-
Notifications
You must be signed in to change notification settings - Fork 18.7k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Implement SpatialPyramidPoolingLayer with the Split, Pooling, Flatten & Concat layers #560
Closed
Changes from all commits
Commits
Show all changes
12 commits
Select commit
Hold shift + click to select a range
5ea99c3
Composite SpatialPyramidPooling with Split, Pooling, Flatten & Concat
kloudkl c0bbc40
Pooling layer allows float heights and widths for kernels and strides
kloudkl 0d5a65d
Support non-square float kernel and stride in spatial pyramid pooling
kloudkl 9498df0
Add more spatial bins to test the SpatialPyramidPoolingLayer
kloudkl d5006af
Test the pooling layers with float kernels and strides
kloudkl 03a6a00
Test the spatial pyramid pooling layer with float kernels and strides
kloudkl a1ec93e
Simplify the verbose assignment & comparison in pooling layer tests
kloudkl 8a81bfd
Improve computing the pooled height and width in the pooling layer
kloudkl 652d2c8
Avoid the verbose assignment & comparison in spatial pooling layer tests
kloudkl 863fa57
Add example network definitions using the spatial pyramid pooling layer
kloudkl 2d0bb1e
Compute more accurate average pooling sizes in the PoolingLayer
kloudkl d7d6662
Add spatial pyramid pooling in the directory name of examples/voc2012
kloudkl File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
8 changes: 8 additions & 0 deletions
8
examples/voc2012-spatial-pyramid-pooling/finetune_voc2012_spp.sh
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,8 @@ | ||
| #!/usr/bin/env sh | ||
|
|
||
| TOOLS=../../build/tools | ||
| MODEL=../imagenet/caffe_reference_imagenet_model | ||
|
|
||
| GLOG_logtostderr=1 $TOOLS/finetune_net.bin voc2012_finetune_spatial_pyramid_pooling_solver.prototxt $MODEL | ||
|
|
||
| echo "Done." |
18 changes: 18 additions & 0 deletions
18
.../voc2012-spatial-pyramid-pooling/voc2012_finetune_spatial_pyramid_pooling_solver.prototxt
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,18 @@ | ||
| # 5717 images | ||
| train_net: "voc2012_finetune_spatial_pyramid_pooling_train.prototxt" | ||
| # 5823 images, batch_size 100 | ||
| test_net: "voc2012_finetune_spatial_pyramid_pooling_test.prototxt" | ||
| test_iter: 59 | ||
| test_interval: 500 | ||
| base_lr: 0.0001 | ||
| lr_policy: "step" | ||
| gamma: 0.1 | ||
| stepsize: 20000 | ||
| display: 20 | ||
| max_iter: 100000 | ||
| momentum: 0.9 | ||
| weight_decay: 0.0005 | ||
| snapshot: 500 | ||
| snapshot_prefix: "voc2012_finetune_spatial_pyramid_pooling_train" | ||
| # solver mode: CPU or GPU | ||
| solver_mode: CPU |
328 changes: 328 additions & 0 deletions
328
...es/voc2012-spatial-pyramid-pooling/voc2012_finetune_spatial_pyramid_pooling_test.prototxt
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,328 @@ | ||
| name: "ImagenetSpatialPyramidPoolingNet" | ||
| layers { | ||
| name: "data" | ||
| type: DATA | ||
| top: "data" | ||
| top: "label" | ||
| data_param { | ||
| source: "voc2012_test.leveldb" | ||
| mean_file: "../../data/ilsvrc12/imagenet_mean.binaryproto" | ||
| batch_size: 100 | ||
| crop_size: 227 | ||
| mirror: true | ||
| } | ||
| } | ||
| 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: "pool1" | ||
| type: POOLING | ||
| bottom: "conv1" | ||
| top: "pool1" | ||
| pooling_param { | ||
| pool: MAX | ||
| kernel_size: 3 | ||
| stride: 2 | ||
| } | ||
| } | ||
| layers { | ||
| name: "norm1" | ||
| type: LRN | ||
| bottom: "pool1" | ||
| top: "norm1" | ||
| lrn_param { | ||
| local_size: 5 | ||
| alpha: 0.0001 | ||
| beta: 0.75 | ||
| } | ||
| } | ||
| layers { | ||
| name: "conv2" | ||
| type: CONVOLUTION | ||
| bottom: "norm1" | ||
| 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: 1 | ||
| } | ||
| } | ||
| } | ||
| layers { | ||
| name: "relu2" | ||
| type: RELU | ||
| bottom: "conv2" | ||
| top: "conv2" | ||
| } | ||
| layers { | ||
| name: "pool2" | ||
| type: POOLING | ||
| bottom: "conv2" | ||
| top: "pool2" | ||
| pooling_param { | ||
| pool: MAX | ||
| kernel_size: 3 | ||
| stride: 2 | ||
| } | ||
| } | ||
| layers { | ||
| name: "norm2" | ||
| type: LRN | ||
| bottom: "pool2" | ||
| top: "norm2" | ||
| lrn_param { | ||
| local_size: 5 | ||
| alpha: 0.0001 | ||
| beta: 0.75 | ||
| } | ||
| } | ||
| layers { | ||
| name: "conv3" | ||
| type: CONVOLUTION | ||
| bottom: "norm2" | ||
| 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: 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: 1 | ||
| } | ||
| } | ||
| } | ||
| layers { | ||
| name: "relu5" | ||
| type: RELU | ||
| bottom: "conv5" | ||
| top: "conv5" | ||
| } | ||
| layers { | ||
| name: "spatial_pyramid_pooling" | ||
| type: SPATIAL_PYRAMID_POOLING | ||
| bottom: "conv5" | ||
| top: "spatial_pyramid_pooling" | ||
| spatial_pyramid_pooling_param { | ||
| pool: MAX | ||
| spatial_bin: 1 | ||
| spatial_bin: 2 | ||
| spatial_bin: 3 | ||
| spatial_bin: 6 | ||
| scale: 1 | ||
| } | ||
| } | ||
| layers { | ||
| name: "ip6" | ||
| type: INNER_PRODUCT | ||
| bottom: "spatial_pyramid_pooling" | ||
| top: "ip6" | ||
| 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: 1 | ||
| } | ||
| } | ||
| } | ||
| layers { | ||
| name: "relu6" | ||
| type: RELU | ||
| bottom: "ip6" | ||
| top: "ip6" | ||
| } | ||
| layers { | ||
| name: "drop6" | ||
| type: DROPOUT | ||
| bottom: "ip6" | ||
| top: "ip6" | ||
| dropout_param { | ||
| dropout_ratio: 0.5 | ||
| } | ||
| } | ||
| layers { | ||
| name: "fc7" | ||
| type: INNER_PRODUCT | ||
| bottom: "ip6" | ||
| 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: 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_voc2012" | ||
| type: INNER_PRODUCT | ||
| bottom: "fc7" | ||
| top: "fc8_voc2012" | ||
| blobs_lr: 10 | ||
| blobs_lr: 20 | ||
| weight_decay: 1 | ||
| weight_decay: 0 | ||
| inner_product_param { | ||
| num_output: 20 | ||
| weight_filler { | ||
| type: "gaussian" | ||
| std: 0.01 | ||
| } | ||
| bias_filler { | ||
| type: "constant" | ||
| value: 0 | ||
| } | ||
| } | ||
| } | ||
| layers { | ||
| name: "accuracy" | ||
| type: ACCURACY | ||
| bottom: "fc8_voc2012" | ||
| bottom: "label" | ||
| top: "accuracy" | ||
| } | ||
| layers { | ||
| name: "prob" | ||
| type: SOFTMAX_LOSS | ||
| bottom: "fc8_voc2012" | ||
| bottom: "label" | ||
| top: "loss" | ||
| } | ||
|
|
||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I am wondering that, the voc2012 classification has multiple labels, how to do leveldb?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
HDF5DataLayer