search

heromanba / 3D-R2N2-PyTorch

PyTorch version of 3D-R2N2
MIT License
56 stars 15 forks source link

Pretrained Model Information #6

Open fabr0d opened 4 years ago

fabr0d commented 4 years ago

Dear author, could you provide us with information about the training that was done to obtain the pretrained model(ResidualGRUNet), such as the configuration used, the hardware, etc. Thanks in advance.

heromanba commented 4 years ago

Hi, sorry to reply late.

For configuration, you can refer to this file https://github.com/heromanba/3D-R2N2-PyTorch/blob/master/experiments/scripts/res_gru_net.sh

For hardware,

+-----------------------------------------------------------------------------+
| NVIDIA-SMI 430.50       Driver Version: 430.50       CUDA Version: 10.1     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|===============================+======================+======================|
| 0  GeForce RTX 2060super  Off | 00000000:01:00.0  On |                  N/A |
|  0%   44C    P8    13W / 175W |    141MiB /  7977MiB |      3%      Default |
+-------------------------------+----------------------+----------------------+