-
Hi, I'm training tiny-yolov2 on one TITAN Xp with `--gpu 0.9` and `--batch 64`, and found the training speed is very slow, say 8500 steps / 15 hrs. CPU utility keeps ~400%, but GPU utility is mostly 0…
-
Thank you for a wonderful code.
I confirmed the operation in the following environment.
All model data has been set up.
* Geforce GTX 1080
* Windows 10 x64
* Python 3.6
* tensorflow-gpu 1.5
*…
-
this has been mentioned quite a lot recently.
* [mobilenet](https://arxiv.org/pdf/1704.04861.pdf)
mobilenet does a better job on describing depthwise separable convolution.
* [xception](https:…
-
Hi,
I'm a somewhat newbie to deep-learning and therefore I would be pleased if you have time to answer my questions.
Situation
Now I'm doing research on how the pedestrian traffic influences the …
LESRQ updated
5 years ago
-
I am looking at a way, we could use your implementation on live object detection.
But looks like inference on static images alone are quite slow.
Will be learning more about your design and algorit…
-
I've fetched the issue while model output type MLMultiArray Flot32 multidimensional array of floats.
Heres in my convert script for .h5 to ml model using coremltools 4.0
```
from tensorflow imp…
-
Is it possible to put the entire load of yolov3-tiny model in GPU memory ??? It seems to be taking quite a lot of cpu on my i7 laptop with GTX 1050.
Statistics:
80 FPS
top
PID USER PR N…
-
I've been looking at your deliverable for weeks 3/4 and I think you have done a very good job. I particularly like the way you are presenting things in the READMe.md file. It is neat and clear.
The…
-
the code requests python3 , but my tensorflow is installed on python 2.7, can the code work on python 2.7?
-
作者您好，你的网络结构初始448x448，然后padding为3，最后7x7卷积，步长为2得到224x224，再2x2（步长2)池化，池化padding为same，得到224x224，而论文是112x112，是不是padding的问题呢？另外我看了原作者的cfg文件，第一层卷积padding为1不是3啊。