둘러보기로 가기 검색하러 가기



  1. The first version entered the field in 2014, and as the name "GoogleNet" suggests, it was developed by a team at Google.[1]
  2. The GoogleNet Architecture is 22 layers deep, with 27 pooling layers included.[1]
  3. GoogleNet is trained using distributed machine learning systems with a modest amount of model and data parallelism.[1]
  4. From the name “GoogLeNet”, we’ve already known that it is from Google.[2]
  5. To classify new images using GoogLeNet, use classify .[3]
  6. You can retrain a GoogLeNet network to perform a new task using transfer learning.[3]
  7. You can also create a trained GoogLeNet network from inside MATLAB by installing the Deep Learning Toolbox Model for GoogLeNet Network support package.[4]
  8. If the Deep Learning Toolbox Model for GoogLeNet Network support package is not installed, then the function provides a link to the required support package in the Add-On Explorer.[4]
  9. You can create an untrained GoogLeNet network from inside MATLAB by importing a trained GoogLeNet network into the Deep Network Designer App and selecting Export > Generate Code.[4]
  10. The exported code will generate an untrained network with the network architecture of GoogLeNet.[4]
  11. GoogLeNet introduces several new concepts.[5]
  12. Another key network that we already seen on quite some occasions in this lecture is GoogleNet.[5]
  13. One particular incarnation of this architecture, GoogLeNet, a 22 layers deep network, was used to assess its quality in the context of object detection and classification.[6]
  14. The paper proposes a new type of architecture – GoogLeNet or Inception v1.[7]
  15. Now that you have understood the architecture of GoogLeNet and the intuition behind it, it’s time to power up Python and implement our learnings using Keras![7]
  16. The GoogLeNet builds on the idea that most of the activations in a deep network are either unnecessary(value of zero) or redundant because of correlations between them.[8]
  17. So GoogLeNet devised a module called inception module that approximates a sparse CNN with a normal dense construction(shown in the figure).[8]
  18. Let us take the first inception module of GoogLeNet as an example which has 192 channels as input.[8]
  19. Use of a large network width and depth allows GoogLeNet to remove the FC layers without affecting the accuracy.[8]
  20. The most straightforward way to improve performance on deep learning is to use more layers and more data, googleNet use 9 inception modules.[9]
  21. Bellow we present 2 inception layers on cascade from the original googleNet.[9]
  22. 7.4.2, GoogLeNet uses a stack of a total of 9 inception blocks and global average pooling to generate its estimates.[10]
  23. We can now implement GoogLeNet piece by piece.[10]
  24. The GoogLeNet model is computationally complex, so it is not as easy to modify the number of channels as in VGG.[10]
  25. Moreover, two popular GoogLeNet architecture versions of CNN, namely, Inception-v1 and Inception-v3, were used.[11]
  26. In GoogLeNet architecture, there is a method called global average pooling is used at the end of the network.[12]
  27. GoogLeNet was the winner at ILSRVRC 2014 taking 1st place in both classification an detection task.[12]
  28. The design of this initial Inception Module is known commonly as GoogLeNet, or Inception v1.[13]
  29. GoogLeNet uses 9 inception module and it eliminates all fully connected layers using average pooling to go from 7x7x1024 to 1x1x1024.[14]
  30. from_pretrained ( "googlenet" ) model .[15]