From a055821b732f748524680d08ffbcef5cbef25713 Mon Sep 17 00:00:00 2001
From: Edmond Yoo <hj3yoo@uwaterloo.ca>
Date: Mon, 17 Sep 2018 06:43:16 +0000
Subject: [PATCH] Fine-tuning opencv
---
darknet.py | 406 ++++++++++++++++++++++++++++++++++++++++++++++++++++++---
1 files changed, 381 insertions(+), 25 deletions(-)
diff --git a/darknet.py b/darknet.py
index 7d7dc69..f00356d 100644
--- a/darknet.py
+++ b/darknet.py
@@ -1,6 +1,38 @@
+#!python3
+"""
+Python 3 wrapper for identifying objects in images
+
+Requires DLL compilation
+
+Both the GPU and no-GPU version should be compiled; the no-GPU version should be renamed "yolo_cpp_dll_nogpu.dll".
+
+On a GPU system, you can force CPU evaluation by any of:
+
+- Set global variable DARKNET_FORCE_CPU to True
+- Set environment variable CUDA_VISIBLE_DEVICES to -1
+- Set environment variable "FORCE_CPU" to "true"
+
+
+To use, either run performDetect() after import, or modify the end of this file.
+
+See the docstring of performDetect() for parameters.
+
+Directly viewing or returning bounding-boxed images requires scikit-image to be installed (`pip install scikit-image`)
+
+
+Original *nix 2.7: https://github.com/pjreddie/darknet/blob/0f110834f4e18b30d5f101bf8f1724c34b7b83db/python/darknet.py
+Windows Python 2.7 version: https://github.com/AlexeyAB/darknet/blob/fc496d52bf22a0bb257300d3c79be9cd80e722cb/build/darknet/x64/darknet.py
+
+@author: Philip Kahn
+@date: 20180503
+"""
+#pylint: disable=R, W0401, W0614, W0703
from ctypes import *
import math
import random
+import os
+import cv2
+import numpy as np
def sample(probs):
s = sum(probs)
@@ -42,11 +74,54 @@
_fields_ = [("classes", c_int),
("names", POINTER(c_char_p))]
-
+
#lib = CDLL("/home/pjreddie/documents/darknet/libdarknet.so", RTLD_GLOBAL)
-lib = CDLL("darknet.so", RTLD_GLOBAL)
-#lib = CDLL("yolo_cpp_dll.dll", RTLD_GLOBAL)
+#lib = CDLL("darknet.so", RTLD_GLOBAL)
+hasGPU = True
+if os.name == "nt":
+ cwd = os.path.dirname(__file__)
+ os.environ['PATH'] = cwd + ';' + os.environ['PATH']
+ winGPUdll = os.path.join(cwd, "yolo_cpp_dll.dll")
+ winNoGPUdll = os.path.join(cwd, "yolo_cpp_dll_nogpu.dll")
+ envKeys = list()
+ for k, v in os.environ.items():
+ envKeys.append(k)
+ try:
+ try:
+ tmp = os.environ["FORCE_CPU"].lower()
+ if tmp in ["1", "true", "yes", "on"]:
+ raise ValueError("ForceCPU")
+ else:
+ print("Flag value '"+tmp+"' not forcing CPU mode")
+ except KeyError:
+ # We never set the flag
+ if 'CUDA_VISIBLE_DEVICES' in envKeys:
+ if int(os.environ['CUDA_VISIBLE_DEVICES']) < 0:
+ raise ValueError("ForceCPU")
+ try:
+ global DARKNET_FORCE_CPU
+ if DARKNET_FORCE_CPU:
+ raise ValueError("ForceCPU")
+ except NameError:
+ pass
+ # print(os.environ.keys())
+ # print("FORCE_CPU flag undefined, proceeding with GPU")
+ if not os.path.exists(winGPUdll):
+ raise ValueError("NoDLL")
+ lib = CDLL(winGPUdll, RTLD_GLOBAL)
+ except (KeyError, ValueError):
+ hasGPU = False
+ if os.path.exists(winNoGPUdll):
+ lib = CDLL(winNoGPUdll, RTLD_GLOBAL)
+ print("Notice: CPU-only mode")
+ else:
+ # Try the other way, in case no_gpu was
+ # compile but not renamed
+ lib = CDLL(winGPUdll, RTLD_GLOBAL)
+ print("Environment variables indicated a CPU run, but we didn't find `"+winNoGPUdll+"`. Trying a GPU run anyway.")
+else:
+ lib = CDLL("./darknet.so", RTLD_GLOBAL)
lib.network_width.argtypes = [c_void_p]
lib.network_width.restype = c_int
lib.network_height.argtypes = [c_void_p]
@@ -56,8 +131,9 @@
predict.argtypes = [c_void_p, POINTER(c_float)]
predict.restype = POINTER(c_float)
-set_gpu = lib.cuda_set_device
-set_gpu.argtypes = [c_int]
+if hasGPU:
+ set_gpu = lib.cuda_set_device
+ set_gpu.argtypes = [c_int]
make_image = lib.make_image
make_image.argtypes = [c_int, c_int, c_int]
@@ -87,6 +163,10 @@
load_net.argtypes = [c_char_p, c_char_p, c_int]
load_net.restype = c_void_p
+load_net_custom = lib.load_network_custom
+load_net_custom.argtypes = [c_char_p, c_char_p, c_int, c_int]
+load_net_custom.restype = c_void_p
+
do_nms_obj = lib.do_nms_obj
do_nms_obj.argtypes = [POINTER(DETECTION), c_int, c_int, c_float]
@@ -115,44 +195,320 @@
predict_image.argtypes = [c_void_p, IMAGE]
predict_image.restype = POINTER(c_float)
+def array_to_image(arr):
+ import numpy as np
+ # need to return old values to avoid python freeing memory
+ arr = arr.transpose(2,0,1)
+ c = arr.shape[0]
+ h = arr.shape[1]
+ w = arr.shape[2]
+ arr = np.ascontiguousarray(arr.flat, dtype=np.float32) / 255.0
+ data = arr.ctypes.data_as(POINTER(c_float))
+ im = IMAGE(w,h,c,data)
+ return im, arr
+
def classify(net, meta, im):
out = predict_image(net, im)
res = []
for i in range(meta.classes):
- res.append((meta.names[i], out[i]))
+ if altNames is None:
+ nameTag = meta.names[i]
+ else:
+ nameTag = altNames[i]
+ res.append((nameTag, out[i]))
res = sorted(res, key=lambda x: -x[1])
return res
-def detect(net, meta, image, thresh=.5, hier_thresh=.5, nms=.45):
- im = load_image(image, 0, 0)
+def detect(net, meta, image, thresh=.5, hier_thresh=.5, nms=.45, debug= False):
+ """
+ Performs the meat of the detection
+ """
+ #pylint: disable= C0321
+ if isinstance(image, np.ndarray):
+ im = array_to_image(image)[0]
+ else:
+ im = load_image(image, 0, 0)
+ #import cv2
+ #custom_image_bgr = cv2.imread(image) # use: detect(,,imagePath,)
+ #custom_image = cv2.cvtColor(custom_image_bgr, cv2.COLOR_BGR2RGB)
+ #custom_image = cv2.resize(custom_image,(lib.network_width(net), lib.network_height(net)), interpolation = cv2.INTER_LINEAR)
+ #import scipy.misc
+ #custom_image = scipy.misc.imread(image)
+ #im, arr = array_to_image(custom_image) # you should comment line below: free_image(im)
+ if debug: print("Loaded image")
num = c_int(0)
+ if debug: print("Assigned num")
pnum = pointer(num)
+ if debug: print("Assigned pnum")
predict_image(net, im)
- dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, None, 0, pnum, 1)
+ if debug: print("did prediction")
+ #dets = get_network_boxes(net, custom_image_bgr.shape[1], custom_image_bgr.shape[0], thresh, hier_thresh, None, 0, pnum, 0) # OpenCV
+ dets = get_network_boxes(net, im.w, im.h, thresh, hier_thresh, None, 0, pnum, 0)
+ if debug: print("Got dets")
num = pnum[0]
- #if (nms): do_nms_obj(dets, num, meta.classes, nms);
- if (nms): do_nms_sort(dets, num, meta.classes, nms);
-
+ if debug: print("got zeroth index of pnum")
+ if nms:
+ do_nms_sort(dets, num, meta.classes, nms)
+ if debug: print("did sort")
res = []
+ if debug: print("about to range")
for j in range(num):
+ if debug: print("Ranging on "+str(j)+" of "+str(num))
+ if debug: print("Classes: "+str(meta), meta.classes, meta.names)
for i in range(meta.classes):
+ if debug: print("Class-ranging on "+str(i)+" of "+str(meta.classes)+"= "+str(dets[j].prob[i]))
if dets[j].prob[i] > 0:
b = dets[j].bbox
- res.append((meta.names[i], dets[j].prob[i], (b.x, b.y, b.w, b.h)))
+ if altNames is None:
+ nameTag = meta.names[i]
+ else:
+ nameTag = altNames[i]
+ if debug:
+ print("Got bbox", b)
+ print(nameTag)
+ print(dets[j].prob[i])
+ print((b.x, b.y, b.w, b.h))
+ res.append((nameTag, dets[j].prob[i], (b.x, b.y, b.w, b.h)))
+ if debug: print("did range")
res = sorted(res, key=lambda x: -x[1])
+ if debug: print("did sort")
free_image(im)
+ if debug: print("freed image")
free_detections(dets, num)
+ if debug: print("freed detections")
return res
-
-if __name__ == "__main__":
- #net = load_net("cfg/densenet201.cfg", "/home/pjreddie/trained/densenet201.weights", 0)
- #im = load_image("data/wolf.jpg", 0, 0)
- #meta = load_meta("cfg/imagenet1k.data")
- #r = classify(net, meta, im)
- #print r[:10]
- net = load_net("cfg/yolov3.cfg", "yolov3.weights", 0)
- meta = load_meta("data/coco.data")
- r = detect(net, meta, "data/dog.jpg", 0.25)
- print r
-
+
+netMain = None
+metaMain = None
+altNames = None
+
+def performDetect(imagePath="data/dog.jpg", thresh= 0.25, configPath = "./cfg/yolov3.cfg", weightPath = "yolov3.weights", metaPath= "./data/coco.data", showImage= True, makeImageOnly = False, initOnly= False):
+ """
+ Convenience function to handle the detection and returns of objects.
+
+ Displaying bounding boxes requires libraries scikit-image and numpy
+
+ Parameters
+ ----------------
+ imagePath: str
+ Path to the image to evaluate. Raises ValueError if not found
+
+ thresh: float (default= 0.25)
+ The detection threshold
+
+ configPath: str
+ Path to the configuration file. Raises ValueError if not found
+
+ weightPath: str
+ Path to the weights file. Raises ValueError if not found
+
+ metaPath: str
+ Path to the data file. Raises ValueError if not found
+
+ showImage: bool (default= True)
+ Compute (and show) bounding boxes. Changes return.
+
+ makeImageOnly: bool (default= False)
+ If showImage is True, this won't actually *show* the image, but will create the array and return it.
+
+ initOnly: bool (default= False)
+ Only initialize globals. Don't actually run a prediction.
+
+ Returns
+ ----------------------
+
+
+ When showImage is False, list of tuples like
+ ('obj_label', confidence, (bounding_box_x_px, bounding_box_y_px, bounding_box_width_px, bounding_box_height_px))
+ The X and Y coordinates are from the center of the bounding box. Subtract half the width or height to get the lower corner.
+
+ Otherwise, a dict with
+ {
+ "detections": as above
+ "image": a numpy array representing an image, compatible with scikit-image
+ "caption": an image caption
+ }
+ """
+ # Import the global variables. This lets us instance Darknet once, then just call performDetect() again without instancing again
+ global metaMain, netMain, altNames #pylint: disable=W0603
+ assert 0 < thresh < 1, "Threshold should be a float between zero and one (non-inclusive)"
+ if not os.path.exists(configPath):
+ raise ValueError("Invalid config path `"+os.path.abspath(configPath)+"`")
+ if not os.path.exists(weightPath):
+ raise ValueError("Invalid weight path `"+os.path.abspath(weightPath)+"`")
+ if not os.path.exists(metaPath):
+ raise ValueError("Invalid data file path `"+os.path.abspath(metaPath)+"`")
+ if netMain is None:
+ netMain = load_net_custom(configPath.encode("ascii"), weightPath.encode("ascii"), 0, 1) # batch size = 1
+ if metaMain is None:
+ metaMain = load_meta(metaPath.encode("ascii"))
+ if altNames is None:
+ # In Python 3, the metafile default access craps out on Windows (but not Linux)
+ # Read the names file and create a list to feed to detect
+ try:
+ with open(metaPath) as metaFH:
+ metaContents = metaFH.read()
+ import re
+ match = re.search("names *= *(.*)$", metaContents, re.IGNORECASE | re.MULTILINE)
+ if match:
+ result = match.group(1)
+ else:
+ result = None
+ try:
+ if os.path.exists(result):
+ with open(result) as namesFH:
+ namesList = namesFH.read().strip().split("\n")
+ altNames = [x.strip() for x in namesList]
+ except TypeError:
+ pass
+ except Exception:
+ pass
+ if initOnly:
+ print("Initialized detector")
+ return None
+ if not os.path.exists(imagePath):
+ raise ValueError("Invalid image path `"+os.path.abspath(imagePath)+"`")
+ # Do the detection
+ #detections = detect(netMain, metaMain, imagePath, thresh) # if is used cv2.imread(image)
+ #detections = detect(netMain, metaMain, imagePath.encode("ascii"), thresh)
+ detections = detect(netMain, metaMain, cv2.imread(imagePath), thresh, debug=True)
+ if showImage:
+ try:
+ from skimage import io, draw
+ import numpy as np
+ image = io.imread(imagePath)
+ print("*** "+str(len(detections))+" Results, color coded by confidence ***")
+ imcaption = []
+ for detection in detections:
+ label = detection[0]
+ confidence = detection[1]
+ pstring = label+": "+str(np.rint(100 * confidence))+"%"
+ imcaption.append(pstring)
+ print(pstring)
+ bounds = detection[2]
+ shape = image.shape
+ # x = shape[1]
+ # xExtent = int(x * bounds[2] / 100)
+ # y = shape[0]
+ # yExtent = int(y * bounds[3] / 100)
+ yExtent = int(bounds[3])
+ xEntent = int(bounds[2])
+ # Coordinates are around the center
+ xCoord = int(bounds[0] - bounds[2]/2)
+ yCoord = int(bounds[1] - bounds[3]/2)
+ boundingBox = [
+ [xCoord, yCoord],
+ [xCoord, yCoord + yExtent],
+ [xCoord + xEntent, yCoord + yExtent],
+ [xCoord + xEntent, yCoord]
+ ]
+ # Wiggle it around to make a 3px border
+ rr, cc = draw.polygon_perimeter([x[1] for x in boundingBox], [x[0] for x in boundingBox], shape= shape)
+ rr2, cc2 = draw.polygon_perimeter([x[1] + 1 for x in boundingBox], [x[0] for x in boundingBox], shape= shape)
+ rr3, cc3 = draw.polygon_perimeter([x[1] - 1 for x in boundingBox], [x[0] for x in boundingBox], shape= shape)
+ rr4, cc4 = draw.polygon_perimeter([x[1] for x in boundingBox], [x[0] + 1 for x in boundingBox], shape= shape)
+ rr5, cc5 = draw.polygon_perimeter([x[1] for x in boundingBox], [x[0] - 1 for x in boundingBox], shape= shape)
+ boxColor = (int(255 * (1 - (confidence ** 2))), int(255 * (confidence ** 2)), 0)
+ draw.set_color(image, (rr, cc), boxColor, alpha= 0.8)
+ draw.set_color(image, (rr2, cc2), boxColor, alpha= 0.8)
+ draw.set_color(image, (rr3, cc3), boxColor, alpha= 0.8)
+ draw.set_color(image, (rr4, cc4), boxColor, alpha= 0.8)
+ draw.set_color(image, (rr5, cc5), boxColor, alpha= 0.8)
+ if not makeImageOnly:
+ io.imshow(image)
+ io.show()
+ detections = {
+ "detections": detections,
+ "image": image,
+ "caption": "\n<br/>".join(imcaption)
+ }
+ except Exception as e:
+ print("Unable to show image: "+str(e))
+ return detections
+
+
+def capture(thresh=.25, hier_thresh=.5, nms=.45, configPath="./cfg/yolov3.cfg", weightPath="yolov3.weights",
+ metaPath="./data/coco.data", showImage=True, makeImageOnly=False, initOnly=False):
+ global metaMain, netMain, altNames # pylint: disable=W0603
+ netMain = load_net_custom(configPath.encode("ascii"), weightPath.encode("ascii"), 0, 1) # batch size = 1
+ metaMain = load_meta(metaPath.encode("ascii"))
+
+ num = c_int(0)
+ pnum = pointer(num)
+ num = pnum[0]
+
+ capture = cv2.VideoCapture('../data/test1.mp4')
+ print(capture.get(cv2.CAP_PROP_FPS))
+
+ capture.set(cv2.CAP_PROP_FRAME_WIDTH, 1024)
+ capture.set(cv2.CAP_PROP_FRAME_HEIGHT, 768)
+
+ while True:
+ ret, frame = capture.read()
+ detections = detect(netMain, metaMain, frame, thresh, debug=True)
+ '''
+ im, arr = array_to_image(frame)
+ predict_image(netMain, im)
+ dets = get_network_boxes(netMain, im.w, im.h, thresh, hier_thresh, None, 0, pnum, 1)
+ if nms:
+ do_nms_sort(dets, num, metaMain.classes, nms)
+ res = []
+ for j in range(num):
+ for i in range(metaMain.classes):
+ if dets[j].prob[i] > 0:
+ b = dets[j].bbox
+ nameTag = metaMain.names[i]
+ res.append((nameTag, dets[j].prob[i], (b.x, b.y, b.w, b.h)))
+ '''
+ for detection in detections:
+ label = detection[0]
+ confidence = detection[1]
+ pstring = label + ": " + str(np.rint(100 * confidence)) + "%"
+ imcaption.append(pstring)
+ print(pstring)
+ bounds = detection[2]
+ shape = image.shape
+ # x = shape[1]
+ # xExtent = int(x * bounds[2] / 100)
+ # y = shape[0]
+ # yExtent = int(y * bounds[3] / 100)
+ yExtent = int(bounds[3])
+ xEntent = int(bounds[2])
+ # Coordinates are around the center
+ xCoord = int(bounds[0] - bounds[2] / 2)
+ yCoord = int(bounds[1] - bounds[3] / 2)
+ boundingBox = [
+ [xCoord, yCoord],
+ [xCoord, yCoord + yExtent],
+ [xCoord + xEntent, yCoord + yExtent],
+ [xCoord + xEntent, yCoord]
+ ]
+ # Wiggle it around to make a 3px border
+ rr, cc = draw.polygon_perimeter([x[1] for x in boundingBox], [x[0] for x in boundingBox], shape=shape)
+ rr2, cc2 = draw.polygon_perimeter([x[1] + 1 for x in boundingBox], [x[0] for x in boundingBox], shape=shape)
+ rr3, cc3 = draw.polygon_perimeter([x[1] - 1 for x in boundingBox], [x[0] for x in boundingBox], shape=shape)
+ rr4, cc4 = draw.polygon_perimeter([x[1] for x in boundingBox], [x[0] + 1 for x in boundingBox], shape=shape)
+ rr5, cc5 = draw.polygon_perimeter([x[1] for x in boundingBox], [x[0] - 1 for x in boundingBox], shape=shape)
+ boxColor = (int(255 * (1 - (confidence ** 2))), int(255 * (confidence ** 2)), 0)
+ draw.set_color(image, (rr, cc), boxColor, alpha=0.8)
+ draw.set_color(image, (rr2, cc2), boxColor, alpha=0.8)
+ draw.set_color(image, (rr3, cc3), boxColor, alpha=0.8)
+ draw.set_color(image, (rr4, cc4), boxColor, alpha=0.8)
+ draw.set_color(image, (rr5, cc5), boxColor, alpha=0.8)
+ print(res)
+ cv2.imshow('frame', frame)
+ if cv2.waitKey(1) & 0xFF == ord('q'):
+ break
+
+ capture.release()
+ cv2.destroyAllWindows()
+
+
+if __name__ == "__main__":
+ performDetect(imagePath='data/scream.jpg')
+ #performDetect(imagePath="../data/test1.jpg", thresh=0.25, configPath="./cfg/tiny_yolo.cfg",
+ # weightPath="./weights/second_general/tiny_yolo_17000.weights",
+ # metaPath="./data/obj.data", showImage=True, makeImageOnly=False, initOnly=False)
+ #print(performDetect(showImage=False))
+ #capture()
--
Gitblit v1.10.0