diff --git a/assets/yolo/yolov5s_320.onnx b/assets/echo_model/best.bin similarity index 63% rename from assets/yolo/yolov5s_320.onnx rename to assets/echo_model/best.bin index a68df07..e9dbee1 100644 Binary files a/assets/yolo/yolov5s_320.onnx and b/assets/echo_model/best.bin differ diff --git a/assets/echo_model/best.xml b/assets/echo_model/best.xml new file mode 100644 index 0000000..cbcca54 --- /dev/null +++ b/assets/echo_model/best.xml @@ -0,0 +1,10791 @@ + + + + + + + + 1 + 3 + 640 + 640 + + + + + + + + 1 + 2 + 8400 + + + + + + + + 32 + 3 + 3 + 3 + + + + + + + + 1 + 3 + 640 + 640 + + + 32 + 3 + 3 + 3 + + + + + 1 + 32 + 320 + 320 + + + + + + + + 1 + 32 + 1 + 1 + + + + + + + + 1 + 32 + 320 + 320 + + + 1 + 32 + 1 + 1 + + + + + 1 + 32 + 320 + 320 + + + + + + + 1 + 32 + 320 + 320 + + + + + 1 + 32 + 320 + 320 + + + + + + + + 64 + 32 + 3 + 3 + + + + + + + + 1 + 32 + 320 + 320 + + + 64 + 32 + 3 + 3 + + + + + 1 + 64 + 160 + 160 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 160 + 160 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 160 + 160 + + + + + + + 1 + 64 + 160 + 160 + + + + + 1 + 64 + 160 + 160 + + + + + + + + 64 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 160 + 160 + + + 64 + 64 + 1 + 1 + + + + + 1 + 64 + 160 + 160 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 160 + 160 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 160 + 160 + + + + + + + 1 + 64 + 160 + 160 + + + + + 1 + 64 + 160 + 160 + + + + + + + + + + + + + + 2 + + + + + + + 1 + 64 + 160 + 160 + + + + 2 + + + + + 1 + 32 + 160 + 160 + + + 1 + 32 + 160 + 160 + + + + + + + + 16 + 32 + 3 + 3 + + + + + + + + 1 + 32 + 160 + 160 + + + 16 + 32 + 3 + 3 + + + + + 1 + 16 + 160 + 160 + + + + + + + + 1 + 16 + 1 + 1 + + + + + + + + 1 + 16 + 160 + 160 + + + 1 + 16 + 1 + 1 + + + + + 1 + 16 + 160 + 160 + + + + + + + 1 + 16 + 160 + 160 + + + + + 1 + 16 + 160 + 160 + + + + + + + + 32 + 16 + 3 + 3 + + + + + + + + 1 + 16 + 160 + 160 + + + 32 + 16 + 3 + 3 + + + + + 1 + 32 + 160 + 160 + + + + + + + + 1 + 32 + 1 + 1 + + + + + + + + 1 + 32 + 160 + 160 + + + 1 + 32 + 1 + 1 + + + + + 1 + 32 + 160 + 160 + + + + + + + 1 + 32 + 160 + 160 + + + + + 1 + 32 + 160 + 160 + + + + + + + + 1 + 32 + 160 + 160 + + + 1 + 32 + 160 + 160 + + + + + 1 + 32 + 160 + 160 + + + + + + + + 1 + 32 + 160 + 160 + + + 1 + 32 + 160 + 160 + + + 1 + 32 + 160 + 160 + + + + + 1 + 96 + 160 + 160 + + + + + + + + 128 + 96 + 1 + 1 + + + + + + + + 1 + 96 + 160 + 160 + + + 128 + 96 + 1 + 1 + + + + + 1 + 128 + 160 + 160 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 160 + 160 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 160 + 160 + + + + + + + 1 + 128 + 160 + 160 + + + + + 1 + 128 + 160 + 160 + + + + + + + + 128 + 128 + 3 + 3 + + + + + + + + 1 + 128 + 160 + 160 + + + 128 + 128 + 3 + 3 + + + + + 1 + 128 + 80 + 80 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 80 + 80 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 80 + 80 + + + + + + + 1 + 128 + 80 + 80 + + + + + 1 + 128 + 80 + 80 + + + + + + + + 128 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 80 + 80 + + + 128 + 128 + 1 + 1 + + + + + 1 + 128 + 80 + 80 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 80 + 80 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 80 + 80 + + + + + + + 1 + 128 + 80 + 80 + + + + + 1 + 128 + 80 + 80 + + + + + + + + + + + + + + 2 + + + + + + + 1 + 128 + 80 + 80 + + + + 2 + + + + + 1 + 64 + 80 + 80 + + + 1 + 64 + 80 + 80 + + + + + + + + 32 + 64 + 3 + 3 + + + + + + + + 1 + 64 + 80 + 80 + + + 32 + 64 + 3 + 3 + + + + + 1 + 32 + 80 + 80 + + + + + + + + 1 + 32 + 1 + 1 + + + + + + + + 1 + 32 + 80 + 80 + + + 1 + 32 + 1 + 1 + + + + + 1 + 32 + 80 + 80 + + + + + + + 1 + 32 + 80 + 80 + + + + + 1 + 32 + 80 + 80 + + + + + + + + 64 + 32 + 3 + 3 + + + + + + + + 1 + 32 + 80 + 80 + + + 64 + 32 + 3 + 3 + + + + + 1 + 64 + 80 + 80 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 80 + 80 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 80 + 80 + + + + + + + 1 + 64 + 80 + 80 + + + + + 1 + 64 + 80 + 80 + + + + + + + + 1 + 64 + 80 + 80 + + + 1 + 64 + 80 + 80 + + + + + 1 + 64 + 80 + 80 + + + + + + + + 1 + 64 + 80 + 80 + + + 1 + 64 + 80 + 80 + + + 1 + 64 + 80 + 80 + + + + + 1 + 192 + 80 + 80 + + + + + + + + 256 + 192 + 1 + 1 + + + + + + + + 1 + 192 + 80 + 80 + + + 256 + 192 + 1 + 1 + + + + + 1 + 256 + 80 + 80 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 80 + 80 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 80 + 80 + + + + + + + 1 + 256 + 80 + 80 + + + + + 1 + 256 + 80 + 80 + + + + + + + + 256 + 256 + 3 + 3 + + + + + + + + 1 + 256 + 80 + 80 + + + 256 + 256 + 3 + 3 + + + + + 1 + 256 + 40 + 40 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 40 + 40 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 40 + 40 + + + + + + + 1 + 256 + 40 + 40 + + + + + 1 + 256 + 40 + 40 + + + + + + + + 256 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 40 + 40 + + + 256 + 256 + 1 + 1 + + + + + 1 + 256 + 40 + 40 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 40 + 40 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 40 + 40 + + + + + + + 1 + 256 + 40 + 40 + + + + + 1 + 256 + 40 + 40 + + + + + + + + + + + + + + 2 + + + + + + + 1 + 256 + 40 + 40 + + + + 2 + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 40 + 40 + + + + + + + + 64 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 40 + 40 + + + 64 + 128 + 1 + 1 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 40 + 40 + + + + + + + 1 + 64 + 40 + 40 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 64 + 64 + 3 + 3 + + + + + + + + 1 + 64 + 40 + 40 + + + 64 + 64 + 3 + 3 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 40 + 40 + + + + + + + 1 + 64 + 40 + 40 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 64 + 64 + 3 + 3 + + + + + + + + 1 + 64 + 40 + 40 + + + 64 + 64 + 3 + 3 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 40 + 40 + + + + + + + 1 + 64 + 40 + 40 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 64 + 40 + 40 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 64 + 64 + 3 + 3 + + + + + + + + 1 + 64 + 40 + 40 + + + 64 + 64 + 3 + 3 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 40 + 40 + + + + + + + 1 + 64 + 40 + 40 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 64 + 64 + 3 + 3 + + + + + + + + 1 + 64 + 40 + 40 + + + 64 + 64 + 3 + 3 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 40 + 40 + + + + + + + 1 + 64 + 40 + 40 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 64 + 40 + 40 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 64 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 40 + 40 + + + 64 + 128 + 1 + 1 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 40 + 40 + + + + + + + 1 + 64 + 40 + 40 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 64 + 40 + 40 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 128 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 40 + 40 + + + 128 + 128 + 1 + 1 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 40 + 40 + + + + + + + 1 + 128 + 40 + 40 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 40 + 40 + + + + + 1 + 384 + 40 + 40 + + + + + + + + 256 + 384 + 1 + 1 + + + + + + + + 1 + 384 + 40 + 40 + + + 256 + 384 + 1 + 1 + + + + + 1 + 256 + 40 + 40 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 40 + 40 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 40 + 40 + + + + + + + 1 + 256 + 40 + 40 + + + + + 1 + 256 + 40 + 40 + + + + + + + + 512 + 256 + 3 + 3 + + + + + + + + 1 + 256 + 40 + 40 + + + 512 + 256 + 3 + 3 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 1 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 1 + 512 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + 1 + 512 + 20 + 20 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 512 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 512 + 512 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 1 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 1 + 512 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + 1 + 512 + 20 + 20 + + + + + 1 + 512 + 20 + 20 + + + + + + + + + + + + + + 2 + + + + + + + 1 + 512 + 20 + 20 + + + + 2 + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + + + + + + 128 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 128 + 256 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 128 + 128 + 3 + 3 + + + + + + + + 1 + 128 + 20 + 20 + + + 128 + 128 + 3 + 3 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 128 + 128 + 3 + 3 + + + + + + + + 1 + 128 + 20 + 20 + + + 128 + 128 + 3 + 3 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 128 + 128 + 3 + 3 + + + + + + + + 1 + 128 + 20 + 20 + + + 128 + 128 + 3 + 3 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 128 + 128 + 3 + 3 + + + + + + + + 1 + 128 + 20 + 20 + + + 128 + 128 + 3 + 3 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 128 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 128 + 256 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 20 + 20 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 256 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 256 + 256 + 1 + 1 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 20 + 20 + + + + + + + 1 + 256 + 20 + 20 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + + + 1 + 768 + 20 + 20 + + + + + + + + 512 + 768 + 1 + 1 + + + + + + + + 1 + 768 + 20 + 20 + + + 512 + 768 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 1 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 1 + 512 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + 1 + 512 + 20 + 20 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 256 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 256 + 512 + 1 + 1 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 20 + 20 + + + + + + + 1 + 256 + 20 + 20 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 20 + 20 + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 20 + 20 + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 20 + 20 + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + + + 1 + 1024 + 20 + 20 + + + + + + + + 512 + 1024 + 1 + 1 + + + + + + + + 1 + 1024 + 20 + 20 + + + 512 + 1024 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 1 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 1 + 512 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + 1 + 512 + 20 + 20 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 512 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 512 + 512 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 1 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 1 + 512 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + 1 + 512 + 20 + 20 + + + + + 1 + 512 + 20 + 20 + + + + + + + + + + + + + + 2 + + + + + + + 1 + 512 + 20 + 20 + + + + 2 + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + + + + + + 512 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 512 + 256 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 1 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 1 + 512 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 4 + + + + + + + + 1 + 512 + 20 + 20 + + + 4 + + + + + 1 + 4 + 128 + 400 + + + + + + + + + + + + + + 3 + + + + + + + 1 + 4 + 128 + 400 + + + + 3 + + + + + 1 + 4 + 32 + 400 + + + 1 + 4 + 32 + 400 + + + 1 + 4 + 64 + 400 + + + + + + + + 1 + 1 + 1 + 1 + + + + + + + + 1 + 4 + 32 + 400 + + + 1 + 1 + 1 + 1 + + + + + 1 + 4 + 32 + 400 + + + + + + + + 1 + 4 + 32 + 400 + + + 1 + 4 + 32 + 400 + + + + + 1 + 4 + 400 + 400 + + + + + + + + 1 + 4 + 400 + 400 + + + + + 1 + 4 + 400 + 400 + + + + + + + + 1 + 4 + 64 + 400 + + + 1 + 4 + 400 + 400 + + + + + 1 + 4 + 64 + 400 + + + + + + + + 1 + 256 + 20 + 20 + + + + + 4 + + + + + + + + 1 + 4 + 64 + 400 + + + 4 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 4 + 64 + 400 + + + 4 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 256 + 1 + 1 + 3 + 3 + + + + + + + + 1 + 256 + 20 + 20 + + + 256 + 1 + 1 + 3 + 3 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 256 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 256 + 256 + 1 + 1 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 512 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 512 + 256 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 1 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 1 + 512 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + 1 + 512 + 20 + 20 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 256 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 256 + 512 + 1 + 1 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 512 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 512 + 512 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 1 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 1 + 512 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + 1 + 512 + 20 + 20 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 2 + + + + + + + + 2 + + + + + + + + 1 + 512 + 20 + 20 + + + 2 + + + 2 + + + + + 1 + 512 + 40 + 40 + + + + + + + + 1 + 512 + 40 + 40 + + + 1 + 256 + 40 + 40 + + + + + 1 + 768 + 40 + 40 + + + + + + + + 256 + 768 + 1 + 1 + + + + + + + + 1 + 768 + 40 + 40 + + + 256 + 768 + 1 + 1 + + + + + 1 + 256 + 40 + 40 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 40 + 40 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 40 + 40 + + + + + + + 1 + 256 + 40 + 40 + + + + + 1 + 256 + 40 + 40 + + + + + + + + + + + + + + 2 + + + + + + + 1 + 256 + 40 + 40 + + + + 2 + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 40 + 40 + + + + + + + + 64 + 128 + 3 + 3 + + + + + + + + 1 + 128 + 40 + 40 + + + 64 + 128 + 3 + 3 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 40 + 40 + + + + + + + 1 + 64 + 40 + 40 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 128 + 64 + 3 + 3 + + + + + + + + 1 + 64 + 40 + 40 + + + 128 + 64 + 3 + 3 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 40 + 40 + + + + + + + 1 + 128 + 40 + 40 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 40 + 40 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 40 + 40 + + + + + 1 + 384 + 40 + 40 + + + + + + + + 256 + 384 + 1 + 1 + + + + + + + + 1 + 384 + 40 + 40 + + + 256 + 384 + 1 + 1 + + + + + 1 + 256 + 40 + 40 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 40 + 40 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 40 + 40 + + + + + + + 1 + 256 + 40 + 40 + + + + + 1 + 256 + 40 + 40 + + + + + + + + 2 + + + + + + + + 2 + + + + + + + + 1 + 256 + 40 + 40 + + + 2 + + + 2 + + + + + 1 + 256 + 80 + 80 + + + + + + + + 1 + 256 + 80 + 80 + + + 1 + 256 + 80 + 80 + + + + + 1 + 512 + 80 + 80 + + + + + + + + 128 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 80 + 80 + + + 128 + 512 + 1 + 1 + + + + + 1 + 128 + 80 + 80 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 80 + 80 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 80 + 80 + + + + + + + 1 + 128 + 80 + 80 + + + + + 1 + 128 + 80 + 80 + + + + + + + + + + + + + + 2 + + + + + + + 1 + 128 + 80 + 80 + + + + 2 + + + + + 1 + 64 + 80 + 80 + + + 1 + 64 + 80 + 80 + + + + + + + + 32 + 64 + 3 + 3 + + + + + + + + 1 + 64 + 80 + 80 + + + 32 + 64 + 3 + 3 + + + + + 1 + 32 + 80 + 80 + + + + + + + + 1 + 32 + 1 + 1 + + + + + + + + 1 + 32 + 80 + 80 + + + 1 + 32 + 1 + 1 + + + + + 1 + 32 + 80 + 80 + + + + + + + 1 + 32 + 80 + 80 + + + + + 1 + 32 + 80 + 80 + + + + + + + + 64 + 32 + 3 + 3 + + + + + + + + 1 + 32 + 80 + 80 + + + 64 + 32 + 3 + 3 + + + + + 1 + 64 + 80 + 80 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 80 + 80 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 80 + 80 + + + + + + + 1 + 64 + 80 + 80 + + + + + 1 + 64 + 80 + 80 + + + + + + + + 1 + 64 + 80 + 80 + + + 1 + 64 + 80 + 80 + + + + + 1 + 64 + 80 + 80 + + + + + + + + 1 + 64 + 80 + 80 + + + 1 + 64 + 80 + 80 + + + 1 + 64 + 80 + 80 + + + + + 1 + 192 + 80 + 80 + + + + + + + + 128 + 192 + 1 + 1 + + + + + + + + 1 + 192 + 80 + 80 + + + 128 + 192 + 1 + 1 + + + + + 1 + 128 + 80 + 80 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 80 + 80 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 80 + 80 + + + + + + + 1 + 128 + 80 + 80 + + + + + 1 + 128 + 80 + 80 + + + + + + + + 64 + 128 + 3 + 3 + + + + + + + + 1 + 128 + 80 + 80 + + + 64 + 128 + 3 + 3 + + + + + 1 + 64 + 80 + 80 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 80 + 80 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 80 + 80 + + + + + + + 1 + 64 + 80 + 80 + + + + + 1 + 64 + 80 + 80 + + + + + + + + 64 + 64 + 3 + 3 + + + + + + + + 1 + 64 + 80 + 80 + + + 64 + 64 + 3 + 3 + + + + + 1 + 64 + 80 + 80 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 80 + 80 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 80 + 80 + + + + + + + 1 + 64 + 80 + 80 + + + + + 1 + 64 + 80 + 80 + + + + + + + + 64 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 80 + 80 + + + 64 + 64 + 1 + 1 + + + + + 1 + 64 + 80 + 80 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 80 + 80 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 80 + 80 + + + + + + + + 128 + 1 + 1 + 3 + 3 + + + + + + + + 1 + 128 + 80 + 80 + + + 128 + 1 + 1 + 3 + 3 + + + + + 1 + 128 + 80 + 80 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 80 + 80 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 80 + 80 + + + + + + + 1 + 128 + 80 + 80 + + + + + 1 + 128 + 80 + 80 + + + + + + + + 128 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 80 + 80 + + + 128 + 128 + 1 + 1 + + + + + 1 + 128 + 80 + 80 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 80 + 80 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 80 + 80 + + + + + + + 1 + 128 + 80 + 80 + + + + + 1 + 128 + 80 + 80 + + + + + + + + 128 + 1 + 1 + 3 + 3 + + + + + + + + 1 + 128 + 80 + 80 + + + 128 + 1 + 1 + 3 + 3 + + + + + 1 + 128 + 80 + 80 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 80 + 80 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 80 + 80 + + + + + + + 1 + 128 + 80 + 80 + + + + + 1 + 128 + 80 + 80 + + + + + + + + 128 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 80 + 80 + + + 128 + 128 + 1 + 1 + + + + + 1 + 128 + 80 + 80 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 80 + 80 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 80 + 80 + + + + + + + 1 + 128 + 80 + 80 + + + + + 1 + 128 + 80 + 80 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 80 + 80 + + + 1 + 128 + 1 + 1 + + + + + 1 + 1 + 80 + 80 + + + + + + + + 1 + 1 + 1 + 1 + + + + + + + + 1 + 1 + 80 + 80 + + + 1 + 1 + 1 + 1 + + + + + 1 + 1 + 80 + 80 + + + + + + + + 1 + 64 + 80 + 80 + + + 1 + 1 + 80 + 80 + + + + + 1 + 65 + 80 + 80 + + + + + + + + 3 + + + + + + + + 1 + 65 + 80 + 80 + + + 3 + + + + + 1 + 65 + 6400 + + + + + + + + 128 + 128 + 3 + 3 + + + + + + + + 1 + 128 + 80 + 80 + + + 128 + 128 + 3 + 3 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 40 + 40 + + + + + + + 1 + 128 + 40 + 40 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 1 + 128 + 40 + 40 + + + 1 + 256 + 40 + 40 + + + + + 1 + 384 + 40 + 40 + + + + + + + + 256 + 384 + 1 + 1 + + + + + + + + 1 + 384 + 40 + 40 + + + 256 + 384 + 1 + 1 + + + + + 1 + 256 + 40 + 40 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 40 + 40 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 40 + 40 + + + + + + + 1 + 256 + 40 + 40 + + + + + 1 + 256 + 40 + 40 + + + + + + + + + + + + + + 2 + + + + + + + 1 + 256 + 40 + 40 + + + + 2 + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 40 + 40 + + + + + + + + 64 + 128 + 3 + 3 + + + + + + + + 1 + 128 + 40 + 40 + + + 64 + 128 + 3 + 3 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 40 + 40 + + + + + + + 1 + 64 + 40 + 40 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 128 + 64 + 3 + 3 + + + + + + + + 1 + 64 + 40 + 40 + + + 128 + 64 + 3 + 3 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 40 + 40 + + + + + + + 1 + 128 + 40 + 40 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 40 + 40 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 40 + 40 + + + + + 1 + 384 + 40 + 40 + + + + + + + + 256 + 384 + 1 + 1 + + + + + + + + 1 + 384 + 40 + 40 + + + 256 + 384 + 1 + 1 + + + + + 1 + 256 + 40 + 40 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 40 + 40 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 40 + 40 + + + + + + + 1 + 256 + 40 + 40 + + + + + 1 + 256 + 40 + 40 + + + + + + + + 64 + 256 + 3 + 3 + + + + + + + + 1 + 256 + 40 + 40 + + + 64 + 256 + 3 + 3 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 40 + 40 + + + + + + + 1 + 64 + 40 + 40 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 64 + 64 + 3 + 3 + + + + + + + + 1 + 64 + 40 + 40 + + + 64 + 64 + 3 + 3 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 40 + 40 + + + + + + + 1 + 64 + 40 + 40 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 64 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 40 + 40 + + + 64 + 64 + 1 + 1 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 40 + 40 + + + + + + + + 256 + 1 + 1 + 3 + 3 + + + + + + + + 1 + 256 + 40 + 40 + + + 256 + 1 + 1 + 3 + 3 + + + + + 1 + 256 + 40 + 40 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 40 + 40 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 40 + 40 + + + + + + + 1 + 256 + 40 + 40 + + + + + 1 + 256 + 40 + 40 + + + + + + + + 128 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 40 + 40 + + + 128 + 256 + 1 + 1 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 40 + 40 + + + + + + + 1 + 128 + 40 + 40 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 128 + 1 + 1 + 3 + 3 + + + + + + + + 1 + 128 + 40 + 40 + + + 128 + 1 + 1 + 3 + 3 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 40 + 40 + + + + + + + 1 + 128 + 40 + 40 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 128 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 40 + 40 + + + 128 + 128 + 1 + 1 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 40 + 40 + + + + + + + 1 + 128 + 40 + 40 + + + + + 1 + 128 + 40 + 40 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 40 + 40 + + + 1 + 128 + 1 + 1 + + + + + 1 + 1 + 40 + 40 + + + + + + + + 1 + 1 + 1 + 1 + + + + + + + + 1 + 1 + 40 + 40 + + + 1 + 1 + 1 + 1 + + + + + 1 + 1 + 40 + 40 + + + + + + + + 1 + 64 + 40 + 40 + + + 1 + 1 + 40 + 40 + + + + + 1 + 65 + 40 + 40 + + + + + + + + 3 + + + + + + + + 1 + 65 + 40 + 40 + + + 3 + + + + + 1 + 65 + 1600 + + + + + + + + 256 + 256 + 3 + 3 + + + + + + + + 1 + 256 + 40 + 40 + + + 256 + 256 + 3 + 3 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 20 + 20 + + + + + + + 1 + 256 + 20 + 20 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 512 + 20 + 20 + + + + + 1 + 768 + 20 + 20 + + + + + + + + 512 + 768 + 1 + 1 + + + + + + + + 1 + 768 + 20 + 20 + + + 512 + 768 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 1 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 1 + 512 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + 1 + 512 + 20 + 20 + + + + + 1 + 512 + 20 + 20 + + + + + + + + + + + + + + 2 + + + + + + + 1 + 512 + 20 + 20 + + + + 2 + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + + + + + + 128 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 128 + 256 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 128 + 128 + 3 + 3 + + + + + + + + 1 + 128 + 20 + 20 + + + 128 + 128 + 3 + 3 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 128 + 128 + 3 + 3 + + + + + + + + 1 + 128 + 20 + 20 + + + 128 + 128 + 3 + 3 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 128 + 128 + 3 + 3 + + + + + + + + 1 + 128 + 20 + 20 + + + 128 + 128 + 3 + 3 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 128 + 128 + 3 + 3 + + + + + + + + 1 + 128 + 20 + 20 + + + 128 + 128 + 3 + 3 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 128 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 128 + 256 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 20 + 20 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 256 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 256 + 256 + 1 + 1 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 1 + 1 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 1 + 1 + + + + + 1 + 256 + 20 + 20 + + + + + + + 1 + 256 + 20 + 20 + + + + + 1 + 256 + 20 + 20 + + + + + + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + 1 + 256 + 20 + 20 + + + + + 1 + 768 + 20 + 20 + + + + + + + + 512 + 768 + 1 + 1 + + + + + + + + 1 + 768 + 20 + 20 + + + 512 + 768 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 1 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 1 + 512 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + 1 + 512 + 20 + 20 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 64 + 512 + 3 + 3 + + + + + + + + 1 + 512 + 20 + 20 + + + 64 + 512 + 3 + 3 + + + + + 1 + 64 + 20 + 20 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 20 + 20 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 20 + 20 + + + + + + + 1 + 64 + 20 + 20 + + + + + 1 + 64 + 20 + 20 + + + + + + + + 64 + 64 + 3 + 3 + + + + + + + + 1 + 64 + 20 + 20 + + + 64 + 64 + 3 + 3 + + + + + 1 + 64 + 20 + 20 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 20 + 20 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 20 + 20 + + + + + + + 1 + 64 + 20 + 20 + + + + + 1 + 64 + 20 + 20 + + + + + + + + 64 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 20 + 20 + + + 64 + 64 + 1 + 1 + + + + + 1 + 64 + 20 + 20 + + + + + + + + 1 + 64 + 1 + 1 + + + + + + + + 1 + 64 + 20 + 20 + + + 1 + 64 + 1 + 1 + + + + + 1 + 64 + 20 + 20 + + + + + + + + 512 + 1 + 1 + 3 + 3 + + + + + + + + 1 + 512 + 20 + 20 + + + 512 + 1 + 1 + 3 + 3 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 1 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 1 + 512 + 1 + 1 + + + + + 1 + 512 + 20 + 20 + + + + + + + 1 + 512 + 20 + 20 + + + + + 1 + 512 + 20 + 20 + + + + + + + + 128 + 512 + 1 + 1 + + + + + + + + 1 + 512 + 20 + 20 + + + 128 + 512 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 128 + 1 + 1 + 3 + 3 + + + + + + + + 1 + 128 + 20 + 20 + + + 128 + 1 + 1 + 3 + 3 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 128 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 128 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 128 + 20 + 20 + + + + + + + 1 + 128 + 20 + 20 + + + + + 1 + 128 + 20 + 20 + + + + + + + + 1 + 128 + 1 + 1 + + + + + + + + 1 + 128 + 20 + 20 + + + 1 + 128 + 1 + 1 + + + + + 1 + 1 + 20 + 20 + + + + + + + + 1 + 1 + 1 + 1 + + + + + + + + 1 + 1 + 20 + 20 + + + 1 + 1 + 1 + 1 + + + + + 1 + 1 + 20 + 20 + + + + + + + + 1 + 64 + 20 + 20 + + + 1 + 1 + 20 + 20 + + + + + 1 + 65 + 20 + 20 + + + + + + + + 3 + + + + + + + + 1 + 65 + 20 + 20 + + + 3 + + + + + 1 + 65 + 400 + + + + + + + + 1 + 65 + 6400 + + + 1 + 65 + 1600 + + + 1 + 65 + 400 + + + + + 1 + 65 + 8400 + + + + + + + + + + + + + + 2 + + + + + + + 1 + 65 + 8400 + + + + 2 + + + + + 1 + 64 + 8400 + + + 1 + 1 + 8400 + + + + + + + + 4 + + + + + + + + 1 + 64 + 8400 + + + 4 + + + + + 1 + 4 + 16 + 8400 + + + + + + + + 4 + + + + + + + 1 + 4 + 16 + 8400 + + + 4 + + + + + 1 + 16 + 4 + 8400 + + + + + + + + 1 + 16 + 4 + 8400 + + + + + 1 + 16 + 4 + 8400 + + + + + + + + 1 + 16 + 1 + 1 + + + + + + + + 1 + 16 + 4 + 8400 + + + 1 + 16 + 1 + 1 + + + + + 1 + 1 + 4 + 8400 + + + + + + + + 3 + + + + + + + + 1 + 1 + 4 + 8400 + + + 3 + + + + + 1 + 4 + 8400 + + + + + + + + 1 + + + + + + + + + + + + + + 4 + + + 1 + + + + + + 1 + + + + + + + + 1 + + + + + + + + 1 + 64 + 8400 + + + + + 3 + + + + + + + + 1 + + + + + + + + + + + + + + 3 + + + 1 + + + + + + 1 + + + + + + + + 1 + + + 1 + + + 1 + + + + + 3 + + + + + + + + 3 + + + + + 3 + + + + + + + + 1 + + + + + + + + 3 + + + + 1 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 1 + + + + + 1 + + + + + + + + 1 + + + + + 1 + + + + + + + + + 1 + + + + + 1 + + + + + + + + 1 + + + + + + + + 1 + + + 1 + + + + + 2 + + + + + + + 1 + 4 + 8400 + + + + 2 + + + + + 1 + 2 + 8400 + + + 1 + 2 + 8400 + + + + + + + + 1 + 2 + 8400 + + + 1 + 2 + 8400 + + + + + 1 + 2 + 8400 + + + + + + + + 1 + 2 + 8400 + + + 1 + 2 + 8400 + + + + + 1 + 2 + 8400 + + + + + + + + 1 + 2 + 8400 + + + 1 + 2 + 8400 + + + + + 1 + 2 + 8400 + + + + + + + + 1 + 1 + 1 + + + + + + + + 1 + 2 + 8400 + + + 1 + 1 + 1 + + + + + 1 + 2 + 8400 + + + + + + + + 1 + 2 + 8400 + + + 1 + 2 + 8400 + + + + + 1 + 2 + 8400 + + + + + + + + 1 + 2 + 8400 + + + 1 + 2 + 8400 + + + + + 1 + 4 + 8400 + + + + + + + + 1 + 1 + 8400 + + + + + + + + 1 + 4 + 8400 + + + 1 + 1 + 8400 + + + + + 1 + 4 + 8400 + + + + + + + 1 + 1 + 8400 + + + + + 1 + 1 + 8400 + + + + + + + + 1 + 4 + 8400 + + + 1 + 1 + 8400 + + + + + 1 + 5 + 8400 + + + + + + + 1 + 5 + 8400 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/assets/echo_model/metadata.yaml b/assets/echo_model/metadata.yaml new file mode 100644 index 0000000..eb3293b --- /dev/null +++ b/assets/echo_model/metadata.yaml @@ -0,0 +1,21 @@ +description: Ultralytics YOLO11s model trained on split_dataset\data.yaml +author: Ultralytics +date: '2025-04-16T09:53:39.504253' +version: 8.3.108 +license: AGPL-3.0 License (https://ultralytics.com/license) +docs: https://docs.ultralytics.com +stride: 32 +task: detect +batch: 1 +imgsz: +- 640 +- 640 +names: + 0: echo +args: + batch: 1 + fraction: 1.0 + half: false + int8: false + dynamic: false + nms: false diff --git a/src/OpenVinoYolo8Detect.py b/src/OpenVinoYolo8Detect.py new file mode 100644 index 0000000..fea594d --- /dev/null +++ b/src/OpenVinoYolo8Detect.py @@ -0,0 +1,271 @@ +import os +import random +import time +from typing import Tuple + +# import onnxruntime as ort # Removed onnxruntime +from openvino import Core # Added OpenVINO Core +import cv2 +import numpy as np + +from ok import Logger, Box, sort_boxes + +logger = Logger.get_logger(__name__) + + +class OpenVinoYolo8Detect: # Renamed class + + def __init__(self, weights='echo.onnx', model_h=640, model_w=640, iou_thres=0.45): + """ + yolov OpenVINO inference + dic_labels: {0: 'person', 1: 'bicycle'} + """ + self.dic_labels = {0: 'echo'} + self.weights = weights + self.model_size = (model_w, model_h) + self.iou_threshold = iou_thres + self.openfile_name_model = weights + + # --- OpenVINO Initialization --- + self.core = Core() + # self.core.set_property("CPU", {"INFERENCE_NUM_THREADS": str(1)}) + device = "CPU" # Default device, tries GPU then CPU etc. + + try: + logger.info(f"Compiling OpenVINO model for {device}...") + # Read and compile the ONNX model directly + model = self.core.read_model(model=self.openfile_name_model) + self.compiled_model = self.core.compile_model(model=model, device_name=device, + config={"PERFORMANCE_HINT": "LATENCY"},) + # Get input/output names (usually one input, one output for YOLOv5) + self.input_layer = self.compiled_model.input(0) + self.output_layer = self.compiled_model.output(0) + self.input_width = self.input_layer.shape[2] + self.input_height = self.input_layer.shape[3] + logger.info(f"OpenVINO model compiled successfully for {self.compiled_model} {self.input_width}x{self.input_height}.") + except Exception as e: + logger.error(f"Error initializing OpenVINO: {e}") + raise RuntimeError("Could not initialize OpenVINO model") from e + # --- End OpenVINO Initialization --- + + def letterbox(self, img: np.ndarray, new_shape: Tuple[int, int] = (640, 640)) -> Tuple[np.ndarray, Tuple[int, int]]: + """ + Resize and reshape images while maintaining aspect ratio by adding padding. + + Args: + img (np.ndarray): Input image to be resized. + new_shape (Tuple[int, int]): Target shape (height, width) for the image. + + Returns: + (np.ndarray): Resized and padded image. + (Tuple[int, int]): Padding values (top, left) applied to the image. + """ + shape = img.shape[:2] # current shape [height, width] + + # Scale ratio (new / old) + r = min(new_shape[0] / shape[0], new_shape[1] / shape[1]) + + # Compute padding + new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r)) + dw, dh = (new_shape[1] - new_unpad[0]) / 2, (new_shape[0] - new_unpad[1]) / 2 # wh padding + + if shape[::-1] != new_unpad: # resize + img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR) + top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1)) + left, right = int(round(dw - 0.1)), int(round(dw + 0.1)) + img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=(114, 114, 114)) + + return img, (top, left) + + def _preprocess(self, img): + """图像预处理（保持宽高比的缩放填充） - unchanged""" + img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) + + img, pad = self.letterbox(img, (self.input_width, self.input_height)) + + # Normalize the image data by dividing it by 255.0 + image_data = np.array(img) / 255.0 + + # Transpose the image to have the channel dimension as the first dimension + image_data = np.transpose(image_data, (2, 0, 1)) # Channel first + + # Expand the dimensions of the image data to match the expected input shape + image_data = np.expand_dims(image_data, axis=0).astype(np.float32) + + # Return the preprocessed image data + return image_data, pad + + + def _postprocess(self, outputs, padding, orig_shape, confidence_threshold, label): + """ + Perform post-processing on the model's output to extract and visualize detections. + + This method processes the raw model output to extract bounding boxes, scores, and class IDs. + It applies non-maximum suppression to filter overlapping detections and draws the results on the input image. + + Args: + input_image (np.ndarray): The input image. + output (List[np.ndarray]): The output arrays from the model. + pad (Tuple[int, int]): Padding values (top, left) used during letterboxing. + + Returns: + (np.ndarray): The input image with detections drawn on it. + """ + # Transpose and squeeze the output to match the expected shape + outputs = np.transpose(np.squeeze(outputs[0])) + + # Get the number of rows in the outputs array + rows = outputs.shape[0] + + # Lists to store the bounding boxes, scores, and class IDs of the detections + boxes = [] + scores = [] + class_ids = [] + + # Calculate the scaling factors for the bounding box coordinates + gain = min(orig_shape[0] / orig_shape[0], self.input_width / orig_shape[1]) + + outputs[:, 0] -= padding[1] + outputs[:, 1] -= padding[0] + + # Iterate over each row in the outputs array + for i in range(rows): + # Extract the class scores from the current row + classes_scores = outputs[i][4:] + + # Find the maximum score among the class scores + max_score = np.amax(classes_scores) + class_id = np.argmax(classes_scores) + # If the maximum score is above the confidence threshold + if max_score >= confidence_threshold and (label==-1 or label==class_id): + # Get the class ID with the highest score + + + # Extract the bounding box coordinates from the current row + x, y, w, h = outputs[i][0], outputs[i][1], outputs[i][2], outputs[i][3] + + # Calculate the scaled coordinates of the bounding box + left = int((x - w / 2) / gain) + top = int((y - h / 2) / gain) + width = int(w / gain) + height = int(h / gain) + + # Add the class ID, score, and box coordinates to the respective lists + class_ids.append(class_id) + scores.append(max_score) + boxes.append([left, top, width, height]) + + # Apply non-maximum suppression to filter out overlapping bounding boxes + indices = cv2.dnn.NMSBoxes(boxes, scores, confidence_threshold, self.iou_threshold) + + # Iterate over the selected indices after non-maximum suppression + results = [] + for i in indices: + # Get the box, score, and class ID corresponding to the index + box = boxes[i] + box_obj = Box(box[0], box[1], box[2], box[3]) # Use Box class if available + box_obj.name = self.dic_labels.get(int(class_ids[i]), 'unknown') + box_obj.confidence = scores[i] + results.append(box_obj) + # Draw the detection on the input image + # self.draw_detections(input_image, box, score, class_id) + return results + + # 推理 + def detect(self, image, threshold=0.5, label=-1): + ''' + 预测 + ''' + try: + h, w = image.shape[:2] + img_data, pad = self._preprocess(image) + # input_tensor = np.expand_dims(img_data, axis=0) # Add batch dimension + + # --- OpenVINO Inference --- + # Input is a dictionary {input_layer_name: data} + # Output is a dictionary {output_layer_name: data} + results = self.compiled_model({self.input_layer: img_data}) + # Extract the output tensor using the output layer obtained during init + outputs = results[self.output_layer] + # --- End OpenVINO Inference --- + boxes = self._postprocess(outputs, pad, (h, w), threshold, label) + + return sort_boxes(boxes) + except Exception as e: + logger.error(f'OpenVINO yolo detect error:', e) # Added exc_info + return [] + + +# --- Main execution part needs to be updated to use the new class --- +if __name__ == '__main__': + # Ensure ok module and Box class are available, or provide stubs + class MockLogger: + def get_logger(self, name): return self + + def debug(self, msg, *args): print(f"DEBUG: {msg}") + + def info(self, msg, *args): print(f"INFO: {msg}") + + def warning(self, msg, *args): print(f"WARN: {msg}") + + def error(self, msg, *args, **kwargs): print(f"ERROR: {msg}") + + + class MockOk: + class og: use_dml = False # Simulate ok.og.use_dml if needed + + Logger = MockLogger() + + + if 'ok' not in globals(): # Define stubs if 'ok' module is not present + ok = MockOk() + Logger = ok.Logger + + + class Box: + def __init__(self, x, y, w, h): + self.x, self.y, self.w, self.h = x, y, w, h + self.name = "unknown" + self.confidence = 0.0 + + def __repr__(self): + return f"Box(x={self.x}, y={self.y}, w={self.w}, h={self.h}, name='{self.name}', conf={self.confidence:.2f})" + + image_path = "tests/images/echo.png" + weights = "assets/echo_model/best.xml" # OpenVINO reads ONNX directly + model_h = 640 + model_w = 640 + + + # NOTE: You need a real ONNX model at the 'weights' path for inference to work. + if not os.path.exists(weights): + print(f"ERROR: Model file not found at {weights}. Inference will fail.") + print("Please download or place yolov5s_320.onnx in assets/yolo/") + # Create a dummy file to avoid immediate crash during init, but it won't work + # with open(weights, 'w') as f: f.write('') # This won't be a valid model + + # Use the new OpenVINO class + yolov = OpenVinoYolo8Detect(weights=weights, model_w=model_w, model_h=model_h) + + # Test 1 + big_img = cv2.imdecode(np.fromfile(file=image_path, dtype=np.uint8), cv2.IMREAD_COLOR) + if big_img is None: + print(f"Error loading image: {image_path}") + else: + start_time = time.time() + for i in range(100): + res_loc = yolov.detect(big_img, label=0) # label=12 -> '声骸' + end_time = time.time() + print(f"Detection 1 time: {(end_time - start_time) * 1000:.2f} ms") + + # Test 2 + img2 = cv2.imread("tests/images/echo2.png") + if img2 is None: + print("Error loading image: tests/images/echo2.png") + else: + start_time = time.time() + for i in range(100): + res_loc = yolov.detect(img2, label=0) + end_time = time.time() + print(f"Detection 2 time: {(end_time - start_time) * 1000:.2f} ms") + diff --git a/src/combat/CombatCheck.py b/src/combat/CombatCheck.py index 46b6785..b6b8699 100644 --- a/src/combat/CombatCheck.py +++ b/src/combat/CombatCheck.py @@ -196,7 +196,7 @@ class CombatCheck(BaseWWTask): return self.wait_until(self.has_target, time_out=self.target_enemy_time_out, pre_action=lambda: self.middle_click(interval=0.2)) - def check_health_bar(self): + def has_health_bar(self): if self._in_combat: min_height = self.height_of_screen(12 / 2160) max_height = min_height * 3 @@ -221,8 +221,13 @@ class CombatCheck(BaseWWTask): self.boss_health = self.boss_health_box.crop_frame(self.frame) self.draw_boxes('boss_health', boxes, color='blue') return True + return False - return self.find_boss_lv_text() + def check_health_bar(self): + if self.has_health_bar(): + return True + else: + return self.find_boss_lv_text() def find_boss_lv_text(self): texts = self.ocr(box=self.box_of_screen(1269 / 3840, 10 / 2160, 2533 / 3840, 140 / 2160, hcenter=True), diff --git a/src/globals.py b/src/globals.py index f4ccb8a..a85552d 100644 --- a/src/globals.py +++ b/src/globals.py @@ -5,7 +5,7 @@ import cv2 from PySide6.QtCore import Signal, QObject from ok import Config, Logger, get_path_relative_to_exe -from src.OpenVinoYoloDetect import OpenVinoYoloDetect +from src.OpenVinoYolo8Detect import OpenVinoYolo8Detect logger = Logger.get_logger(__name__) @@ -21,10 +21,10 @@ class Globals(QObject): @property def yolo_model(self): if self._yolo_model is None: - self._yolo_model = OpenVinoYoloDetect(weights=get_path_relative_to_exe(os.path.join("assets","yolo", "yolov5s_320.onnx"))) + self._yolo_model = OpenVinoYolo8Detect(weights=get_path_relative_to_exe(os.path.join("assets", "echo_model", "best.xml"))) return self._yolo_model - def yolo_detect(self, image, threshold=0.5, label=-1): + def yolo_detect(self, image, threshold=0.6, label=-1): return self.yolo_model.detect(image, threshold=threshold, label=label) diff --git a/src/task/AutoCombatTask.py b/src/task/AutoCombatTask.py index 8df41b9..23e5474 100644 --- a/src/task/AutoCombatTask.py +++ b/src/task/AutoCombatTask.py @@ -20,7 +20,7 @@ class AutoCombatTask(BaseCombatTask, TriggerTask): self.scene: WWScene | None = None self.default_config.update({ 'Auto Target': True, - 'Auto Pick Echo After Combat': True, + 'Auto Pick Echo After Combat': False, }) self.config_description = { 'Auto Target': 'Turn off to enable auto combat only when manually target enemy using middle click' diff --git a/src/task/BaseCombatTask.py b/src/task/BaseCombatTask.py index 695429f..5797f8c 100644 --- a/src/task/BaseCombatTask.py +++ b/src/task/BaseCombatTask.py @@ -116,7 +116,7 @@ class BaseCombatTask(CombatCheck): self.wait_in_team_and_world(time_out=10) self.sleep(1) self.middle_click() - self.sleep(0.2) + self.sleep(1) def run_in_circle_to_find_echo(self, circle_count=3): directions = ['w', 'a', 's', 'd'] diff --git a/src/task/BaseWWTask.py b/src/task/BaseWWTask.py index bea7dbc..52db9b0 100644 --- a/src/task/BaseWWTask.py +++ b/src/task/BaseWWTask.py @@ -141,15 +141,59 @@ class BaseWWTask(BaseTask): return None return f - def walk_to_box(self, find_function, time_out=30, end_condition=None, y_offset=0.05, v_move_fix_time=0): + def walk_to_yolo_echo(self, time_out=15): + last_direction = None + start = time.time() + no_echo_start = 0 + while time.time() - start < time_out: + self.next_frame() + if self.pick_echo(): + return True + echos = self.find_echos() + if not echos: + if no_echo_start == 0: + no_echo_start = time.time() + elif time.time() - no_echo_start > 1.5: + self.log_debug(f'walk front to_echo, no echos found, break') + break + continue + else: + no_echo_start = 0 + echo = echos[0] + center_distance = echo.center()[0] - self.width_of_screen(0.5) + threshold = 0.05 if not last_direction else 0.15 + if abs(center_distance) < self.height_of_screen(threshold): + if echo.y + echo.height > self.height_of_screen(0.65): + next_direction = 's' + else: + next_direction = 'w' + elif center_distance > 0: + next_direction = 'd' + else: + next_direction = 'a' + last_direction = self._walk_direction(last_direction, next_direction) + self._stop_last_direction(last_direction) + + + def _walk_direction(self, last_direction, next_direction): + if next_direction != last_direction: + self._stop_last_direction(last_direction) + if next_direction: + self.send_key_down(next_direction) + return next_direction + + def _stop_last_direction(self, last_direction): + if last_direction: + self.send_key_up(last_direction) + self.sleep(0.01) + return None + + def walk_to_box(self, find_function, time_out=30, end_condition=None, y_offset=0.05): if not find_function: self.log_info('find_function not found, break') return False last_direction = None - v_fix_count = 0 - original_y_offset = y_offset start = time.time() - last_v_move = start ended = False last_target = None while time.time() - start < time_out: @@ -166,27 +210,14 @@ class BaseWWTask(BaseTask): treasure_icon = None if treasure_icon: last_target = treasure_icon - next_direction = None if last_target is None: - if not end_condition: - self.log_info('find_function not found, break') - break - if 0 < v_move_fix_time < time.time() - last_v_move: - if v_fix_count < 5: - v_fix_count += 1 - y_offset = original_y_offset - 0.05 * v_fix_count - else: - v_fix_count += 1 - y_offset = original_y_offset + 0.05 * (v_fix_count - 4) - - if next_direction is None: + next_direction = self.opposite_direction(last_direction) + self.log_info('find_function not found, change to opposite direction') + else: x, y = last_target.center() y = max(0, y - self.height_of_screen(y_offset)) next_direction = self.get_direction(x, y, self.width, self.height, current_direction=last_direction) - if next_direction == 'w' or next_direction == 's': - last_v_move = time.time() - if next_direction != last_direction: if last_direction: self.send_key_up(last_direction) @@ -405,7 +436,7 @@ class BaseWWTask(BaseTask): result = self.executor.ocr_lib(image, use_det=True, use_cls=False, use_rec=True) self.logger.info(f'ocr_result {result}') - def find_echo(self, threshold=0.5): + def find_echos(self, threshold=0.6): """ Main function to load ONNX model, perform inference, draw bounding boxes, and display the output image. @@ -417,12 +448,12 @@ class BaseWWTask(BaseTask): list: List of dictionaries containing detection information such as class_id, class_name, confidence, etc. """ # Load the ONNX model - boxes = og.my_app.yolo_detect(self.frame, threshold=threshold, label=12) + ret = og.my_app.yolo_detect(self.frame, threshold=threshold, label=0) - ret = sorted(boxes, key=lambda detection: detection.x, reverse=True) for box in ret: - box.y -= box.height * 2/3 + box.y += box.height * 1/3 box.height = 1 + self.draw_boxes("echo", ret) return ret def yolo_find_all(self, threshold=0.3): @@ -454,7 +485,7 @@ class BaseWWTask(BaseTask): self.send_key('f') return True - def yolo_find_echo(self, use_color=True, walk=True, turn=True): + def yolo_find_echo(self, use_color=False, turn=True): if self.debug: # self.draw_boxes('echo', echos) self.screenshot('yolo_echo_start') @@ -467,14 +498,13 @@ class BaseWWTask(BaseTask): for i in range(4): if turn: self.center_camera() - echos = self.find_echo() - if len(echos) > 0: - self.draw_boxes('yolo_echo', echos) + echos = self.find_echos() max_echo_count = max(max_echo_count, len(echos)) self.log_debug(f'max_echo_count {max_echo_count}') if echos: self.log_info(f'yolo found echo {echos}') - return self.walk_to_box(self.find_echo, time_out=15, end_condition=self.pick_echo, v_move_fix_time=5), max_echo_count > 1 + # return self.walk_to_box(self.find_echos, time_out=15, end_condition=self.pick_echo), max_echo_count > 1 + return self.walk_to_yolo_echo(), max_echo_count > 1 if use_color: color_percent = self.calculate_color_percentage(echo_color, front_box) self.log_debug(f'pick_echo color_percent:{color_percent}') @@ -482,28 +512,26 @@ class BaseWWTask(BaseTask): # if self.debug: # self.screenshot('echo_color_picked') self.log_debug(f'found color_percent {color_percent} > {color_threshold}, walk now') - return self.walk_find_echo(), max_echo_count > 1 - if not turn and i==0: + #return self.walk_to_box(self.find_echos, time_out=15, end_condition=self.pick_echo), max_echo_count > 1 + return self.walk_to_yolo_echo(), max_echo_count > 1 + if not turn and i == 0: return False, max_echo_count > 1 self.send_key('a', down_time=0.05) self.sleep(0.5) self.center_camera() - if walk: - picked = self.walk_find_echo() - return picked, max_echo_count > 1 return False, max_echo_count > 1 def center_camera(self): - self.click(0.5, 0.5, down_time=0.2, after_sleep=0.5, key='middle') + self.click(0.5, 0.5, down_time=0.2, after_sleep=1, key='middle') def turn_direction(self, direction): if direction != 'w': self.send_key(direction, down_time=0.05, after_sleep=0.5) self.center_camera() - def walk_find_echo(self, backward_time=1): - if self.walk_until_f(time_out=4, backward_time=backward_time, target_text=self.absorb_echo_text(), + def walk_find_echo(self, backward_time=1, time_out=4): + if self.walk_until_f(time_out=time_out, backward_time=backward_time, target_text=self.absorb_echo_text(), raise_if_not_found=False): # find and pick echo logger.debug(f'farm echo found echo move forward walk_until_f to find echo') return True @@ -659,13 +687,13 @@ class BaseWWTask(BaseTask): self.sleep(1) def openF2Book(self, feature="gray_book_all_monsters"): - self.log_info('click f2 to open the book') - # self.send_key_down('alt') - # self.sleep(0.05) - # self.click_relative(0.77, 0.05) - # self.send_key_up('alt') self.sleep(1) - self.send_key('f2') + self.log_info('click f2 to open the book') + self.send_key_down('alt') + self.sleep(0.05) + self.click_relative(0.77, 0.05) + self.send_key_up('alt') + # self.send_key('f2') gray_book_boss = self.wait_book(feature) if not gray_book_boss: self.log_error("can't find gray_book_boss, make sure f2 is the hotkey for book", notify=True) diff --git a/src/task/FarmMapTask.py b/src/task/FarmMapTask.py index db41e9b..fe85c62 100644 --- a/src/task/FarmMapTask.py +++ b/src/task/FarmMapTask.py @@ -157,7 +157,7 @@ class BigMap(WWOneTimeTask, BaseCombatTask): self.draw_boxes('me', in_big_map.scale(0.1), color='blue') # self.screenshot('box_minimap', frame=frame, show_box=True) # self.screenshot('template_minimap', frame=mat) - self.my_box = in_big_map.scale(1.25) + self.my_box = in_big_map.scale(1.3) return in_big_map def create_circle_mask_with_hole(image): @@ -201,6 +201,7 @@ class FarmMapTask(BigMap): self.stuck_keys = [['space', 0.02], ['a',2], ['d',2], ['t', 0.02]] self.stuck_index = 0 self.last_distance = 0 + self._has_health_bar = False @property def star_move_distance_threshold(self): @@ -215,6 +216,8 @@ class FarmMapTask(BigMap): def on_combat_check(self): self.incr_drop(self.pick_f()) self.find_my_location() + if not self._has_health_bar: + self._has_health_bar = self.has_health_bar() return True def go_to_star(self): @@ -225,6 +228,7 @@ class FarmMapTask(BigMap): while True: self.sleep(0.01) self.middle_click(interval=1, after_sleep=0.2) + self._has_health_bar = False if self.in_combat(): self.sleep(2) if current_direction is not None: @@ -234,14 +238,13 @@ class FarmMapTask(BigMap): start = time.time() self.combat_once() duration = time.time() - start - if duration > 8: - self.my_box = self.my_box.scale(1.1) - while True: - dropped, has_more = self.yolo_find_echo(use_color=False, walk=False) - self.incr_drop(dropped) - self.sleep(0.5) - if not dropped or not has_more: - break + + while True: + dropped, has_more = self.yolo_find_echo(use_color=False, turn=duration > 15 or self._has_health_bar) + self.incr_drop(dropped) + self.sleep(0.5) + if not dropped or not has_more: + break star, distance, angle = self.find_direction_angle() # self.draw_boxes('next_star', star, color='green') if not star: diff --git a/src/tests/images/echo.png b/src/tests/images/echo.png new file mode 100644 index 0000000..82314ad Binary files /dev/null and b/src/tests/images/echo.png differ diff --git a/tests/TestCon.py b/tests/TestCon.py new file mode 100644 index 0000000..d3c51f9 --- /dev/null +++ b/tests/TestCon.py @@ -0,0 +1,29 @@ +import unittest +from config import config +from ok.test.TaskTestCase import TaskTestCase +from src.task.AutoCombatTask import AutoCombatTask + +config['debug'] = True + + +class TestCombatCheck(TaskTestCase): + task_class = AutoCombatTask + config = config + + def test_con_full(self): + self.task.do_reset_to_false() + self.set_image('tests/images/con_full.png') + # in_combat = self.task.in_combat() + # self.assertTrue(in_combat) + # + # self.task.do_reset_to_false() + # self.set_image('tests/images/con_full.png') + # in_combat = self.task.in_combat() + # self.assertTrue(in_combat) + self.task.load_chars() + con_full = self.task.get_current_char().is_con_full() + self.assertTrue(con_full) + + +if __name__ == '__main__': + unittest.main() diff --git a/tests/TestEcho.py b/tests/TestEcho.py new file mode 100644 index 0000000..d54588f --- /dev/null +++ b/tests/TestEcho.py @@ -0,0 +1,30 @@ +import time +import unittest +from config import config +from ok.test.TaskTestCase import TaskTestCase +from src.task.AutoCombatTask import AutoCombatTask +from src.task.DailyTask import DailyTask + +config['debug'] = True + + +class TestEcho(TaskTestCase): + task_class = DailyTask + config = config + + def test_find_echo(self): + self.set_image('tests/images/echo.png') + echos = self.task.find_echo() + self.assertEqual(1, len(echos)) + time.sleep(1) + self.task.screenshot('echo1', show_box=True) + self.set_image('tests/images/echo2.png') + echos = self.task.find_echo() + time.sleep(1) + self.task.screenshot('echo2', show_box=True) + self.assertEqual(1, len(echos)) + time.sleep(1) + + +if __name__ == '__main__': + unittest.main() diff --git a/tests/images/con_full.png b/tests/images/con_full.png new file mode 100644 index 0000000..07e3578 Binary files /dev/null and b/tests/images/con_full.png differ