Hello guys,
Now I make a training using yolov4 model with GPU calculation in opencv. All the parameters are default. I use the NVIDA Jetson AGX Xavier 32G NX TX2 developing kit. However, the training speed is very slow, less than 2 frame/s.
Following is the log when I am training to recognize the picture of a dog.
There are about 160 layers for the neural network. It is running so slow. Do you know what’s the problem?
Here is the parameter and command for running the training:
atlixch@atlixch-desktop:/opt/module/yolov4/darknet$ ./darknet detector test ./cfg/coco.data ./cfg/yolov4.cfg ./yolov4.weights data/dog.jpg
[yolo] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.10
nms_kind: greedynms (1), beta = 0.600000
151 route 147 → 38 x 38 x 256
152 conv 512 3 x 3/ 2 38 x 38 x 256 → 19 x 19 x 512 0.852 BF
153 route 152 116 → 19 x 19 x1024
154 conv 512 1 x 1/ 1 19 x 19 x1024 → 19 x 19 x 512 0.379 BF
155 conv 1024 3 x 3/ 1 19 x 19 x 512 → 19 x 19 x1024 3.407 BF
156 conv 512 1 x 1/ 1 19 x 19 x1024 → 19 x 19 x 512 0.379 BF
157 conv 1024 3 x 3/ 1 19 x 19 x 512 → 19 x 19 x1024 3.407 BF
158 conv 512 1 x 1/ 1 19 x 19 x1024 → 19 x 19 x 512 0.379 BF
159 conv 1024 3 x 3/ 1 19 x 19 x 512 → 19 x 19 x1024 3.407 BF
160 conv 255 1 x 1/ 1 19 x 19 x1024 → 19 x 19 x 255 0.189 BF
161 yolo
[yolo] params: iou loss: ciou (4), iou_norm: 0.07, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.05
nms_kind: greedynms (1), beta = 0.600000
Total BFLOPS 128.459
avg_outputs = 1068395
Allocate additional workspace_size = 42.19 MB
Loading weights from ./yolov4.weights…
seen 64, trained: 32032 K-images (500 Kilo-batches_64)
Done! Loaded 162 layers from weights-file
Detection layer: 139 - type = 28
Detection layer: 150 - type = 28
Detection layer: 161 - type = 28
data/dog.jpg: Predicted in 1669.076000 milli-seconds.
bicycle: 92%
dog: 98%
truck: 92%
pottedplant: 33%
Gtk-Message: 17:29:13.103: Failed to load module “canberra-gtk-module”
[5]+ 已杀死 ./darknet detector demo cfg/voc-mask.data cfg/yolov4-mask-test.cfg /opt/module/yolov4/backup/yolov4-mask_best.weights /software/testfiles/kouzhao2_masked.avi
atlixch@atlixch-desktop:/opt/module/yolov4/darknet$
Can anyone give me the solution?
Thanks!