def detect(self,
image: str,
thresh: float = .5,
hier_thresh: float = .5,
nms: float = .45) -> list:
if isinstance(image, str):
im = dn.load_image(image.encode(), 0, 0)
elif image is None:
return []
else:
arr = image.transpose(2, 0, 1)
c, h, w = arr.shape
arr = (arr/255.0).flatten()
data = dn.c_array(dn.c_float, arr)
im = dn.IMAGE(w, h, c, data)
num = dn.c_int(0)
pnum = dn.pointer(num)
dn.predict_image(self.net, im)
dets = dn.get_network_boxes(
self.net, im.w, im.h, thresh, hier_thresh, None, 0, pnum)
num = pnum[0]
if (nms):
dn.do_nms_obj(dets, num, self.meta.classes, nms)
res = []
for j in range(num):
if dets[j].prob[PERSON_ID] > 0:
bb = dets[j].bbox
res.append((dets[j].prob[PERSON_ID], BBOX(bb)))
res = sorted(res, key=lambda x: -x[0]) # 0 is prob
# dn.free_image(im) # raise double free error
dn.free_detections(dets, num)
return res
def array_to_image(arr):
arr = arr.transpose(2, 0, 1)
c = arr.shape[0]
h = arr.shape[1]
w = arr.shape[2]
arr = (arr / 255.0).flatten()
data = dn.c_array(dn.c_float, arr)
im = dn.IMAGE(w, h, c, data)
return im
def array_to_image(array):
array = array.transpose(2, 0, 1)
c = array.shape[0]
h = array.shape[1]
w = array.shape[2]
array = (array / 255.0).flatten()
data = darknet.c_array(darknet.c_float, array)
image = darknet.IMAGE(w, h, c, data)
return image
def genTestData(name, inpShape, outShape):
net = dn.load_net(name + '.cfg', '', 0)
inp = np.random.standard_normal(inpShape).astype(np.float32)
inpData = dn.c_array(dn.c_float, inp.flatten())
pred = dn.predict(net, inpData)
total = np.prod(outShape)
out = np.zeros([total], np.float32)
for i in range(total):
out[i] = pred[i]
out = out.reshape(outShape)
np.save(name + '_in.npy', inp)
np.save(name + '_out.npy', out)
def genTestData(name, inpShape, outShape):
net = dn.load_net(name + '.cfg', '', 0)
inp = np.random.standard_normal(inpShape).astype(np.float32)
inpData = dn.c_array(dn.c_float, inp.flatten())
pred = dn.predict(net, inpData)
total = np.prod(outShape)
out = np.zeros([total], np.float32)
for i in range(total):
out[i] = pred[i]
out = out.reshape(outShape)
np.save(name + '_in.npy', inp)
np.save(name + '_out.npy', out)
def array_to_image(arr):
time1 = time.time()
arr = arr.transpose(2, 0, 1)
time2 = time.time()
print("transpose took: ", time2 - time1)
c = arr.shape[0]
h = arr.shape[1]
w = arr.shape[2]
arr = (arr / 255.0).flatten()
time3 = time.time()
print("flattern took: ", time3 - time2)
data = dn.c_array(dn.c_float, arr)
time4 = time.time()
print("change to c_array took: ", time4 - time3)
im = dn.IMAGE(w, h, c, data)
time5 = time.time()
print("final loading IMAGE from array took: ", time5 - time4)
return im
