-
Our target is to use object detection API on NVIDIA Jetson platform.
Here are some experiments:
## tf.where op takes long time on GPU
**1.** Test on a TITAN Z PC
**2.** Model: ssd_mobilenet_v1…
-
我的PaddleLite lib使用的代码版本的commitid为：580b929
FZ3A板卡Linux内核版本：4.14.0-xilinx-v2018.3
arm64架构
使用的模型基于yolov3_mobilenet_v1训练，未进行任何量化。
-
Hi!
I'm trying to run pytorch model on an android device and followed this tutorial :
https://github.com/pytorch/tutorials/blob/master/prototype_source/vulkan_workflow.rst
for better performance.…
-
尊敬的Tengine团队：
不好意思，打扰了，有一个问题希望得到你们的帮助。
■问题
在板子「Orange Pi 4(RK3399)」上，我做了一个测试代码，用GPU去运行yolov4-tiny。
结果发现，用GPU(OpenCL)处理时的速度，居然比用CPU(NEON)慢。这是为什么呢？
是因为现在Tengine-Lite还没有完善对yolov4-tiny的匹配吗？或者，您能告诉我…
-
I have test the image on GOPRO dataset by running test_matrics.py,
and with pretrained mobilenet model that author release,
but I got PSRN=26.89 and SSIM=0.814, not 28.17 and 0.925.
Does anyone got…
-
我按照博客的思路 使用MobileNet 自己跑了一个pb 模型，
out:[[ 0.36073172 1.583321 -0.00267795 -0.71573097 -0.17697099]]
pre class_id:[1]
测试结果也没有问题
但是在android studio上面跑的时候，报错：
```
Caused by: java.lang.Illegal…
-
Explore different pretrained models (Inception V3, MobileNet, etc.)
Explore different image preprocessing
Aim for at least 80% accuracy
-
Hey,
Thanks for the amazing work! I would like to implement hardware-friendly DNNs like MobileNets, etc. I wanted to know if there is any upcoming support for depthwise conv layer? If no, may I kn…
-
I am using the solver provided here @#9 with base learning rate reduced to 0.01 to fine-tune mobilenet v1 on ImageNet, and the loss goes up to 87.3365 in the first 20 iterations. I am wondering if you…
-
This is just advice.
In production environment, latency is also very important.
Do you have any plan to train small network, such as mobilenet v1&v2, shufflenet v1&v2 and so on???