edward3862/lofgan-pytorch

LoFGAN: Fusing Local Representations for Few-shot Image Generation. (ICCV 2021)

lofgan-pytorch's Issues

Questions regarding Animal Faces dataset.

Thanks for the exellent work. I have a query reagarding the dataset used in this paper. The shared .npy file for the Animal Faces dataset has a dimension of (149, 100, 128, 128, 3). It means 100 images for each class. The same is also mentioned in the paper. Thus, total it has 14900 images. However, the orginal Animal Faces dataset proposed in the FUNIT paper [1] has 117574 images, (~750 images per class). I am wondering why this paper doesn't use the whole set. Are the 100 images sampled randomly from the original set?

In the Flower dataset .npy file also there are reduced number of samples than the original dataset.

[1] Few-Shot Unsupervised Image-to-Image Translation

one question

When I runing LOFGAN using checkpoints'resume in my own datasets, I meet Gradient explosion like the picture shows. Had you ever meet this question?
And another question, with LOFGAN running, the GPU'memory consumption goes bigger and bigger until memory overflow. How do you run it for 100000 epoches? I try to resume the model after memory overflow and go on training until 100000 epoches, but I only do once successfully which means the rest failed caused by Gradient explosion. Can you give me some advice?

How to reproduce the FID indicator?

Thank you for your good job! I have a question about the FID.
python main_metric.py --gpu 0 --dataset flower --name results/flower_lofgan --real_dir datasets/for_fid/flower --ckpt gen_00100000.pt --fake_dir test_for_fid

Can you please let me know where is "datasets/for_fid/flower" present to calculate the fid score.

关于论文中Figure 4和Figure 5

请问作者，论文中Figure 4是怎么得到的，有代码可以参考一下吗？Figure 5对于不同的η，是重新训练一次还是只在测试的时候改变η的值呢？

Classification evaluation

Can you please provide the script for reproducing the classification in your paper?
Thanks a lot.

Datasets

Could you please share the datasets in .npy format or the source code to produce the data?

Augment for Classification Experiments.

Hi, edward.
How to split the seen data to pre-train the ResNet18 in section 4.7? THX!

How to reproduce the classification results

Thank you for your good job. Can you please provide the code for calculating the classification accuracy as noted down in the paper.

Re: Labels for each of the datasets

Thanks for this amazing work!
I observed that the order of the classes in the .npy files for all the datasets is random, if possible could you provide the labels according to the order of classes in the .npy files as well?

一个小问题

学姐你好，我正在学习你提出的lofgan，并且尝试用在了自己的数据集上，这个是画的一个损失函数图。上面的是鉴别器的loss_adv_dis损失，训练到后期基本降至0了；下面的是生成器的loss_adv_gen损失，是一个逐渐上升的趋势。想请教下您这个情况是正常的吗

typo

'smaple' in dataset.py, should be 'sample'

How to realize Visualization of the Learned Similarity

Hi, Edward～Thank you for your excellent work！
In section 4.2 of your paper, this part of the work is really interesting.
I have two problems: (1) Is this subsection of the experiment implemented with grad-cam? (2) Can you share the relevant code? This trick for the highlight is very clever.

Happy New Year to you! Good work in the new year!

余弦相似度问题？

https://github.com/edward3862/LoFGAN-pytorch/blob/4ad8b4dd4ec8f8795e044b2c58f507af898d580d/networks/lofgan.py#L292C17-L292C17

fx = torch.matmul(w_feat_select, w_ref) # (321264)

这里实在求余弦相似度吗？ 只求了内积？

Datasets

Could you please share the datasets in .npy format or the source code to produce the data? I want to try this model on a homemade dataset to see how the image is generated

Cuda out of memory.

Hi, Edward.
Thanks a lot for your excellent work.
I met this problem when I run the code on machine with 3090 20G *1 after training 2000 iterations.
Any idea how to fix it?
I train the model with your recommended setting:
python train.py --conf configs/flower_lofgan.yaml --output_dir results/flower_lofgan --gpu 0
RuntimeError: CUDA out of memory. Tried to allocate 200.00 MiB (GPU 0; 23.70 GiB total capacity; 18.17 GiB already allocated; 120.56 MiB free; 22.21 GiB reserved in total by PyTorch)

To address this issue, I have tried below in the training loop:

• torch.cuda.empty_cache()
• del imgs, lable
• gc.collect()
  However, none of them helps.
  I also tried to detach() the loss items, still the same issue after 2000 iterations.

Dataset

Hi,I could not find the dataset vgg_face_data_rgb.npy,the link is not exist. Could you share it again?

About VGGface dataset

Hello, it is a wonderful work and thanks for the open source code.
However, there is no VGGface in the download link of the datasets provided. Could you please provide a download link of VGGface?

About the experiment

Hi and thanks for the great work. I have two questions about the experiment. 1. What is the division ratio of Sin and Sreal when calculating FID? Whether the three datasets randomly select 30 reference images for each unseen category, and then generate 128 images. 2. For the experimental part "Augmentation for Classification" , is the generated image using the image in Dtrain as reference images?

about "classification" of Discriminator

Hi, Edward.
Thanks a lot for your excellent work.
I met this problem when I study your paper and code.That's I don't understand what's the purpose of "classification" layer in Discriminator. So I want to ask for your opinion.

关于相似度函数g是如何计算的？

作者您好，请问下，文中的相似度函数g具体是？在代码中，我看到的只是一个均匀分布替代相似度计算。希望解答一下，祝科研顺利！

About datasets

Thank you for your amazing work!
I didn't find the datasets of vgg_face_data_rgb.npy, can you provide it?

dataset

Hi, Edward. Thanks for your excellent work. I could not find the dataset vgg_face_data_rgb.npy.Could you share it? THX!

How to train on dataset with image size 384*384

Hi, Edward.
Thanks a lot for your excellent work.
I met this problem when I run the code using my dataset with image size 384*384,
Any idea how to fix it?
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [32,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [33,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [35,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [36,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [37,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [38,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [39,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [41,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [42,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [43,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [44,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [47,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [48,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [49,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [50,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [55,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [58,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [60,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [61,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [62,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [63,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [0,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [1,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [2,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [3,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [5,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [7,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [8,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [10,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [12,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [14,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [15,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [16,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [18,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [19,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [20,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [21,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [22,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [23,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [26,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [27,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [28,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [29,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [30,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [2,0,0], thread: [31,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [32,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [33,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [34,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [35,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [36,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [39,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [40,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [41,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [42,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [44,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [45,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [46,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [47,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [49,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [50,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [52,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [55,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [56,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [57,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [58,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [59,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [61,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [62,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [63,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [0,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [1,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [2,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [6,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [7,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [8,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [9,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [10,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [11,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [12,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [13,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [14,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [16,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [17,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [18,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [19,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [20,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [21,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [22,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [23,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [26,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [28,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [29,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [30,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [1,0,0], thread: [31,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [32,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [33,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [34,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [35,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [36,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [39,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [40,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [41,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [42,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [44,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [45,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [46,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [47,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [49,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [50,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [52,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [55,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [56,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [57,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [58,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [59,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [61,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [62,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [63,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [0,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [1,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [2,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [6,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [7,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [8,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [9,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [10,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [11,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [12,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [13,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [14,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [16,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [17,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [18,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [19,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [20,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [21,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [22,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [23,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [26,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [28,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [29,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [30,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/ScatterGatherKernel.cu:115: operator(): block: [0,0,0], thread: [31,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
Traceback (most recent call last):
File "/home/jefflin/Documents/LoFGAN-pytorch/train.py", line 56, in
trainer.gen_update(imgs, label)
File "/home/jefflin/Documents/LoFGAN-pytorch/trainer.py", line 32, in gen_update
losses = self.model(xs, y, 'gen_update')
File "/home/jefflin/.conda/envs/pytorch/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/jefflin/Documents/LoFGAN-pytorch/networks/lofgan.py", line 31, in forward
feat_real, _, _ = self.dis(xs)
File "/home/jefflin/.conda/envs/pytorch/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/jefflin/Documents/LoFGAN-pytorch/networks/lofgan.py", line 147, in forward
feat = self.cnn_f(x)
File "/home/jefflin/.conda/envs/pytorch/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/jefflin/.conda/envs/pytorch/lib/python3.9/site-packages/torch/nn/modules/container.py", line 139, in forward
input = module(input)
File "/home/jefflin/.conda/envs/pytorch/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/jefflin/Documents/LoFGAN-pytorch/networks/blocks.py", line 198, in forward
x = self.conv(self.pad(x))
File "/home/jefflin/.conda/envs/pytorch/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1060, in call_impl
result = hook(self, input)
File "/home/jefflin/.conda/envs/pytorch/lib/python3.9/site-packages/torch/nn/utils/spectral_norm.py", line 105, in call
setattr(module, self.name, self.compute_weight(module, do_power_iteration=module.training))
File "/home/jefflin/.conda/envs/pytorch/lib/python3.9/site-packages/torch/nn/utils/spectral_norm.py", line 85, in compute_weight
u = normalize(torch.mv(weight_mat, v), dim=0, eps=self.eps, out=u)
File "/home/jefflin/.conda/envs/pytorch/lib/python3.9/site-packages/torch/nn/functional.py", line 4431, in normalize
denom = input.norm(p, dim, keepdim=True).clamp_min(eps).expand_as(input)
File "/home/jefflin/.conda/envs/pytorch/lib/python3.9/site-packages/torch/_tensor.py", line 417, in norm
return torch.norm(self, p, dim, keepdim, dtype=dtype)
File "/home/jefflin/.conda/envs/pytorch/lib/python3.9/site-packages/torch/functional.py", line 1356, in norm
return _VF.norm(input, p, _dim, keepdim=keepdim) # type: ignore[attr-defined]
RuntimeError: CUDA error: device-side assert triggered
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

One question

Thangks for your great work. I have some question due to my poor GPU with only 8GB memory when I try to reproduce your work. And I want to change some parameter of LOFGAN to make it suitable for the picture with a size of 32323. Do you think it is feasible? and can you give me some advice on how to change the parameter?

数据集问题

你好，最近在学习lofgan，想使用其他数据集，仿照给出的flower和animal两个npy文件制作了新的npy文件，但是试验的效果不是很好，请问能否提供一下生成npy文件的源码，谢谢

about loss of dis and gen

The left is generator'loss, and the right is discrainatar'loss when I run lofgan in my own datasets.
Does this mean the generator not be better after about 7506 epochs?