Pedestrian-Synthesis-GAN

Pedestrian-Synthesis-GAN copied to clipboard

Should person discriminator's loss be back-propagated to generator?

3

I think discriminator's loss should't be back-propagated to generator. But in the source code, when calculating cropped pedestrian discriminator's loss, the tensor `self.person_crop_fake` isn't detached. I think it should be...

bilzard

Confusing bounding box key name

1

bounding box's key names 'h' and 'w' make us associate 'height' and 'width', but they are **NOT**. according source code, they means bounding box's bottom right (x, y) coordinate. https://github.com/yueruchen/Pedestrian-Synthesis-GAN/blob/master/models/pix2pix_model.py#L93-L94...

bilzard

cuda() got an unexpected keyword argument '_id'

3

when training, the below error occurs: ``` python train.py \ --dataroot /content/psgan_datasets/ \ --name my_experiment_1 \ --model pix2pix \ --which_model_netG unet_256 \ --batchSize 256 \ --which_direction BtoA \ --lambda_A 100...

bilzard

invalid argument 2: pad should be smaller than half of kernel size, but got padW = 1, padH = 2, kW = 14, kH = 3 at /pytorch/torch/lib/THCUNN/generic/SpatialDilatedMaxPooling.cu:39

ludaiv

数据集制作

1

你好，冒昧打扰你，想向你请教数据集的格式，疑惑包括 1）加噪声框是手动添加吗，代码中没有包含加噪声框吗 2）从dataset中的格式来看，加噪声框的图片是需要和原图拼在一起形成一张图片吗？ 希望得到你的回复，感谢你！

ludaiv

Hi, I would like to compare my results on the CityPersons detections with your work in your paper. Can you please tell me the exact evaluation protocol that you used?...

vobecant

Could you please point the location of spp-layer?

gtalan

Can you give pointers as to which script corresponds to creating the noisy data ?

subhashree-r

Training on Custom data and objects besides person

4

HI @oyxhust @yueruchen Thanks for wonderful code , when i train the model for custom object besides person it behaves differently , can you share some pointers what are the...

abhigoku10

您好，我看了您的硕士论文，收获破丰，我现在的应用场景是在战场上生成坦克，希望可以得到您的指导，还有就是运行您这个project的话是不是要把cityscapes的数据下载后按照论文第四章的要求截取成256*256的进行训练哈。

HITxyer