def run(self, imgList, fpgaOutput_list, fpgaOutputShape_list, shapeArr):
if self.numProcessed == 0:
self.zmqPub = None
if self.args['zmqpub']:
self.zmqPub = mp_classify.ZmqResultPublisher(self.args['deviceID'])
self.goldenMap = None
self.numProcessed += len(imgList)
bboxlist_for_images = self.yolo_postproc(fpgaOutput_list, args, shapeArr, biases=self.biases)
if(not self.args['profile']):
for i in range(min(self.args['batch_sz'], len(shapeArr))):
print("Detected {} boxes in {}".format(len(bboxlist_for_images[i]), imgList[i]))
if(self.args['results_dir']):
boxes = bboxlist_for_images
for i in range(min(self.args['batch_sz'], len(shapeArr))):
filename = os.path.splitext(os.path.basename(imgList[i]))[0]
out_file_txt = os.path.join(self.args['results_dir'], filename + '.txt')
print("Saving {} boxes to {}".format(len(boxes[i]), out_file_txt)); sys.stdout.flush()
saveDetectionDarknetStyle(out_file_txt, boxes[i], shapeArr[i])
if(self.args['visualize']):
out_file_png = os.path.join(self.args['results_dir'], filename + '.png')
print("Saving result to {}".format(out_file_png)); sys.stdout.flush()
draw_boxes(imgList[i], boxes[i], self.labels, self.colors, out_file_png)
def run(self, imgList, fpgaOutput_list, fpgaOutputShape_list, shapeArr):
if self.numProcessed == 0:
self.startTime = timeit.default_timer()
self.labels = xdnn_io.get_labels(self.args['labels'])
self.zmqPub = None
if self.args['zmqpub']:
self.zmqPub = mp_classify.ZmqResultPublisher(
self.args['deviceID'])
self.goldenMap = None
self.numProcessed += len(imgList)
firstInputShape = xdnn.CompilerJsonParser(
self.args['netcfg']).getInputs().itervalues().next()
if ((args['yolo_model'] == 'standard_yolo_v3')
or (args['yolo_model'] == 'tiny_yolo_v3')):
num_ouptut_layers = len(fpgaOutput_list)
fpgaOutput = []
for idx in range(num_ouptut_layers):
fpgaOutput.append(
np.frombuffer(fpgaOutput_list[idx],
dtype=np.float32).reshape(
tuple(fpgaOutputShape_list[idx])))
bboxlist_for_images = det_postprocess(fpgaOutput, args, shapeArr)
for i in range(min(self.args['batch_sz'], len(shapeArr))):
print "image: ", imgList[
i], " has num boxes detected : ", len(
bboxlist_for_images[i])
else:
fpgaOutput = fpgaOutput_list[0]
fpgaOutputShape = fpgaOutputShape_list[0]
npout_view = np.frombuffer(fpgaOutput, dtype=np.float32)\
.reshape(tuple(fpgaOutputShape))
npout_view = npout_view.flatten()
fpgaoutsz = fpgaOutputShape[1] * fpgaOutputShape[
2] * fpgaOutputShape[3]
bboxlist_for_images = []
for i in range(min(self.args['batch_sz'], len(shapeArr))):
startidx = i * fpgaoutsz
softmaxout = npout_view[startidx:startidx + fpgaoutsz]
# first activate first two channels of each bbox subgroup (n)
for b in range(self.args['bboxplanes']):
for r in range(\
self.args['batchstride']*b,
self.args['batchstride']*b+2*self.args['groups']):
softmaxout[r] = sigmoid(softmaxout[r])
for r in range(\
self.args['batchstride']*b\
+self.args['groups']*self.args['coords'],
self.args['batchstride']*b\
+self.args['groups']*self.args['coords']+self.args['groups']):
softmaxout[r] = sigmoid(softmaxout[r])
# Now softmax on all classification arrays in image
for b in range(self.args['bboxplanes']):
for g in range(self.args['groups']):
softmax(
self.args['beginoffset'] +
b * self.args['batchstride'] +
g * self.args['groupstride'], softmaxout,
softmaxout, self.args['outsz'],
self.args['groups'])
# NMS
bboxes = nms.do_baseline_nms(
softmaxout, shapeArr[i][1], shapeArr[i][0],
firstInputShape[2], firstInputShape[3], self.args['out_w'],
self.args['out_h'], self.args['bboxplanes'],
self.args['outsz'], self.args['scorethresh'],
self.args['iouthresh'])
bboxlist_for_images.append(bboxes)
print "image: ", imgList[
i], " has num boxes detected : ", len(bboxes)
if self.args['golden'] is None:
return
for i in range(min(self.args['batch_sz'], len(shapeArr))):
filename = imgList[i]
out_file_txt = ((filename.split("/")[-1]).split(".")[0])
out_file_txt = self.args[
'detection_labels'] + "/" + out_file_txt + ".txt"
out_line_list = []
bboxes = bboxlist_for_images[i]
for j in range(len(bboxes)):
x, y, w, h = darknet_style_xywh(shapeArr[i][1], shapeArr[i][0],
bboxes[j]["ll"]["x"],
bboxes[j]["ll"]["y"],
bboxes[j]['ur']['x'],
bboxes[j]['ur']['y'])
line_string = str(bboxes[j]["classid"])
line_string = line_string + " " + str(
round(bboxes[j]['prob'], 3))
line_string = line_string + " " + str(x)
line_string = line_string + " " + str(y)
line_string = line_string + " " + str(w)
line_string = line_string + " " + str(h)
out_line_list.append(line_string + "\n")
log.info("writing this into prediction file at %s" %
(out_file_txt))
with open(out_file_txt, "w") as the_file:
for lines in out_line_list:
the_file.write(lines)