leixy

in video2anime.py change tf.v1 to tf.compat.v1, in test.py change args.style_name to args.save_dir. just sample errors.

yolov3 not in model zoo?

7

## ❓ Questions and Help

论文中的420fps的batch设置为多少？

6

请教下，论文中的420fps是在什么GPU上测试的，以及batch设置为多少？ 我在1070上和titanX上，batch=16时的fps，分别为1000fps和1600fps。

the original conditional judgment while be True while torchvision>=0.10

Hi, When I run the simpleCUFFT_2d_MGPU, after the call the [result = cufftXtMemcpy(planComplex, d_d_f, d_f, CUFFT_COPY_DEVICE_TO_DEVICE);](https://github.com/NVIDIA/cuda-samples/blob/master/Samples/4_CUDA_Libraries/simpleCUFFT_2d_MGPU/simpleCUFFT_2d_MGPU.cu#L255),I copyData d_f、d_d_f from gpus to host memory, like this,  In host Memory, d_f_out!=d_d_f_out....