RTNet

RTNet copied to clipboard

您好，我发现您给出的分割结果是两种，有一种通过CRF进行了后处理，我使用您的预训练模型，可以实现未使用CRF的分割结果，但是我用CRF处理了这部分结果，效果不是特别好，我想请问一下这部分的实现细节是什么样的，十分感谢！

YZ1012

I would like to know how did you get the youtube-objects dataset? ?

wen-coder

Unable to train

1

Thanks for your excellent work. However, when I try to train the model, the training process stops at this point. Thanks for helping me out with this issue.

johnson111788

测试数据是怎么组织的？

5

1.您好，我在测试test.py过程中发现DAVIS_dataset = RTTestDataset(dataset, 2, 384, int(384 * 1.75)),其中的dataset不知道如何组织； 2.查看RTTestDataset参数含义发现dataset为以下形式pathes使用： for path in pathes: file = sorted(os.listdir(os.path.join(path, "img"))) for i in file: self.img_list.append(os.path.join(path, "img", i)) self.label_list.append(os.path.join(path, "label", i[:-3] + "png")) self.fwflow_list.append(os.path.join(path,...

aojue1109

How to pre-train the appearance and motion stream models

2

Could you please provide details of training the model of appearance (spatial-R34 or spatial RX-50) and motion stream (temporal-R34 or temporal RX-50)? At first, I tested the pre-trained whole model...

ueoo

About datasets

3

Hello, I want to know why the flipped datasets are four times larger than the original (why not twice), and whether the original data and the flipped data are input...

mindingyao

The H and W of the input img of this function SelfScaling are 1 respectively?

3

Thanks for your good work. The H and W of the input img of this function SelfScaling are 1 respectively? Otherwise, mul cannot be executed. 

longmalongma

Thanks for your amazing work, however I have some questions and would be happy if you answer: - did you use specific model for flipping the images? Any code for...

JawadTawhidi