Jackie Loong
Jackie Loong
Learner nParams: 32901 Traceback (most recent call last): File "main.py", line 38, in results = importlib.import_module(opt['metaLearner']).run(opt, data) File "/home/i/meta/FewShotLearning/model/lstm/train-lstm.py", line 121, in run opt['batchSize'][opt['nTrainShot']]) File "/home/i/conda/envs/py27/lib/python2.7/site-packages/torch/nn/modules/module.py", line 325, in __call__...
dear fellows: As one of the most large-scale video action dataset, hacs has been published and widely used for years. I thinks its relatively important to support this large dataset....
点击“New Issue”就可以发帖啦，一般1~3天之内回复。大家可以自由交流。
Dear author: Thanks for the neat and well-documented repo. It's really helpful! I found these `V_19` series pth file can not found any instances, While these` V_39 ` series pth...
Dear all: I noticed that the cross entropy ID loss for small ID number dataset works pretty well. But when scaled to large-scale ID numbers, let's say up to 0.1M...
Dear all: I found lots of people can not reproduce the visdrone result even using pretrained weights. Here is my result:  when i decrease the threshold from 0.4 to...
Dear author, I found mmation2 is already supportin posec3d now.I wonder is this repo. still active ? or you will switch to mmaction2 next step? thank you.
Hi, dear author: Thank you for the well-done work! How to extract flow in dataset prepration and set it up for training? I did not see the guides in data...
Dear authors: Thanks for your great work. COCO is widely used, hence i wonder will you add coco panoptic dataset support? or can you give me some tips on how...
Thanks for your great implementation. Currently Iam trying to translate it to TF2 implementation. But I find it difficult for me to understand SharedAdam part and do not know how...