MyCaffe
1.12.2.41
Deep learning software for Windows C# programmers.
|
Specifies the parameters for the DataSequenceLayer. More...
Public Member Functions | |
DataSequenceParameter () | |
Constructor for the parameter. More... | |
override object | Load (System.IO.BinaryReader br, bool bNewInstance=true) |
Load the parameter from a binary reader. More... | |
override void | Copy (LayerParameterBase src) |
Copy on parameter to another. More... | |
override LayerParameterBase | Clone () |
Creates a new copy of this instance of the parameter. More... | |
override RawProto | ToProto (string strName) |
Convert the parameter into a RawProto. More... | |
Public Member Functions inherited from MyCaffe.param.LayerParameterBase | |
LayerParameterBase () | |
Constructor for the parameter. More... | |
virtual string | PrepareRunModelInputs () |
This method gives derivative classes a chance specify model inputs required by the run model. More... | |
virtual void | PrepareRunModel (LayerParameter p) |
This method gives derivative classes a chance to prepare the layer for a run-model. More... | |
void | Save (BinaryWriter bw) |
Save this parameter to a binary writer. More... | |
abstract object | Load (BinaryReader br, bool bNewInstance=true) |
Load the parameter from a binary reader. More... | |
Public Member Functions inherited from MyCaffe.basecode.BaseParameter | |
BaseParameter () | |
Constructor for the parameter. More... | |
virtual bool | Compare (BaseParameter p) |
Compare this parameter to another parameter. More... | |
Static Public Member Functions | |
static DataSequenceParameter | FromProto (RawProto rp) |
Parses the parameter from a RawProto. More... | |
Static Public Member Functions inherited from MyCaffe.basecode.BaseParameter | |
static double | ParseDouble (string strVal) |
Parse double values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More... | |
static bool | TryParse (string strVal, out double df) |
Parse double values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More... | |
static float | ParseFloat (string strVal) |
Parse float values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More... | |
static bool | TryParse (string strVal, out float f) |
Parse doufloatble values using the US culture if the decimal separator = '.', then using the native culture, and if then lastly trying the US culture to handle prototypes containing '.' as the separator, yet parsed in a culture that does not use '.' as a decimal. More... | |
Properties | |
int | cache_size [getset] |
Specifies the cache size used for each labeled image cache, which should be at least 4 x the batch size used (default = 256). More... | |
int | k [getset] |
Specifies the 'k' number of negatively matched labled images (default = 0, maximum = 10). When specifying 0, the output is just the anchor and one alternating negatively/positive matched image. More... | |
bool | balance_matches [getset] |
Specifies to balance the matching image between negative and positive matches. This setting only applies when k=0 (default = true). More... | |
bool | output_labels [getset] |
Specifies whether or not to output the labels in an additional top output. (default = true). More... | |
int | label_count [getset] |
Specifies the number of labels in the data set, or 0 to use dynamic label discovery (requires large enough batch sizes to cover all labels within first batch) - (default = 0). More... | |
int | label_start [getset] |
Specifies the first label in the label set (default = 0). More... | |
Additional Inherited Members | |
Public Types inherited from MyCaffe.param.LayerParameterBase | |
enum | LABEL_TYPE { NONE , SINGLE , MULTIPLE , ONLY_ONE } |
Defines the label type. More... | |
Specifies the parameters for the DataSequenceLayer.
Definition at line 21 of file DataSequenceParameter.cs.
MyCaffe.param.beta.DataSequenceParameter.DataSequenceParameter | ( | ) |
Constructor for the parameter.
Definition at line 31 of file DataSequenceParameter.cs.
|
virtual |
Creates a new copy of this instance of the parameter.
Implements MyCaffe.param.LayerParameterBase.
Definition at line 148 of file DataSequenceParameter.cs.
|
virtual |
Copy on parameter to another.
src | Specifies the parameter to copy. |
Implements MyCaffe.param.LayerParameterBase.
Definition at line 133 of file DataSequenceParameter.cs.
|
static |
Parses the parameter from a RawProto.
rp | Specifies the RawProto to parse. |
Definition at line 179 of file DataSequenceParameter.cs.
override object MyCaffe.param.beta.DataSequenceParameter.Load | ( | System.IO.BinaryReader | br, |
bool | bNewInstance = true |
||
) |
Load the parameter from a binary reader.
br | Specifies the binary reader. |
bNewInstance | When true a new instance is created (the default), otherwise the existing instance is loaded from the binary reader. |
Definition at line 118 of file DataSequenceParameter.cs.
|
virtual |
Convert the parameter into a RawProto.
strName | Specifies the name to associate with the RawProto. |
Implements MyCaffe.basecode.BaseParameter.
Definition at line 160 of file DataSequenceParameter.cs.
|
getset |
Specifies to balance the matching image between negative and positive matches. This setting only applies when k=0 (default = true).
Definition at line 68 of file DataSequenceParameter.cs.
|
getset |
Specifies the cache size used for each labeled image cache, which should be at least 4 x the batch size used (default = 256).
The cache size should be higher than the maximum number of items for a given label within a batch, otherwise items within a given batch will overrite other items from the batch for a given label.
NOTE: The batch size must also be large enough to contain at least two items from each label.
Definition at line 45 of file DataSequenceParameter.cs.
|
getset |
Specifies the 'k' number of negatively matched labled images (default = 0, maximum = 10). When specifying 0, the output is just the anchor and one alternating negatively/positive matched image.
When specifying k>0, the anchor is output with a positive match and 'k' number of negative matches.
Definition at line 58 of file DataSequenceParameter.cs.
|
getset |
Specifies the number of labels in the data set, or 0 to use dynamic label discovery (requires large enough batch sizes to cover all labels within first batch) - (default = 0).
Definition at line 96 of file DataSequenceParameter.cs.
|
getset |
Specifies the first label in the label set (default = 0).
Definition at line 106 of file DataSequenceParameter.cs.
|
getset |
Specifies whether or not to output the labels in an additional top output. (default = true).
Labels areoutput in order per tuplet, so if k = 0 (e.g. output anchor and one negative) the output lables are as follows: 0 anchor label 0 negative label 1 anchor label 1 negative label :
Definition at line 86 of file DataSequenceParameter.cs.