File:2016 DeepCompressionCompressingDeepN Fig1.png

Size of this preview: 800 × 280 pixels. Other resolution: 921 × 322 pixels.

Original file ‎(921 × 322 pixels, file size: 74 KB, MIME type: image/png)

Summary

Figure 1: The three stage compression pipeline: pruning, quantization and Huffman coding. Pruning reduces the number of weights by 10×, while quantization further improves the compression rate: between 27× and 31×. Huffman coding gives more compression: between 35× and 49×. The compression rate already included the meta-data for sparse representation. The compression scheme doesn’t incur any accuracy loss. In: Han et al. (2016)

Click on a date/time to view the file as it appeared at that time.

	Date/Time	Thumbnail	Dimensions	User	Comment
current	16:50, 16 December 2018		921 × 322 (74 KB)	Omoreira (talk \| contribs)	Figure 1: The three stage compression pipeline: pruning, quantization and Huffman coding. Pruning reduces the number of...

You cannot overwrite this file.

The following 2 pages use this file:

This file contains additional information, probably added from the digital camera or scanner used to create or digitize it.

If the file has been modified from its original state, some details may not fully reflect the modified file.

Software used	Shutter