# README
Caffe2 Prediction 
# Packages
No description provided by the author
No description provided by the author
No description provided by the author
# Functions
Asset loads and returns the asset for the given name.
AssetDir returns the file names below a certain directory embedded in the file by go-bindata.
AssetInfo loads and returns the asset info for the given name.
AssetNames returns the names of the assets.
MustAsset is like Asset but panics when Asset would return an error.
No description provided by the author
RestoreAsset restores an asset under the given directory.
RestoreAssets restores an asset under the given directory recursively.
# Constants
Default_DeviceOption_DeviceType ...
Default_ModelInfo_PredictorType ...
Default_OperatorDef_IsGradientOp ...
Default_PredictorConsts_GLOBAL_INIT_NET_TYPE ...
Default_PredictorConsts_INPUTS_BLOB_TYPE ...
Default_PredictorConsts_META_NET_DEF ...
Default_PredictorConsts_MULTI_PREDICTOR ...
Default_PredictorConsts_OUTPUTS_BLOB_TYPE ...
Default_PredictorConsts_PARAMETERS_BLOB_TYPE ...
Default_PredictorConsts_PREDICT_INIT_NET_TYPE ...
Default_PredictorConsts_PREDICT_NET_TYPE ...
Default_PredictorConsts_PREDICTOR_DBREADER ...
Default_PredictorConsts_SINGLE_PREDICTOR ...
Default_PredictorConsts_TRAIN_INIT_PLAN_TYPE ...
Default_PredictorConsts_TRAIN_PLAN_TYPE ...
Default_TensorProto_DataType ...
Default_TensorShape_DataType ...
Default_TensorShape_UnknownShape ...
DeviceType_CPU ...
DeviceType_CPU ...
DeviceType_CPU ...
DeviceType_CPU ...
CAFFE_LEGACY_POOLING is a flag that notifies the code to use the old Caffe padding strategy.
LegacyPadding_NOTSET ...
LegacyPadding_NOTSET ...
VALID and SAME are two strategies adopted in Google DistBelief: it forces the input shape as follows.
Less-commonly used data types.
TensorProto_UNDEFINED ...
TensorProto_UNDEFINED ...
TensorProto_UNDEFINED ...
TensorProto_UNDEFINED ...
TensorProto_UNDEFINED ...
TensorProto_UNDEFINED ...
TensorProto_UNDEFINED ...
TensorProto_UNDEFINED ...
TensorProto_UNDEFINED ...
TensorProto_UNDEFINED ...
TensorProto_UNDEFINED ...
TensorProto_UNDEFINED ...
# Variables
Version ...
DeviceType_name ...
DeviceType_value ...
ErrInvalidLengthCaffe2 ...
ErrInvalidLengthHsm ...
ErrInvalidLengthMetanet ...
ErrInvalidLengthPredictorConsts ...
ErrInvalidLengthProfDag ...
ErrInvalidLengthCaffe2 ...
ErrInvalidLengthHsm ...
ErrInvalidLengthMetanet ...
ErrInvalidLengthPredictorConsts ...
ErrInvalidLengthProfDag ...
FrameworkManifest ...
Version ...
LegacyPadding_name ...
LegacyPadding_value ...
TensorProto_DataType_name ...
TensorProto_DataType_value ...
Version ...
# Structs
A named argument containing either singular float, integer and string values, or repeated float, int and string arrays.
Protobuf format for blobs that are not Tensors.
BlobsMap ...
Protobuf format to serialize DBReader.
Device-specific options.
ExecutionStep is actually a sort-of-hacky way we simulate iteration right now.
Internal Protobuf format which represents the path in the tree hierarchy for each word in the vocabulary.
MetaNetDef ...
ModelInfo ...
Network definition.
NetsMap ...
Each node in the hierarchy contains links to either leaf nodes or more non-terminal nodes.
Operator Definition.
Represents a node in the path from the root node all the way down to the word (leaf).
Each PathProto belongs to a word and is an array of nodes in the path from the root to the leaf (which is the word itself) in the tree.
PlanDef ...
PlansMap ...
PredictorConsts ...
Protobuf format to serialize profiler data.
ProfDAGProtos ...
QTensorProto ...
StringMap ...
TensorProto stores serialized Tensor objects.
When loading from chunks this is going to indicate where to put data in the full array.
TensorProtos stores multiple TensorProto objects in one single proto.
TensorShape ...
TensorShapes ...
Protobuf format to accept hierarchy for hierarchical softmax operator.
# Type aliases
DeviceType that Caffe2 currently supports.
LegacyPadding ...
TensorProto_DataType ...