WS_DAN issues

当batchsize设为4或8时报错

train_sample.py中的np.random.choice(np.arange(0, num_parts), 1, p=part_weights) 处报错 “probabilities contain NaN”. 使用batchsize=1, 12, 16, 32均不报错。请问是为什么呢？该算法对batchsize有特殊限制？

geolvr

something wrong when converting Aircraft

2

$ python convert_data.py --dataset_name=Aircraft --dataset_dir=./Aircraft/Data Traceback (most recent call last): File "convert_data.py", line 76, in tf.app.run() File "/mnt/disk0/home/mahailong/anaconda3/envs/CenterNet/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 126, in run _sys.exit(main(argv)) File "convert_data.py", line 65, in main convert_aircraft.run(FLAGS.dataset_dir)...

macn3388

Some performance issues in the programs

Hello, I found that there are some little performance issue in [tf.random_uniform](https://github.com/tau-yihouxiang/WS_DAN/blob/199fa5e97312e6d34ebd53eb03ac806bc92e5639/nets/nasnet/nasnet_test.py#L167) WS_DAN//nets/nasnet/nasnet_test.py. If the function is called a lot, the efficiency of program execution will be reduced. I think...

DLPerf

引用

你好，这篇文章最后发表在哪了？我想引用，但是找不到除了arxiv的bib。

boxyao

Why are pooled features multiplied by 100?

In `bilinear_attention_pooling` the pooled features are multiplied by 100. Why is that?

catalys1

DateSets

2

QingxinWx

How to run inference on image or video?

1

Hi @tau-yihouxiang @ManWingloeng @Danbinabo, Can any one please tell me how to run the inference on input image or video? I have trained the model using readme instructions. but I...

lakshmankanakala

Different claims for the paper and the code on attention regularization

2

Hi there, Thanks for the contribution! After reading the code, I am kind of confused on the attention regularization part. Please correct me if there is some misunderstanding. From the...

tao0420