lufficc / dpnet Goto Github PK

Hi, how can i use your pre trained models to obtain results ?

你好，我正在复现RPC数据集论文，目前进行到对合成图片进行渲染，发现渲染图片中商品位置发生改变，数量也发生了变化，请问可以详细交流一下渲染训练与测试过程吗，十分感谢，以下是我的训练和渲染过程：

1.我使用了1000张合成图片放入trainA文件夹，1000张RPC数据集真实图片放入突然trainB文件夹，训练了200个epoch。
2.训练指令为python train.py --dataroot ./datasets/goods --name goods_cyclegan --model cycle_gan --pool_size 50 --no_dropout。
3.日志文件最后一个epoch显示：
learning rate 0.0000020 -> 0.0000000
(epoch: 200, iters: 100, time: 0.346, data: 0.206) D_A: 0.142 G_A: 0.519 cycle_A: 0.220 idt_A: 0.078 D_B: 0.034 G_B: 0.762 cycle_B: 0.292 idt_B: 0.068
(epoch: 200, iters: 200, time: 1.660, data: 0.001) D_A: 0.143 G_A: 0.342 cycle_A: 0.360 idt_A: 0.079 D_B: 0.089 G_B: 0.731 cycle_B: 0.314 idt_B: 0.102
(epoch: 200, iters: 300, time: 0.346, data: 0.001) D_A: 0.192 G_A: 0.414 cycle_A: 0.213 idt_A: 0.045 D_B: 0.062 G_B: 0.679 cycle_B: 0.193 idt_B: 0.086
(epoch: 200, iters: 400, time: 0.346, data: 0.002) D_A: 0.182 G_A: 0.421 cycle_A: 0.457 idt_A: 0.080 D_B: 0.028 G_B: 0.803 cycle_B: 0.239 idt_B: 0.134
(epoch: 200, iters: 500, time: 0.345, data: 0.001) D_A: 0.186 G_A: 0.249 cycle_A: 0.273 idt_A: 0.054 D_B: 0.068 G_B: 0.578 cycle_B: 0.211 idt_B: 0.077
(epoch: 200, iters: 600, time: 0.587, data: 0.001) D_A: 0.205 G_A: 0.253 cycle_A: 0.258 idt_A: 0.099 D_B: 0.204 G_B: 0.650 cycle_B: 0.379 idt_B: 0.071
(epoch: 200, iters: 700, time: 0.345, data: 0.001) D_A: 0.157 G_A: 0.469 cycle_A: 0.266 idt_A: 0.064 D_B: 0.099 G_B: 0.426 cycle_B: 0.219 idt_B: 0.083
(epoch: 200, iters: 800, time: 0.346, data: 0.001) D_A: 0.122 G_A: 0.426 cycle_A: 0.400 idt_A: 0.137 D_B: 0.142 G_B: 0.857 cycle_B: 0.431 idt_B: 0.133
(epoch: 200, iters: 900, time: 0.346, data: 0.001) D_A: 0.137 G_A: 0.664 cycle_A: 0.320 idt_A: 0.071 D_B: 0.084 G_B: 0.456 cycle_B: 0.280 idt_B: 0.085
(epoch: 200, iters: 1000, time: 1.736, data: 0.001) D_A: 0.116 G_A: 0.381 cycle_A: 0.288 idt_A: 0.077 D_B: 0.121 G_B: 0.725 cycle_B: 0.296 idt_B: 0.088
saving the latest model (epoch 200, total_iters 200000)
saving the model at the end of epoch 200, iters 200000
End of epoch 200 / 200 Time Taken: 332 sec

4.测试指令为python test.py --dataroot datasets/goods/testA --name goods_pretrained --model test --no_dropout，其中使用的模型为latest_net_G_A.pth模型修改得到的latest_net_G.pth，用于单侧的测试。

最后生成的渲染图片效果不是很理想，如下图所示：

非常希望得到你的帮助，谢谢！

lufficc您好，想向您请教一个问题，
我用gan训练完后，发现结果存在一些明显的噪声，我训练了200个epoch，trainA里面放的是用您的算法生成的图像，共3000张，如图1所示，trainB里面放的rpc数据中的原始val2019里面的数据，共3000张，如图2所示。
图1

图2

we can see Paper recommend use Salient Object Detection with CRF.
But from your source code ,we can inference you use traditional edge detection.

Do you know which is better?

how to quickly reproduce you paper ?

we want to discuss with you in depth in smart retail field?
I do not know whether there is any chance to cooperate in business？
my qq:469234443
email:[email protected]

Dear @lufficc , thank you for sharing your work.
As you said in other issue:
We first use traditional edge detection to extract coarse masks, and then use Salient Object Detection to refine the coarse masks.

As I know, there are two approaches to refining the coarse masks:

1. Traditional image processing: Grabcut https://dl.acm.org/doi/10.1145/1186562.1015720 and its extent densecut http://mmcheng.net/densecut/
2. Deep learning: https://github.com/AceCoooool/DSS-pytorch. This method requires images and their corresponding labels to train the model.

Could you let me know which method you used to refine the coarse masks?
If you used the 2nd approach as I mention above, then you must used the already refined masks to train the network?

why can not inference used pre-trained model ?