GSM

GSM copied to clipboard

I want to implement this GSM model on a custom dataset. Could you please kindly let me know to what all files I have to make changes to in order...

kalyanmanuri

dose this repository has a way to apply grad-cam ? however, I try to use this https://github.com/ramprs/grad-cam to apply grad-cam but does not work with me please help to use...

dralmadani

As a novice, I saw that the author used different frames to train the model in the paper. Could you tell me how to set the parameters to change the...

jianyulei1

about the gate shift module

4

HI! How does GSM selectively integrate spatial and temporal information through gating？ When the gating values are different, which py file in the project can be found the differencing and...

luchen828

test_rgb.sh cannot work. And get an error:RuntimeError: shape '[0, 8, 64, 28, 28]' is invalid for input of size 50176

1

Thanks for your beautiful work. I trained the .sh file `python main.py something-v1 RGB --arch BNInception \ --num_segments 8 --consensus_type avg \ --batch-size 16 --iter_size 2 --dropout 0.5 \ --lr...

SceneRec

Exact Configuration for reproducing results on Diving48

39

Hi, I would like to achieve the performance you mentioned in the paper (~40%). I am training the model with the following configuration which after 15 epochs gave me 18.65%...

avijit9

How many GPUs are used when you train the models here? I have 4 gpus. How can I set the learning rate here ?

1

shuyuandeqipa

How does the batch_size parameter influence the accuracy

3

Hi, I try to train the model on my computer on Diving48 dataset. But if I set the batch_size 16, the training program will be out of my GPU memory....

zyy-student

Confused with the codes using grads clipping and accumulation simultaneously

1

Take args.iter_size==2 for example, I think the clipped and accumulated grads of your codes are clip(clip(grads1)+grads2), not clip(grads1+grads2), which makes more sense for me. I haven't run the code yet,...

0HaNC

t-sne

5

In the paper, which layer of features is used in Figure 5 to make t-sne

fuchao01