mega.pytorch

mega.pytorch copied to clipboard

Hello, I want to train the network only with VID instead of DET. When I changed DATASETS_TRAIN in base_rcnn_1gpu. yaml and vid_R_101_C4_mega_1x. yaml , the following error occurred. How to...

youzi260

属性错误 nms = amp.float_function(_C.nms) AttributeError(name) AttributeError: nms

1

/home/ming/anaconda3/lib/python3.8/subprocess.py:844: RuntimeWarning: line buffering (buffering=1) isn't supported in binary mode, the default buffer size will be used self.stdout = io.open(c2pread, 'rb', bufsize) Traceback (most recent call last): File "demo_1.py", line...

Zhangming001

there was a probblem using my own datasets:RuntimeError: Sizes of tensors must match except in dimension 3. Got 425 and 423 (The offending index is 0)

3

LuoXiang-LX

How do you visualize the output of FlowNet in DFF

2

Is the output of FlowNet in dff still optical flow And if so, how do you visualize it

gxpzy

which dataset should I download？

2

VID initial release. 22GB. MD5: b329300dd0cd4422171878970d30e1da VID initial release snippets. 15GB. MD5: 4e8f46f7d507edec5a42e1c25de664c3 There are a total of 1952 snippets for training. The number of snippets for each synset ranges...

SpongeBab

BLR post process code

3

thanks for your work. when reading the test_net.py code, I do not find any code about BLR post process. Hasn't this part been released yet。 or just I miss somewhere...

junliang230

I have encountered a problem when using my own data set for training and evaluation.

1

I have encountered a problem when using my own data set for training and evaluation. What is the specific content in the file vid_groundtruth_motion_iou.mat? When I use my own data...

XiaoSue

我用官方给的配置文件和数据集训练模型得到结果并没有论文中的好，我的是78.1%，这是什么原因呢？

3

asmallcat

https://github.com/Scalsol/mega.pytorch/blob/a6aa6e0537b82d70da94228100a51e6a53d98f82/mega_core/data/datasets/vid_mega.py#L133 `images["cur"] = img`, However, this `img` is not corresponding to the current `idx` when `cfg.MODEL.VID.MEGA.GLOBAL.ENABLE == True`. The for loop in line116 will replace `img` at each iteration https://github.com/Scalsol/mega.pytorch/blob/a6aa6e0537b82d70da94228100a51e6a53d98f82/mega_core/data/datasets/vid_mega.py#L116...

Dawn-LX

How to aggregate the results of local aggregation and LGlobal aggregation? What is the operation aggregation? Which line of code implements the aggregation of the results of local aggregation and...

longmalongma