FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

Overhaul layer catalogue documentation. · Charrin/CaffeOnACL@bae0607 · GitHub

  1. Charrin
  2. CaffeOnACL

Repository navigation

Commit bae0607

Browse files
williford
committed
Overhaul layer catalogue documentation.
Create scripts/split_caffe_proto.py file for splitting up the caffe.proto file, so that parts of the file can be included from the layer help pages. Create separate pages for each layer and link each page from layers.md.
1 parent f731bc4 commit bae0607

62 files changed

Lines changed: 1573 additions & 476 deletions

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎docs/tutorial/layers.md‎

Lines changed: 86 additions & 476 deletions
Large diffs are not rendered by default.

‎docs/tutorial/layers/absval.md‎

Lines changed: 22 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,22 @@
1+
---
2+
title: Absolute Value Layer
3+
---
4+
5+
# Absolute Value Layer
6+
7+
* Layer type: `AbsVal`
8+
* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1AbsValLayer.html)
9+
* Header: [`./include/caffe/layers/absval_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/absval_layer.hpp)
10+
* CPU implementation: [`./src/caffe/layers/absval_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/absval_layer.cpp)
11+
* CUDA GPU implementation: [`./src/caffe/layers/absval_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/absval_layer.cu)
12+
13+
* Sample
14+
15+
layer {
16+
name: "layer"
17+
bottom: "in"
18+
top: "out"
19+
type: "AbsVal"
20+
}
21+
22+
The `AbsVal` layer computes the output as abs(x) for each input element x.

‎docs/tutorial/layers/accuracy.md‎

Lines changed: 21 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,21 @@
1+
---
2+
title: Accuracy and Top-k
3+
---
4+
5+
# Accuracy and Top-k
6+
7+
`Accuracy` scores the output as the accuracy of output with respect to target -- it is not actually a loss and has no backward step.
8+
9+
* Layer type: `Accuracy`
10+
* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1AccuracyLayer.html)
11+
* Header: [`./include/caffe/layers/accuracy_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/accuracy_layer.hpp)
12+
* CPU implementation: [`./src/caffe/layers/accuracy_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/accuracy_layer.cpp)
13+
* CUDA GPU implementation: [`./src/caffe/layers/accuracy_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/accuracy_layer.cu)
14+
15+
## Parameters
16+
* Parameters (`AccuracyParameter accuracy_param`)
17+
* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
18+
19+
{% highlight Protobuf %}
20+
{% include proto/AccuracyParameter.txt %}
21+
{% endhighlight %}

‎docs/tutorial/layers/argmax.md‎

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
---
2+
title: ArgMax Layer
3+
---
4+
5+
# ArgMax Layer
6+
7+
* Layer type: `ArgMax`
8+
* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1ArgMaxLayer.html)
9+
* Header: [`./include/caffe/layers/argmax_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/argmax_layer.hpp)
10+
* CPU implementation: [`./src/caffe/layers/argmax_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/argmax_layer.cpp)
11+
* CUDA GPU implementation: [`./src/caffe/layers/argmax_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/argmax_layer.cu)
12+
13+
## Parameters
14+
* Parameters (`ArgMaxParameter argmax_param`)
15+
* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
16+
17+
{% highlight Protobuf %}
18+
{% include proto/ArgMaxParameter.txt %}
19+
{% endhighlight %}

‎docs/tutorial/layers/batchnorm.md‎

Lines changed: 20 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,20 @@
1+
---
2+
title: Batch Norm Layer
3+
---
4+
5+
# Batch Norm Layer
6+
7+
* Layer type: `BatchNorm`
8+
* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1BatchNormLayer.html)
9+
* Header: [`./include/caffe/layers/batch_norm_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/batch_norm_layer.hpp)
10+
* CPU implementation: [`./src/caffe/layers/batch_norm_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/batch_norm_layer.cpp)
11+
* CUDA GPU implementation: [`./src/caffe/layers/batch_norm_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/batch_norm_layer.cu)
12+
13+
## Parameters
14+
15+
* Parameters (`BatchNormParameter batch_norm_param`)
16+
* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto):
17+
18+
{% highlight Protobuf %}
19+
{% include proto/BatchNormParameter.txt %}
20+
{% endhighlight %}

‎docs/tutorial/layers/batchreindex.md‎

Lines changed: 16 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,16 @@
1+
---
2+
title: Batch Reindex Layer
3+
---
4+
5+
# Batch Reindex Layer
6+
7+
* Layer type: `BatchReindex`
8+
* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1BatchReindexLayer.html)
9+
* Header: [`./include/caffe/layers/batch_reindex_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/batch_reindex_layer.hpp)
10+
* CPU implementation: [`./src/caffe/layers/batch_reindex_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/batch_reindex_layer.cpp)
11+
* CUDA GPU implementation: [`./src/caffe/layers/batch_reindex_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/batch_reindex_layer.cu)
12+
13+
14+
## Parameters
15+
16+
No parameters.

‎docs/tutorial/layers/bias.md‎

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
---
2+
title: Bias Layer
3+
---
4+
5+
# Bias Layer
6+
7+
* Layer type: `Bias`
8+
* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1BiasLayer.html)
9+
* Header: [`./include/caffe/layers/bias_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/bias_layer.hpp)
10+
* CPU implementation: [`./src/caffe/layers/bias_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/bias_layer.cpp)
11+
* CUDA GPU implementation: [`./src/caffe/layers/bias_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/bias_layer.cu)
12+
13+
## Parameters
14+
* Parameters (`BiasParameter bias_param`)
15+
* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
16+
17+
{% highlight Protobuf %}
18+
{% include proto/BiasParameter.txt %}
19+
{% endhighlight %}

‎docs/tutorial/layers/bnll.md‎

Lines changed: 25 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,25 @@
1+
---
2+
title: BNLL Layer
3+
---
4+
5+
# BNLL Layer
6+
7+
* Layer type: `BNLL`
8+
* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1BNLLLayer.html)
9+
* Header: [`./include/caffe/layers/bnll_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/bnll_layer.hpp)
10+
* CPU implementation: [`./src/caffe/layers/bnll_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/bnll_layer.cpp)
11+
* CUDA GPU implementation: [`./src/caffe/layers/bnll_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/bnll_layer.cu)
12+
13+
The `BNLL` (binomial normal log likelihood) layer computes the output as log(1 + exp(x)) for each input element x.
14+
15+
## Parameters
16+
No parameters.
17+
18+
## Sample
19+
20+
layer {
21+
name: "layer"
22+
bottom: "in"
23+
top: "out"
24+
type: BNLL
25+
}

‎docs/tutorial/layers/concat.md‎

Lines changed: 40 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,40 @@
1+
---
2+
title: Concat Layer
3+
---
4+
5+
# Concat Layer
6+
7+
* Layer type: `Concat`
8+
* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1ConcatLayer.html)
9+
* Header: [`./include/caffe/layers/concat_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/concat_layer.hpp)
10+
* CPU implementation: [`./src/caffe/layers/concat_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/concat_layer.cpp)
11+
* CUDA GPU implementation: [`./src/caffe/layers/concat_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/concat_layer.cu)
12+
* Input
13+
- `n_i * c_i * h * w` for each input blob i from 1 to K.
14+
* Output
15+
- if `axis = 0`: `(n_1 + n_2 + ... + n_K) * c_1 * h * w`, and all input `c_i` should be the same.
16+
- if `axis = 1`: `n_1 * (c_1 + c_2 + ... + c_K) * h * w`, and all input `n_i` should be the same.
17+
* Sample
18+
19+
layer {
20+
name: "concat"
21+
bottom: "in1"
22+
bottom: "in2"
23+
top: "out"
24+
type: "Concat"
25+
concat_param {
26+
axis: 1
27+
}
28+
}
29+
30+
The `Concat` layer is a utility layer that concatenates its multiple input blobs to one single output blob.
31+
32+
## Parameters
33+
* Parameters (`ConcatParameter concat_param`)
34+
- Optional
35+
- `axis` [default 1]: 0 for concatenation along num and 1 for channels.
36+
* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
37+
38+
{% highlight Protobuf %}
39+
{% include proto/ConcatParameter.txt %}
40+
{% endhighlight %}

‎docs/tutorial/layers/contrastiveloss.md‎

Lines changed: 20 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,20 @@
1+
---
2+
title: Contrastive Loss Layer
3+
---
4+
5+
# Contrastive Loss Layer
6+
7+
* Layer type: `ContrastiveLoss`
8+
* [Doxygen Documentation](http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1ContrastiveLossLayer.html)
9+
* Header: [`./include/caffe/layers/contrastive_loss_layer.hpp`](https://github.com/BVLC/caffe/blob/master/include/caffe/layers/contrastive_loss_layer.hpp)
10+
* CPU implementation: [`./src/caffe/layers/contrastive_loss_layer.cpp`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/contrastive_loss_layer.cpp)
11+
* CUDA GPU implementation: [`./src/caffe/layers/contrastive_loss_layer.cu`](https://github.com/BVLC/caffe/blob/master/src/caffe/layers/contrastive_loss_layer.cu)
12+
13+
## Parameters
14+
15+
* Parameters (`ContrastiveLossParameter contrastive_loss_param`)
16+
* From [`./src/caffe/proto/caffe.proto`](https://github.com/BVLC/caffe/blob/master/src/caffe/proto/caffe.proto)):
17+
18+
{% highlight Protobuf %}
19+
{% include proto/ContrastiveLossParameter.txt %}
20+
{% endhighlight %}

0 commit comments

Comments
 (0)
Back | FazBrowse Home | New Git URL