This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
products:sbc:vim4:npu:demos:vgg16 [2023/09/08 06:30] hyphop [Demo4 VGG16] |
products:sbc:vim4:npu:demos:vgg16 [2024/01/04 21:24] (current) louis old revision restored (2023/09/20 01:13) |
||
---|---|---|---|
Line 1: | Line 1: | ||
- | ====== | + | ~~tag> |
+ | |||
+ | ====== VGG16 TensorFlow Keras VIM4 Demo 4 ====== | ||
+ | |||
+ | {{indexmenu_n> | ||
[[https:// | [[https:// | ||
Line 9: | Line 13: | ||
```shell | ```shell | ||
- | git clone https:// | + | $ git clone https:// |
``` | ``` | ||
Line 16: | Line 20: | ||
==== Build virtual environment ==== | ==== Build virtual environment ==== | ||
- | Follow Docker official | + | Follow Docker official |
- | Get Docker. | + | Then fetch the prebuilt NPU Docker |
```shell | ```shell | ||
Line 30: | Line 34: | ||
==== Get convert tool ==== | ==== Get convert tool ==== | ||
- | Download Tool from [[gl> | + | Download Tool from [[gl> |
```shell | ```shell | ||
- | $ git clone https:// | + | $ git clone https:// |
``` | ``` | ||
==== Convert ==== | ==== Convert ==== | ||
- | Keras model can convert rknn model directly. But this demo is to convert tensorflow | + | We first need to convert the Keras model('' |
```shell | ```shell | ||
- | git clone https:// | + | $ git clone https:// |
``` | ``` | ||
- | Enter '' | + | Then we need to convert the TensorFlow model to an ADLA model ('' |
+ | |||
+ | Enter '' | ||
- | ```shell convert_adla.sh | + | ```sh convert_adla.sh |
#!/bin/bash | #!/bin/bash | ||
| | ||
Line 72: | Line 78: | ||
``` | ``` | ||
- | Run '' | + | Run '' |
```shell | ```shell | ||
Line 85: | Line 91: | ||
```shell | ```shell | ||
- | $ git clone https:// | + | $ git clone https:// |
``` | ``` | ||
Line 114: | Line 120: | ||
<WRAP tip > | <WRAP tip > | ||
- | If your **vgg16** model classes | + | If your **VGG16** model classes |
</ | </ | ||