yangbisheng2009

Results 12 issues of yangbisheng2009

``` background = (0, 0, 255) # random_color(238, 255) color = (0, 0, 255, 255) # random_color(0, 200, random.randint(220, 255)) im = self.create_captcha_image(chars, color, background) #self.create_noise_dots(im, color) #self.create_noise_curve(im, color) im...

Since resnet is very strong now, why didn't your try it? Is it something wrong or some theory not suitable for nsfw? Looking forward to your guidance

enhancement
help wanted
question
training

I am a little confuse. If they use the same training data, In fine_tune phase just train the last few layer. I think this operating is a little redundant with...

question
training

根据我的实验结果,最终效果不太理想呢,是不是有些细节需要调优

AttributeError: 'RetainNet' object has no attribute 'load_pretrained_weight'

我原来一直在根据 https://github.com/eriklindernoren/PyTorch-YOLOv3 这个来做训练、预测,但是一直没有解决多卡训练的问题,我发现单纯的添加: model = nn.DataParallel(model, device_ids=args.device) model.cuda() 这两行,并不能为训练速度带来提升,我看您的代码有支持多卡训练,能帮忙解答下吗?感谢!

我在训练的过程中,现在跑了大约30个epoch 发现训练集的准确率总是高于验证集10个点,感觉像是有点过拟合, 我现在准备改一下,添加一些防止过拟合的参数,希望楼主能给点建议