liudaizong / csmgan Goto Github PK

Hi, the TACoS feature link is unavailable. Could you please update it?

你好，我使用的是TACOS，有tall_c3d_features.hdf5，但是没有以.npy结尾的特征文件

Hello, after reading your paper, I have a question I would like to consult. I want to know how formula (6) in your paper is realized in the code,

Hi! I have downloaded the extracted features of Activity Caption, the downloaded file suffix is .hdf5, and an error ('No such file or directory') will be reported when running. I have tried to modify the file name or the suffix but it has no effect. How should I use this file?

"we adopt convolution kernel size of [16, 32, 64, 96, 128, 160, 192] for Activity Caption, and [8, 16, 32, 64] for TACoS."
actually, the kernel size is 1 in your code. This may not be called a multi-scale window.
In addition, could you please provide your results using the correct IoU calculation?

hello,i noticed that your pretrained model with a subsript like model_4274 on tacos and model_6852 on activity,does it means you
finished training the model on 4274 and 6852 epoch respectively? Now im trying to retrain it without load any pretrained model,but it never arrive this line and the performence get worse and worse after epoch100+,my main.py hyper-parameters are all your defualt set on README.MD.Are you got a gradually improvement when you train it with the same hypara.expecting a reply think you.

Hi, I am confused about implemention of the loss function used in the paper, this is the function:

and I only find the following code:

Could you share the code of the paper function ?

The function calculate_IoU_batch in criteria.py, Why do you add 1 to the numerator and denominator when you compute the IOU? I am very confused!! It feels unfair!!

Hi, I've download the glove embeddings glove.840B.300d.zip, how can I use it? Or how can I get the file glove.bin?

The model implemented by the code is quite different (e.g., only one layer Graph) from the model described in the paper. However, the results of the code are consistent with the paper. It feels so strange. Anyone can help me?

您好，最近在调式您公布的代码，遇到了一点技术上的问题。详情如下，希望能得到您的解答，谢谢！
1、使用的是数据集activitynet，使用的特征是 http://activity-net.org/challenges/2016/download.html 上的PCA_activitynet_v1-3.hdf5
2、但是运行的过程中，出现了这个error提示：“OSError: Unable to open file (unable to open file: name = './Extracted_Features/PCA_activitynet_v1-3/v_yINX46xPRf0.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)。”
请问您能帮忙看下这是哪里出现了问题吗？（是否是activitynet的特征取错了？还是其他原因呢？）

could you please release the features ?thanks