-
There are no rotate_nms_kernel.cu and rbbox_overlaps_kernel.cu files in box_utils directory, so I can't compile nms_gpu and iou_gpu on Windows. Would you update these files?
-
My computer configuration:
PyTorch version: 1.0.1
Is debug build: No
CUDA used to build PyTorch: 10.0.130
OS: Ubuntu 18.04.5 LTS
GCC version: (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
CMake version:…
-
Hi
I found a problem. When I was testing the model (python ./tools/test_net.py --config-file=configs/arpn/e2e_rrpn_R_50_C4_1x_test_AFPN.yaml).
2020-12-31 13:35:14,374 maskrcnn_benchmark.utils.chec…
-
感谢作者，您的工作给小弟提供了极大帮助！
不过暂时不太懂，这样一行
anchor_angle=[-60, -30, 0, 30, 60, 90]
请问角度是如何定义的呢？
是矩形较长的边与x轴的夹角吗？
变化范围是多少？
非常感谢您！
-
对于FPN版本，作者推荐的anchor size为[2, 4, 8, 16, 32]，和maskrcnn_benchmark默认的anchor size [32, 64, 128, 256, 512]差别较大，我看了一下生成anchor部分的代码还是有一定区别：
原始RPN：
```
def generate_anchors(
stride=16, sizes=(32, 64,…
-
I am using the pre-trained model for testing on my own images. I had downloaded model_IC15_89.pth using the link https://drive.google.com/file/d/1nv-ZjbYBj8ePZRa_fAhbHvzm7HqSxPWK/view?usp=sharing and …
-
感谢您分享mask rcnn的rrpn模型，接触深度学习时间不太长，所以有些地方没有看明白
1.我理解的是我需要把我的数据组织成VOC数据集的格式。我手里有自己用labelme制作的json格式的数据集，我把他转化为xml格式然后组织成
VOC
|_ JPEGImages
| |_ .jpg
| |_ ...
| |_ .jpg
|_ Annotations
| |_ .j…
-
can you share your model config yaml to us so that we can train our stable model ?
i use your code to train on ic15 and mlt17 , but the result is not good ,so may i ask you to
share your training y…
-
## 🐛 Bug
```
from maskrcnn_benchmark.layers.rotate_nms import rotate_iou
a=torch.tensor([[50.7325,50.7325,100.7325,300.7325,-3.4]]).float().to('cuda')
b=torch.tensor([[50.7325,50.7325,100.73…
-
学长，你好，我按照你在ｇｉｔｈｕｂ上的步骤一步步进行，ｄｅｍｏ测试没有问题，但是在训练网络时报错，在网上也搜不到答案，请问下面的问题是数据生成的不对吗？
数据数据时用到的代码内容如下：
![image](https://user-images.githubusercontent.com/28551961/36962643-5738d852-208b-11e8-93d5-5873531fde22…