google-deepmind / google-deepmind/kinetics-i3d
The problem of receptive field in I3D paper
Open
- Dominant language
- Python
- Stars
- 1.8k
- Forks
- 467
- PR merge metrics
- No merged PRs in 30d
Description
I tried to calculate the receptive field in Figure 3 of the paper, but the calculated receptive field was different from the last two. Could you please tell me how to calculate it
Contributor guide
Research direction
Start with Figure 3 and the receptive-field calculation described in the I3D paper, comparing each listed convolution and pooling layer. Done means providing an explanation that reconciles the calculated receptive field with the final two values shown in the figure.
Written by the indexing model from the issue text.
Assessment
- Domain
- computer-vision, machine-learning
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100