Caffe
E366103
Caffe is an open-source deep learning framework known for its speed and modular design, widely used in computer vision research and applications.
All labels observed (2)
How this entity was disambiguated
This entity first appeared as the object of triple T3520383 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Caffe Context triple: [VGG, implementedIn, Caffe]
-
A.
Cappachino
Cappachino is an alias of Cappadonna, an American rapper best known for his longtime affiliation with the Wu-Tang Clan.
-
B.
Café au Lait
Café au Lait is one of the short, conversational vignettes in Jim Jarmusch’s film "Coffee and Cigarettes," featuring characters chatting over coffee in a minimalist, black-and-white setting.
-
C.
Mocha
Mocha is a popular JavaScript test framework used primarily for running unit and integration tests in Node.js and browser-based applications.
-
D.
Mocha
Mocha is a subsidiary peak of the Carihuairazo volcanic massif in the Ecuadorian Andes.
-
E.
ECAFE
ECAFE is the former name (Economic Commission for Asia and the Far East) of the United Nations regional body now known as the Economic and Social Commission for Asia and the Pacific (ESCAP), which promotes economic and social development in the Asia-Pacific region.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Caffe Target entity description: Caffe is an open-source deep learning framework known for its speed and modular design, widely used in computer vision research and applications.
-
A.
Cappachino
Cappachino is an alias of Cappadonna, an American rapper best known for his longtime affiliation with the Wu-Tang Clan.
-
B.
Café au Lait
Café au Lait is one of the short, conversational vignettes in Jim Jarmusch’s film "Coffee and Cigarettes," featuring characters chatting over coffee in a minimalist, black-and-white setting.
-
C.
Mocha
Mocha is a popular JavaScript test framework used primarily for running unit and integration tests in Node.js and browser-based applications.
-
D.
Mocha
Mocha is a subsidiary peak of the Carihuairazo volcanic massif in the Ecuadorian Andes.
-
E.
ECAFE
ECAFE is the former name (Economic Commission for Asia and the Far East) of the United Nations regional body now known as the Economic and Social Commission for Asia and the Pacific (ESCAP), which promotes economic and social development in the Asia-Pacific region.
- F. None of above. chosen
Statements (51)
| Predicate | Object |
|---|---|
| instanceOf |
deep learning framework
ⓘ
machine learning framework ⓘ open-source software ⓘ software library ⓘ |
| configurationFormat |
Protocol Buffers
ⓘ
surface form:
Protobuf
|
| designGoal |
expressiveness
ⓘ
modularity ⓘ speed ⓘ |
| developer |
Berkeley Vision and Learning Center
ⓘ
Yangqing Jia ⓘ |
| hasModelZoo | Caffe Model Zoo ⓘ |
| influenced |
Caffe2
ⓘ
other deep learning frameworks ⓘ |
| license |
BSD license
ⓘ
surface form:
BSD 2-Clause License
|
| notableUse |
academic computer vision research
ⓘ
industrial computer vision applications ⓘ |
| openSource | true ⓘ |
| primaryDomain | computer vision ⓘ |
| programmingLanguage |
C++
ⓘ
NVIDIA CUDA ⓘ
surface form:
CUDA
Python ⓘ |
| repositoryHostingService | GitHub ⓘ |
| supportsBackend |
NVIDIA CUDA
ⓘ
surface form:
CUDA
cuDNN ⓘ |
| supportsHardware |
CPU
ⓘ
GPU ⓘ |
| supportsLanguageBinding |
MATLAB
ⓘ
Python ⓘ |
| supportsLayerType |
ReLU layer
ⓘ
batch normalization layer ⓘ convolution layer ⓘ dropout layer ⓘ inner product layer ⓘ pooling layer ⓘ |
| supportsModelType |
convolutional neural network
ⓘ
fully connected neural network ⓘ recurrent neural network (via extensions) ⓘ |
| supportsOperatingSystem |
Linux
ⓘ
Windows ⓘ macOS ⓘ |
| supportsPretrainedModels | true ⓘ |
| supportsTask |
feature extraction
ⓘ
fine-tuning of neural networks ⓘ image classification ⓘ object detection ⓘ segmentation ⓘ |
| supportsTraining |
learning rate scheduling
ⓘ
momentum ⓘ stochastic gradient descent ⓘ |
| usesDataFormat |
LMDB
ⓘ
LevelDB ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Caffe Description of subject: Caffe is an open-source deep learning framework known for its speed and modular design, widely used in computer vision research and applications.
Referenced by (3)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
Caffè