deep-learning-for-image-processing

deep-learning-for-image-processing copied to clipboard

大佬您好： 我看完了U2Net的博客和视频，好像在代码中并没有载入预训练权重，我的代码能力比较差。想问一下代码中是否载入了预训练权重？如果没有载入应该在哪里加一些代码呢？ 十分感谢大佬的代码和视频。

xiaomi576

分类任务中，缺少test.py评估模型在测试集上的性能，predict.py只能对单一图片进行分类，美中不足

bayueqiankong

多GPU训练出错，能否帮助看下可能是什么问题

5

**System information** * Have I written custom code: 没有 * OS Platform(e.g., window10 or Linux Ubuntu 16.04):Linux Ubuntu 16.04 * Python version: 3.8 * Deep learning framework and version(e.g., Tensorflow2.1...

Yuhuoo

Efficientnetv2在Imagenet上的推理精度验证？

2

大佬有没有验证过efficienctnetv2-s在imagenet1K验证集上的精度，我怎么推理出来的精度很低，只有12%，好奇怪呀?

qingtian5

**System information** UP你好，我参照视频讲backbone替换成efficientnet，当我使用官方的efficientnet时可以运行，但是用up提供的efficientnet时，出现错误，错误定位到efficientnet代码里drop_path函数的random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)这一行。我使用的torch是1.11.0，torchvision是0.12.0, cu113 **Error info / logs** TypeError: rand() received an invalid combination of arguments - got (Proxy, device=Attribute, dtype=Attribute), but expected one...

fpgajames

**System information** * Have I written custom code: * OS Platform(e.g., window10 or Linux Ubuntu 16.04): * Python version: * Deep learning framework and version(e.g., Tensorflow2.1 or Pytorch1.3): * Use...

davidpengiupui

博主您好，感谢分享！ 请问Res50+FPN模型在anchor生成时只是对特征图中的每一个点按照ratios（0.5，1，2）生成3个anchor吗？

EddieEduardo

报错为这个 Traceback (most recent call last): File "C:\Users\dell\Desktop\deep-learning-for-image-processing-master\pytorch_classification\Test9_efficientNet\train.py", line 145, in main(opt) File "C:\Users\dell\Desktop\deep-learning-for-image-processing-master\pytorch_classification\Test9_efficientNet\train.py", line 76, in main if args.weights != "": AttributeError: 'Namespace' object has no attribute 'weights'

liushuohxgjy

**System information** * Have I written custom code: No * OS Platform: window10 * Python version: 3.8 * Deep learning framework and version: PyTorch 1.7.1 * Use GPU or not:...

Shuvo001

HRNet从头开始训练，跑了209个epoch之后，突然报了这样的错： Epoch: [209] Total time: 1:06:31 (0.8526 s / it) Test: [ 0/199] eta: 0:18:38 model_time: 0.5503 (0.5503) time: 5.6187 data: 3.6315 max mem: 5210 Test: [100/199] eta: 0:00:53 model_time:...

ycj1124