This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
| 
                    products:sbc:edge2:npu:demos:densenet-ctc [2023/08/25 06:22] louis  | 
                
                    products:sbc:edge2:npu:demos:densenet-ctc [2025/04/09 23:25] (current) louis  | 
            ||
|---|---|---|---|
| Line 1: | Line 1: | ||
| - | ====== Demo3 - Densenet CTC ====== | + | ~~tag> DenseNet NPU Edge2 RK3588~~ | 
| - | ===== Get Source Code ===== | + | ====== DenseNet CTC ONNX Keras Edge2 Demo - 3 ====== | 
| - | The codes we use. | + | {{indexmenu_n> | 
| + | |||
| + | ===== Introduction ===== | ||
| + | |||
| + | Densenet_CTC is a text recognition model. It only can recognize single line text. Therefore usually, it needs to be used in conjunction with a text detection model. | ||
| + | |||
| + | Recognition image and inference results on Edge2. | ||
| + | |||
| + | {{: | ||
| + | |||
| + | |||
| + | ===== Train Model ===== | ||
| + | |||
| + | We will use a DenseNet model based on [[gh> | ||
| ```shell | ```shell | ||
| Line 127: | Line 140: | ||
| ==== Get source code ==== | ==== Get source code ==== | ||
| - | Clone the source code form our [[gh> | + | Clone the source code from our [[gh> | 
| ```shell | ```shell | ||
| Line 148: | Line 161: | ||
| ```shell | ```shell | ||
| # Compile | # Compile | ||
| + | $ cd edge2-npu/ | ||
| $ bash build.sh | $ bash build.sh | ||
| Line 156: | Line 170: | ||
| <WRAP tip > | <WRAP tip > | ||
| - | If your densenet_ctc  | + | If your **DenseNet CTC** model classes is not the same as mine, please change '' | 
| </ | </ | ||