Skip to main content

Explore our questions

2 votes
2 answers
293 views

Dropout causes too much noise for network to train

0 votes
0 answers
7 views

Synthesising Images from Features

0 votes
1 answer
27 views

How to get Complexity per Layer, Sequential Operations and Maximum Path Length in CNN architecture?

3 votes
1 answer
111 views

How should continuous action/gesture recognition be performed differently than isolated action recognition

7 votes
4 answers
5k views

Are fully connected layers necessary in a CNN?

0 votes
0 answers
6 views

How to do object detection for 1 object in the image, with 3 possible classes (in a custom dataset)

2 votes
2 answers
3k views

What is the exact output of the Inception ResNet V2's feature extraction layer?

0 votes
1 answer
80 views

What underlying network is typically meant with ResNET?

1 vote
1 answer
68 views

Is there a state-of-the-art deep learning paper that uses center point regression instead of bounding box regression, for object tracking?

-1 votes
0 answers
17 views

Can we use 3D convolution to do 2D convolution on list of input?

6 votes
1 answer
391 views

Which neural networks are suitable for visual place recognition?

1 vote
1 answer
217 views

Is a convolutional layer capable of converting, for example, a binary image into an RGBA image?

0 votes
1 answer
2k views

Training a model to identify certain differences between images?

1 vote
1 answer
230 views

How to handle extremely 'long' images?

Browse more Questions