Raven Zhao

Inference time for python is too high

2

Hi, I used model **models/mobilenetv2_voc/yolo_lite/train_pruned.prototxt** for training and **models/mobilenetv2_voc/yolo_lite/yolov3_lite_deploy_pruned.prototxt** for test, test script used examples/yolo/detect.py for referece, the inference time is 500ms, which is too slow, is there anything wrong?...

Openvino performance a lot worse than darknet model

3

**[Required]** Your device (RaspberryPi3, LaptopPC, or other device name): LaptopPC **[Required]** Your device's CPU architecture (armv7l, x86_64, or other architecture name): x86_64 **[Required]** Your OS (Raspbian, Ubuntu1604, or other os...

During training, IndexError occurred.

8

Not long from training started, an error occurred as follows: `[Epoch 0/500][Iter 2350/5649][lr 0.000000][Loss: anchor 12.62, iou 12.75, l1 60.10, conf 1123.60, cls 258.15, imgsize 320, time: 6.73] [Epoch 0/500][Iter...

Can u post a simple test file?

4

I am using Keras+VGG and I intend to replace the pooling layer with your function, but it seems there are no place to put. Can u help me?

Inference time

2

How about inference time and platform?