.
2. Simonyan, Karen, and Andrew Zisserman. [Very deep convolutional networks for large-scale image recognition](https://arxiv.org/abs/1409.1556). arXiv preprint arXiv:1409.1556 (2014).
@@ -167,7 +167,7 @@ Figure 3. SSD300x300 Visualization Example
...
@@ -167,7 +167,7 @@ Figure 3. SSD300x300 Visualization Example
## To Use Custo Data set
## To Use Custo Data set
In PaddlePaddle, using the custom data set to train SSD model is also easy! Just input the format that ```train.txt``` can understand. Below is a recommended structure to input for ```train.txt```.
In PaddlePaddle, using the custom data set to train SSD model is also easy! Just input the format that ```train.txt``` can understand. Below is a recommended structure to input for ```train.txt```.
Here each row corresponds to an object for 5 fields. The first is for the label (note the background 0, need to be numbered from 1), and the remaining four are for the coordinates.
Here each row corresponds to an object for 5 fields. The first is for the label (note the background 0, need to be numbered from 1), and the remaining four are for the coordinates.
@@ -209,7 +209,7 @@ Figure 3. SSD300x300 Visualization Example
...
@@ -209,7 +209,7 @@ Figure 3. SSD300x300 Visualization Example
## To Use Custo Data set
## To Use Custo Data set
In PaddlePaddle, using the custom data set to train SSD model is also easy! Just input the format that ```train.txt``` can understand. Below is a recommended structure to input for ```train.txt```.
In PaddlePaddle, using the custom data set to train SSD model is also easy! Just input the format that ```train.txt``` can understand. Below is a recommended structure to input for ```train.txt```.
Here each row corresponds to an object for 5 fields. The first is for the label (note the background 0, need to be numbered from 1), and the remaining four are for the coordinates.
Here each row corresponds to an object for 5 fields. The first is for the label (note the background 0, need to be numbered from 1), and the remaining four are for the coordinates.