• Automation framework: CK
  
• Development repository: ck-caffe2
  
• Source: GitHub
  
• Tags: caffe2,weights,caffemodel2,bvlc,alexnet,channel-stable
  
• Support for host OS: linux, windows
  
• Support for target OS: linux, windows
  
• Version: trunk
  
• Software detection plugin: model.caffe2
  
• How to get the stable version from this portal via the CK client:
  
  pip install cbench
  cb download package:caffemodel2-bvlc-alexnet --version=1.0.0 --all
  ck install package:caffemodel2-bvlc-alexnet
  ck help package
  
• How to get the development version:
  
  pip install ck
  ck pull repo:ck-caffe2
  ck install package:caffemodel2-bvlc-alexnet
  ck help package
  
• Useful CK automation actions (CLI with the Python CK API and JSON IO):
  
  ck show env
  ck find env:{ID from above}
  ck virtual env:{ID from above}
  
• CLI and Python API: module:package
  

name: BVLC AlexNet Model caffemodel: bvlc_alexnet.caffemodel caffemodel_url: http://dl.caffe.berkeleyvision.org/bvlc_alexnet.caffemodel license: unrestricted sha1: 9116a64c0fbe4459d18f4bb6b56d647b63920377 caffe_commit: 709dc15af4a06bebda027c1eb2b3f3e3375d5077

This model is a replication of the model described in the AlexNet publication.

Differences: - not training with the relighting data-augmentation; - initializing non-zero biases to 0.1 instead of 1 (found necessary for training, as initialization to 1 gave flat loss).

The bundled model is the iteration 360,000 snapshot. The best validation performance during training was iteration 358,000 with validation accuracy 57.258% and loss 1.83948. This model obtains a top-1 accuracy 57.1% and a top-5 accuracy 80.2% on the validation set, using just the center crop. (Using the average of 10 crops, (4 + 1 center) * 2 mirror, should obtain a bit higher accuracy.)

This model was trained by Evan Shelhamer @shelhamer

License

This model is released for unrestricted use.

• 1.0.0 (2019-10-08)

• .cm/desc.json (3 bytes)
• .cm/info.json (453 bytes)
• .cm/meta.json (2183 bytes)
• deploy.prototxt (3596 bytes)
• predict_net.pb (1395 bytes)
• readme.md (1141 bytes)
• solver.prototxt (298 bytes)
• train_val.prototxt (5464 bytes)