kinetics-i3d
kinetics-i3d copied to clipboard
deepmind
Convolutional neural network model for video classification trained on the Kinetics dataset.
https://github.com/hassony2/kinetics_i3d_pytorch/blob/master/model/model_rgb.pth
Can the model handle not square input of the video? Or does it need to be 224x224? I plan to fine-tune it on another dataset so will be removing the...
Hi, Is there model weight file that pretrained with Imagenet +Kinetics 400 ? I'm looking for .pt or pth files and if there 'rgb, flow' file would be perfect. If...
Can you supply a rough estimate of the runtime of such a model on a certain edge device- Single prediction case: ROM/RAM/Time in milliseconds? Or for the machine it trained...
Hello! I trained I3D model on my own dataset, 2 classes, each about 50 videos, the two classes are similar, like open the door/ close the door, after 40 epochs,...
Hi, I wonder why you only release checkpoint on Kinetics-600 trained from scratch but not from ImageNet pre-trained parameters. In the paper, performance is better with ImageNet pre-training on Kinetics-400...
I'm training this model on my own dataset. I trained it successfully on the RGB stream of the data. Now, I"m trying got do that on the optical flow stream....
How to load this pre-trained model without including the top layer so that is could use it for Transfer Learning? I was unable to find it here. https://tfhub.dev/deepmind/i3d-kinetics-600/1 Please help
I tried to use the DualTVL1OpticalFlow_create from opencv but it is not available at the latest version of cv2. Then, I tried to import cv2.optflow.DualTVL1OpticalFlow and, despite I can do...
