Skip to content

Instantly share code, notes, and snippets.

@kevinlin311tw

kevinlin311tw/deploy.prototxt

Created March 25, 2015 07:19
Show Gist options
  • Save kevinlin311tw/a0a36e2b4d6ab9b09201 to your computer and use it in GitHub Desktop.
Save kevinlin311tw/a0a36e2b4d6ab9b09201 to your computer and use it in GitHub Desktop.
Download ZIP
BVLC AlexNet Model
Raw
readme.md
name caffemodel caffemodel_url license sha1 caffe_commit
BVLC AlexNet Model
bvlc_alexnet.caffemodel
non-commercial
9116a64c0fbe4459d18f4bb6b56d647b63920377
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.)

License

The data used to train this model comes from the ImageNet project, which distributes its database to researchers who agree to a following term of access: "Researcher shall use the Database only for non-commercial research and educational purposes." Accordingly, this model is distributed under a non-commercial license.

Raw
readme.md~
---
name: BVLC AlexNet Model
caffemodel: bvlc_alexnet.caffemodel
caffemodel_url: http://dl.caffe.berkeleyvision.org/bvlc_alexnet.caffemodel
license: non-commercial
sha1: 9116a64c0fbe4459d18f4bb6b56d647b63920377
caffe_commit: 709dc15af4a06bebda027c1eb2b3f3e3375d5077
gist_id: 223a7da39051d8c42345
---
This model is a replication of the model described in the [AlexNet](http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks) 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.)
## License
The data used to train this model comes from the ImageNet project, which distributes its database to researchers who agree to a following term of access:
"Researcher shall use the Database only for non-commercial research and educational purposes."
Accordingly, this model is distributed under a non-commercial license.
Raw
deploy.prototxt
name: "AlexNet"
input: "data"
input_dim: 10
input_dim: 3
input_dim: 227
input_dim: 227
layers {
name: "conv1"
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
}
bottom: "data"
top: "conv1"
}
layers {
name: "relu1"
type: RELU
bottom: "conv1"
top: "conv1"
}
layers {
name: "norm1"
type: LRN
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
bottom: "conv1"
top: "norm1"
}
layers {
name: "pool1"
type: POOLING
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
bottom: "norm1"
top: "pool1"
}
layers {
name: "conv2"
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
group: 2
}
bottom: "pool1"
top: "conv2"
}
layers {
name: "relu2"
type: RELU
bottom: "conv2"
top: "conv2"
}
layers {
name: "norm2"
type: LRN
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
bottom: "conv2"
top: "norm2"
}
layers {
name: "pool2"
type: POOLING
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
bottom: "norm2"
top: "pool2"
}
layers {
name: "conv3"
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
}
bottom: "pool2"
top: "conv3"
}
layers {
name: "relu3"
type: RELU
bottom: "conv3"
top: "conv3"
}
layers {
name: "conv4"
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 2
}
bottom: "conv3"
top: "conv4"
}
layers {
name: "relu4"
type: RELU
bottom: "conv4"
top: "conv4"
}
layers {
name: "conv5"
type: CONVOLUTION
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
group: 2
}
bottom: "conv4"
top: "conv5"
}
layers {
name: "relu5"
type: RELU
bottom: "conv5"
top: "conv5"
}
layers {
name: "pool5"
type: POOLING
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
bottom: "conv5"
top: "pool5"
}
layers {
name: "fc6"
type: INNER_PRODUCT
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 4096
}
bottom: "pool5"
top: "fc6"
}
layers {
name: "relu6"
type: RELU
bottom: "fc6"
top: "fc6"
}
layers {
name: "drop6"
type: DROPOUT
dropout_param {
dropout_ratio: 0.5
}
bottom: "fc6"
top: "fc6"
}
layers {
name: "fc7"
type: INNER_PRODUCT
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 4096
}
bottom: "fc6"
top: "fc7"
}
layers {
name: "relu7"
type: RELU
bottom: "fc7"
top: "fc7"
}
layers {
name: "drop7"
type: DROPOUT
dropout_param {
dropout_ratio: 0.5
}
bottom: "fc7"
top: "fc7"
}
layers {
name: "fc8"
type: INNER_PRODUCT
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 1000
}
bottom: "fc7"
top: "fc8"
}
layers {
name: "prob"
type: SOFTMAX
bottom: "fc8"
top: "prob"
}
Raw
solver.prototxt
net: "models/bvlc_alexnet/train_val.prototxt"
test_iter: 1000
test_interval: 1000
base_lr: 0.01
lr_policy: "step"
gamma: 0.1
stepsize: 100000
display: 20
max_iter: 450000
momentum: 0.9
weight_decay: 0.0005
snapshot: 10000
snapshot_prefix: "models/bvlc_alexnet/caffe_alexnet_train"
solver_mode: GPU
Raw
train_val.prototxt
name: "AlexNet"
layers {
name: "data"
type: DATA
top: "data"
top: "label"
data_param {
source: "examples/imagenet/ilsvrc12_train_lmdb"
backend: LMDB
batch_size: 256
}
transform_param {
crop_size: 227
mean_file: "data/ilsvrc12/imagenet_mean.binaryproto"
mirror: true
}
include: { phase: TRAIN }
}
layers {
name: "data"
type: DATA
top: "data"
top: "label"
data_param {
source: "examples/imagenet/ilsvrc12_val_lmdb"
backend: LMDB
batch_size: 50
}
transform_param {
crop_size: 227
mean_file: "data/ilsvrc12/imagenet_mean.binaryproto"
mirror: false
}
include: { phase: TEST }
}
layers {
name: "conv1"
type: CONVOLUTION
bottom: "data"
top: "conv1"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "relu1"
type: RELU
bottom: "conv1"
top: "conv1"
}
layers {
name: "norm1"
type: LRN
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layers {
name: "pool1"
type: POOLING
bottom: "norm1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layers {
name: "conv2"
type: CONVOLUTION
bottom: "pool1"
top: "conv2"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layers {
name: "relu2"
type: RELU
bottom: "conv2"
top: "conv2"
}
layers {
name: "norm2"
type: LRN
bottom: "conv2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layers {
name: "pool2"
type: POOLING
bottom: "norm2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layers {
name: "conv3"
type: CONVOLUTION
bottom: "pool2"
top: "conv3"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "relu3"
type: RELU
bottom: "conv3"
top: "conv3"
}
layers {
name: "conv4"
type: CONVOLUTION
bottom: "conv3"
top: "conv4"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layers {
name: "relu4"
type: RELU
bottom: "conv4"
top: "conv4"
}
layers {
name: "conv5"
type: CONVOLUTION
bottom: "conv4"
top: "conv5"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layers {
name: "relu5"
type: RELU
bottom: "conv5"
top: "conv5"
}
layers {
name: "pool5"
type: POOLING
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layers {
name: "fc6"
type: INNER_PRODUCT
bottom: "pool5"
top: "fc6"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layers {
name: "relu6"
type: RELU
bottom: "fc6"
top: "fc6"
}
layers {
name: "drop6"
type: DROPOUT
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layers {
name: "fc7"
type: INNER_PRODUCT
bottom: "fc6"
top: "fc7"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layers {
name: "relu7"
type: RELU
bottom: "fc7"
top: "fc7"
}
layers {
name: "drop7"
type: DROPOUT
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layers {
name: "fc8"
type: INNER_PRODUCT
bottom: "fc7"
top: "fc8"
blobs_lr: 1
blobs_lr: 2
weight_decay: 1
weight_decay: 0
inner_product_param {
num_output: 1000
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layers {
name: "accuracy"
type: ACCURACY
bottom: "fc8"
bottom: "label"
top: "accuracy"
include: { phase: TEST }
}
layers {
name: "loss"
type: SOFTMAX_LOSS
bottom: "fc8"
bottom: "label"
top: "loss"
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment