Improving Inception and Image Classification in TensorFlow
Very interesting CNN architecture (e.g.: the inception-style convolutional layers is promising and efficient in terms of reducing the number of parameters).
- from
- Education
- added
- 2026-10-10
- likes
- 0
similar
-
Going Deeper with Convolutions cv-foundation.org
GoogLeNet: Appearance of "Inception" layers/modules, the idea is of parallelizing conv layers into many mini-conv of different size with "same" padding, concatenated on depth.
-
Inceptionism: Going Deeper into Neural Networks@Google Research googleresearch.blogspot.kr
-
Very Deep Convolutional Networks for Large-Scale Image Recognition arxiv.org
Interesting idea of stacking multiple 3x3 conv+ReLU before pooling for a bigger filter size with just a few parameters. There is also a nice table for "ConvNet Configuration".
-
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning arxiv.org
For improving GoogLeNet with residual connections.
-
Core Concepts of Deep Learning devblogs.nvidia.com
-
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour research.fb.com
Incredibly fast distributed training of a CNN.
Education › Posts and Articles: “Very interesting CNN architecture (e.g.: the inception-style convolutional layers is promising and efficient in terms of reducing the number of parameters).”