Merge pull request #25 from lian/master

DarknetImage move float conversion into c code

Makefile

@@ -2,7 +2,8 @@
 .PHONY: prepare_cuda prepare_cudnn download_darknet build_darknet build_darknet_gpu clean clean_cuda clean_cudnn sudo_install
 
 # Latest battletested AlexeyAB version of Darknet commit
-LATEST_COMMIT?=f056fc3b6a11528fa0522a468eca1e909b7004b7
+# LATEST_COMMIT?=f056fc3b6a11528fa0522a468eca1e909b7004b7
+LATEST_COMMIT?=9d40b619756be9521bc2ccd81808f502daaa3e9a
 
 # Temporary folder for building Darknet
 TMP_DIR?=/tmp/

README.md

@@ -35,7 +35,7 @@ Example of such project here: https://github.com/LdDl/license_plate_recognition#
 
 ## Requirements
 
-You need to install fork of [darknet](https://github.com/AlexeyAB/darknet). Latest commit I've tested is [here](https://github.com/AlexeyAB/darknet/commit/f056fc3b6a11528fa0522a468eca1e909b7004b7)
+You need to install fork of [darknet](https://github.com/AlexeyAB/darknet). Latest commit I've tested is [here](https://github.com/AlexeyAB/darknet/commit/9d40b619756be9521bc2ccd81808f502daaa3e9a). It corresponds last official [YOLOv4 release](https://github.com/AlexeyAB/darknet/releases/tag/yolov4)
 
 Use provided [Makefile](Makefile).
 
@@ -114,15 +114,15 @@ Building and running program:
 
     Output should be something like this:
     ```shell
-    traffic light (9): 73.5039% | start point: (238,73) | end point: (251, 106)
+    traffic light (9): 73.5040% | start point: (238,73) | end point: (251, 106)
     truck (7): 96.6401% | start point: (95,79) | end point: (233, 287)
     truck (7): 96.4774% | start point: (662,158) | end point: (800, 321)
     truck (7): 96.1841% | start point: (0,77) | end point: (86, 333)
-    truck (7): 46.8695% | start point: (434,173) | end point: (559, 216)
+    truck (7): 46.8694% | start point: (434,173) | end point: (559, 216)
     car (2): 99.7370% | start point: (512,188) | end point: (741, 329)
-    car (2): 99.2533% | start point: (260,191) | end point: (422, 322)
+    car (2): 99.2532% | start point: (260,191) | end point: (422, 322)
     car (2): 99.0333% | start point: (425,201) | end point: (547, 309)
-    car (2): 83.3919% | start point: (386,210) | end point: (437, 287)
+    car (2): 83.3920% | start point: (386,210) | end point: (437, 287)
     car (2): 75.8621% | start point: (73,199) | end point: (102, 274)
     car (2): 39.1925% | start point: (386,206) | end point: (442, 240)
     bicycle (1): 76.3121% | start point: (189,298) | end point: (253, 402)
@@ -136,19 +136,19 @@ Building and running program:
 
     Output should be something like this:
     ```shell
-    truck (7): 49.5197% | start point: (0,136) | end point: (85, 311)
-    car (2): 36.3747% | start point: (95,152) | end point: (186, 283)
-    truck (7): 48.4384% | start point: (95,152) | end point: (186, 283)
-    truck (7): 45.6590% | start point: (694,178) | end point: (798, 310)
-    car (2): 76.8379% | start point: (1,145) | end point: (84, 324)
-    truck (7): 25.5731% | start point: (107,89) | end point: (215, 263)
-    car (2): 99.8783% | start point: (511,185) | end point: (748, 328)
-    car (2): 99.8194% | start point: (261,189) | end point: (427, 322)
-    car (2): 99.6408% | start point: (426,197) | end point: (539, 311)
-    car (2): 74.5610% | start point: (692,186) | end point: (796, 316)
-    car (2): 72.8053% | start point: (388,206) | end point: (437, 276)
-    bicycle (1): 72.2932% | start point: (178,270) | end point: (268, 406)
-    person (0): 97.3026% | start point: (143,135) | end point: (268, 343)
+    truck (7): 49.5123% | start point: (0,136) | end point: (85, 311)
+    car (2): 36.3694% | start point: (95,152) | end point: (186, 283)
+    truck (7): 48.4177% | start point: (95,152) | end point: (186, 283)
+    truck (7): 45.6520% | start point: (694,178) | end point: (798, 310)
+    car (2): 76.8402% | start point: (1,145) | end point: (84, 324)
+    truck (7): 25.5920% | start point: (107,89) | end point: (215, 263)
+    car (2): 99.8782% | start point: (511,185) | end point: (748, 328)
+    car (2): 99.8193% | start point: (261,189) | end point: (427, 322)
+    car (2): 99.6405% | start point: (426,197) | end point: (539, 311)
+    car (2): 74.5627% | start point: (692,186) | end point: (796, 316)
+    car (2): 72.7975% | start point: (388,206) | end point: (437, 276)
+    bicycle (1): 72.2760% | start point: (178,270) | end point: (268, 406)
+    person (0): 97.3007% | start point: (143,135) | end point: (268, 343)
     ```
 
 ## Documentation

image.c

@@ -11,3 +11,18 @@ void set_data_f32_val(float* data, int index, float value) {
     data[index] = value;
 }
 
+void to_float_and_fill_image(image* im, int w, int h, uint8_t* data) {
+    int x, y, idx_source;
+    int pixel_count = w * h;
+    int idx = 0;
+
+    for (y = 0; y < h; y++) {
+        for (x = 0; x < w; x++) {
+            idx_source = (y*w + x) * 4;
+            im->data[(pixel_count*0) + idx] = (float)data[idx_source] / 255;
+            im->data[(pixel_count*1) + idx] = (float)data[idx_source+1] / 255;
+            im->data[(pixel_count*2) + idx] = (float)data[idx_source+2] / 255;
+            idx++;
+        }
+    }
+}

image.go

@@ -14,61 +14,33 @@ import (
 type DarknetImage struct {
 	Width  int
 	Height int
-	ans    []float32
 	image  C.image
 }
 
 // Close and release resources.
 func (img *DarknetImage) Close() error {
 	C.free_image(img.image)
-	img.ans = nil
 	return nil
 }
 
-// https://stackoverflow.com/questions/33186783/get-a-pixel-array-from-from-golang-image-image/59747737#59747737
-func imgTofloat32(src image.Image) []float32 {
+func Image2Float32(src image.Image) (*DarknetImage, error) {
 	bounds := src.Bounds()
-	width, height := bounds.Max.X, bounds.Max.Y
-	srcRGBA := image.NewRGBA(src.Bounds())
-	draw.Copy(srcRGBA, image.Point{}, src, src.Bounds(), draw.Src, nil)
+	srcRGBA := image.NewRGBA(bounds)
+	draw.Copy(srcRGBA, image.Point{}, src, bounds, draw.Src, nil)
 
-	red := make([]float32, 0, width*height)
-	green := make([]float32, 0, width*height)
-	blue := make([]float32, 0, width*height)
-	for y := 0; y < height; y++ {
-		for x := 0; x < width; x++ {
-			idxSource := (y*width + x) * 4
-			pix := srcRGBA.Pix[idxSource : idxSource+4]
-			rpix, gpix, bpix := float32(pix[0])/257.0, float32(pix[1])/257.0, float32(pix[2])/257.0
-			red = append(red, rpix)
-			green = append(green, gpix)
-			blue = append(blue, bpix)
-		}
-	}
-	srcRGBA = nil
-
-	ans := make([]float32, len(red)+len(green)+len(blue))
-	copy(ans[:len(red)], red)
-	copy(ans[len(red):len(red)+len(green)], green)
-	copy(ans[len(red)+len(green):], blue)
-	red = nil
-	green = nil
-	blue = nil
-	return ans
+	return ImageRGBA2Float32(srcRGBA)
 }
 
 // Image2Float32 Returns []float32 representation of image.Image
-func Image2Float32(img image.Image) (*DarknetImage, error) {
-	// ans := imgTofloat32(img)
+func ImageRGBA2Float32(img *image.RGBA) (*DarknetImage, error) {
 	width := img.Bounds().Dx()
 	height := img.Bounds().Dy()
 	imgDarknet := &DarknetImage{
 		Width:  width,
 		Height: height,
-		ans:    imgTofloat32(img),
 		image:  C.make_image(C.int(width), C.int(height), 3),
 	}
-	C.fill_image_f32(&imgDarknet.image, C.int(width), C.int(height), 3, (*C.float)(unsafe.Pointer(&imgDarknet.ans[0])))
+	C.to_float_and_fill_image(&imgDarknet.image, C.int(width), C.int(height), (*C.uint8_t)(unsafe.Pointer(&img.Pix[0])))
 	return imgDarknet, nil
 }
 

image.h

@@ -3,4 +3,5 @@
 #include <darknet.h>
 
 extern void fill_image_f32(image *im, int w, int h, int c, float* data);
-extern void set_data_f32_val(float* data, int index, float value);
+extern void set_data_f32_val(float* data, int index, float value);
+extern void to_float_and_fill_image(image *im, int w, int h, uint8_t* data);