Mang Ning

the evaluate_on_coco.py nearly run forever in the process of searching json fiile

3

too slow for searching the image labels in JSON file, around 10 minutes for each image. by the way, there are 2 bugs in `evaluate_on_coco.py` (one is the data type...

Cannot freeze conv layers?

1

I didn't find the keyword of freezing layers

训练中，giou_loss 震荡不下降，徘徊在 12 左右

6

我基于此模型训练一个二分类目标检测，训练中，giou_loss 开始就是20左右，最后下降到12左右不下降了，有人遇到同样的问题吗

RuntimeError: CUDA error: device-side assert triggered (can't train the model if batch is not 1)

4

it seems that the batch_size can only be 1, when I set the batch_size = 4 or 8 during training, the error occurs: Traceback (most recent call last): File "trainval_net.py",...

myCalibrator.py 中校验图片的 val.txt 的格式是什么呢

3

RT

Notes for installation in 2023...

5

Since most people are using Pytorch or Tensorflow 2 and Python3, installing this tensorflow1.4 repo is difficult for people who want to use it in 2023. I first provide the...

CUDA_HOME environment variable is not set. Please set it to your CUDA install root

2

error when using `main.py` script to do evaluation

ImageNet64, classifier guidance ADM-G is worse than ADM regarding FID, but better than ADM regarding IS

1

Hi, can anybody share the FID of ADM-G on ImageNet 64? I get a worse FID than the unconditional ADM

Dear authors, in your paper, you cite 'Imagen Video' (reference [16]) but you name it as Stable diffusion, so I am wondering which one you use exactly?

plan for releasing the training code?

1

Hi @Steven-SWZhang , thanks for the awesome work. Do you have any plans for releasing the training code?