Differences

This shows you the differences between two versions of the page.

--- products:sbc:vim4:npu:demos:facenet [2024/01/04 05:22]
louis
+++ products:sbc:vim4:npu:demos:facenet [2024/01/04 21:24] (current)
louis old revision restored (2023/09/20 01:13)
@@ Line 88: / Line 88: @@
         --dtypes "float32" \
         --inference-input-type float32 \
-	--inference-output-type float32 \
+		--inference-output-type float32 \
         --quantize-dtype int8 --outdir onnx_output  \
         --channel-mean-value "0,0,0,255"  \
         --source-file facenet_dataset.txt  \
-        --iterations 500 \
+        --iterations 394 \
         --disable-per-channel False \
         --batch-size 1 --target-platform PRODUCT_PID0XA003
 ```
-<WRAP important >
-Please prepare about 500 pictures for quantification. If the pictures size is smaller than model input size, please resize pictures to input size before quantification.
-</WRAP>
 Run ''convert_adla.sh'' to generate the VIM4 model. The converted model is ''xxx.adla'' in ''onnx_output''.
@@ Line 116: / Line 112: @@
 $ git clone https://github.com/khadas/vim4_npu_applications
 ```
-<WRAP important >
-If your kernel version is 5.4 or earlier, please use tag ''ddk-1.7.5.5''. Tag ''ddk-2.3.6.7'' is for 5.15.
-</WRAP>
 ==== Install dependencies ====

Khadas Docs