Inception v4

ID	inception_v4
LR	0.045
Dropout	0.2
Crop Pct	0.875
Momentum	0.9
Image Size	299
Interpolation	bicubic

Parameters 43 Million

FLOPs 16 Billion

File Size 163.16 MB

Training Data ImageNet

Training Resources 20x NVIDIA Kepler GPUs

Training Time

Training Techniques	RMSProp, Weight Decay, Label Smoothing
Architecture	Average Pooling, Dropout, Inception-A, Inception-B, Inception-C, Reduction-A, Reduction-B, Softmax
ID	inception_v4
LR	0.045
Dropout	0.2
Crop Pct	0.875
Momentum	0.9
Image Size	299
Interpolation	bicubic
SHOW MORE
SHOW LESS

README.md

Summary

Inception-v4 is a convolutional neural network architecture that builds on previous iterations of the Inception family by simplifying the architecture and using more inception modules than Inception-v3.

How do I load this model?

To load a pretrained model:

import timm
m = timm.create_model('inception_v4', pretrained=True)
m.eval()

Replace the model name with the variant you want to use, e.g. inception_v4. You can find the IDs in the model summaries at the top of this page.

How do I train this model?

You can follow the timm recipe scripts for training a new model afresh.

Citation

@misc{szegedy2016inceptionv4,
      title={Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning}, 
      author={Christian Szegedy and Sergey Ioffe and Vincent Vanhoucke and Alex Alemi},
      year={2016},
      eprint={1602.07261},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Results

Image Classification on ImageNet

Image Classification

BENCHMARK	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
ImageNet	inception_v4	Top 1 Accuracy	1.01%	# 327
		Top 5 Accuracy	16.85%	# 327