Download the YOLOv7 official code. WongKinYiu/yolov7

$ git clone https://github.com/WongKinYiu/yolov7

Refer README.md to create and train a YOLOv7 tiny model.

$ git lfs install
$ git lfs clone --recursive https://github.com/khadas/aml_npu_sdk.git

The KSNN conversion tool is under acuity-toolkit/python.

$ cd aml_npu_sdk/acuity-toolkit/python && ls
$ convert  data  outputs

After training the model, modify yolov7/models/yolo.py as follows.

diff --git a/models/yolo.py b/models/yolo.py
index 95a019c..a2e611d 100644
--- a/models/yolo.py
+++ b/models/yolo.py
@@ -144,7 +144,7 @@ class IDetect(nn.Module):
             x[i] = self.m[i](x[i])  # conv
             bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
-            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+            # x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
 
             if not self.training:  # inference
                 if self.grid[i].shape[2:4] != x[i].shape[2:4]:

Then, run export.py to convert the model to ONNX.

$ python export.py

Enter aml_npu_sdk/acuity-toolkit/python and run command as follows.

$ ./convert --model-name yolov7_tiny \
            --platform onnx \
            --model yolov7_tiny.onnx \
            --mean-values '0 0 0 0.00392156' \
            --quantized-dtype asymmetric_affine \
            --source-files ./data/dataset/dataset0.txt \
            --batch-size 1 \
            --iterations 1 \
            --kboard VIM3 --print-level 0 

If you want to use more quantified images, please modify batch-size and iterations. batch-size×iterations=number of quantified images.

If you use VIM3L , please use VIM3L to replace VIM3.

If run succeed, converted model and library will generate in outputs/yolov7_tiny.

Download KSNN library and demo code. khadas/ksnn

$ git clone --recursive https://github.com/khadas/ksnn.git
$ cd ksnn/ksnn
$ pip3 install ksnn-1.3-py3-none-any.whl

If your kernel version is 5.15, use ksnn-1.4-py3-none-any.whl instead of ksnn-1.3-py3-none-any.whl.

$ pip3 install matplotlib

Put yolov7_tiny.nb and libnn_yolov7_tiny.so into ksnn/examples/yolov7_tiny/models/VIM3 and ksnn/examples/yolov7_tiny/libs

If your model's classes is not 80, please remember to modify the parameter, LISTSIZE.

LISTSIZE = classes number + 5

$ cd ksnn/examples/yolov7_tiny
$ python3 yolov7_tiny-picture.py --model ./models/VIM3/yolov7_tiny.nb --library ./libs/libnn_yolov7_tiny.so --picture ./data/horses.jpg --level 0

$ cd ksnn/examples/yolov7_tiny
$ python3 yolov7_tiny-cap.py --model ./models/VIM3/yolov7_tiny.nb --library ./libs/libnn_yolov7_tiny.so --device 0

0 is the camera device index.