Kobe

Results 10 comments of Kobe

博主的数据颜色处理环节是不是有问题哈,代码如下: def random_hue(img_hsv, hue_vari, p=0.5): if np.random.uniform(0, 1) > p: hue_delta = np.random.randint(-hue_vari, hue_vari) img_hsv[:, :, 0] = (img_hsv[:, :, 0] + hue_delta) % 180 return img_hsv 这个地方的180有点诡异,opencv读取的数据范围在[0 255]之间,他这里全部归一化到[0 180]...

how to solve the following problem: Traceback (most recent call last): File "/home/xxx/workspace/face/seanlinux/mtcnn-master/example/train_P_net.py", line 73, in args.begin_epoch, args.end_epoch, args.frequent, args.lr, args.resume) File "/home/xxx/workspace/face/seanlinux/mtcnn-master/example/train_P_net.py", line 11, in train_P_net gt_imdb = imdb.gt_imdb()...

> Hello,I met a problem when I run "python train_P_net.py" with Windows, It print errors like that: > > C:\Users\user\Desktop\V2_MXNet\example>python train_P_net.py > Called with argument: > Namespace(begin_epoch=0, dataset_path='../data/mtcnn', end_epoch=16, epoch=0,...

I rectify the code by the following method, and the code are work... Details coding position as following: cache_file = os.path.join(self.cache_path, self.name + '_gt_roidb.pkl') size_cache_file = 0 if os.path.exists(cache_file): size_cache_file...

![image](https://user-images.githubusercontent.com/33019213/150757064-17fe82a0-212b-44d0-96bb-93621a71646a.png) I am very confused about the gradient explanation of this place, but the use of this gradient is not reflected in your code, and the author's gradient calculation is...

> I did not find it. ModuleNotFoundError: No module named 'pretrainedmodels' How to fix above problem? Can you help me?

> 原作者您好,目前我只是复现了detection部分,效果不太好。RoIRotate这部分实现起来好像还挺复杂的,目前卡在这块了 > @lufo816 我在我的机器上运行你的代码,发现出现 ModuleNotFoundError: No module named 'pretrainedmodels',请问这个pretrainedmodel是python文件,还是模型文件