Dontopedia

nn.Linear(128, 128)

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-10.)

nn.Linear(128, 128) has 21 facts recorded in Dontopedia across 5 references, with 3 live disagreements.

21 facts·13 predicates·5 sources·3 in dispute

Mostly:rdf:type(5), input size(2), output size(2)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (9)

Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.

hasLayerHas Layer(3)

contains-layerContains Layer(1)

containsLayerContains Layer(1)

first-layerFirst Layer(1)

firstLayerFirst Layer(1)

followsFollows(1)

hasMemberHas Member(1)

Other facts (20)

The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.

20 facts
PredicateValueRef
Rdf:typeLinear Layer[1]
Rdf:typeLinear Layer[2]
Rdf:typeLinear Layer[3]
Rdf:typeLinear Layer[4]
Rdf:typeLinear Layer[5]
Input Size128[1]
Input Size128[3]
Output Size64[1]
Output Size128[3]
Connected toRelu Layer[4]
Connected toRelu Activation[5]
In Features128[2]
Out Features64[2]
Belongs toPytorch Model[2]
Is Part ofModel[3]
Has Input Size128[4]
Has Output Size128[4]
PrecedesRelu Layer[4]
Input Features128[5]
Output Features128[5]

Timeline

Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.

typebeam/d44e9c4d-c972-419c-8213-b4acc06875e1
ex:LinearLayer
inputSizebeam/d44e9c4d-c972-419c-8213-b4acc06875e1
128
outputSizebeam/d44e9c4d-c972-419c-8213-b4acc06875e1
64
typebeam/e949b3bf-5972-4a2e-ac8c-633577808057
ex:LinearLayer
inFeaturesbeam/e949b3bf-5972-4a2e-ac8c-633577808057
128
outFeaturesbeam/e949b3bf-5972-4a2e-ac8c-633577808057
64
belongsTobeam/e949b3bf-5972-4a2e-ac8c-633577808057
ex:pytorch-model
typebeam/3f0767b1-b662-4a63-8084-d6ad5cd59ba6
ex:Linear-layer
inputSizebeam/3f0767b1-b662-4a63-8084-d6ad5cd59ba6
128
outputSizebeam/3f0767b1-b662-4a63-8084-d6ad5cd59ba6
128
isPartOfbeam/3f0767b1-b662-4a63-8084-d6ad5cd59ba6
ex:model
typebeam/ab59c72f-e670-464a-abad-d22f2c0027aa
ex:LinearLayer
hasInputSizebeam/ab59c72f-e670-464a-abad-d22f2c0027aa
128
hasOutputSizebeam/ab59c72f-e670-464a-abad-d22f2c0027aa
128
connectedTobeam/ab59c72f-e670-464a-abad-d22f2c0027aa
ex:relu-layer
precedesbeam/ab59c72f-e670-464a-abad-d22f2c0027aa
ex:relu-layer
typebeam/a38a0bc2-6ed2-4089-b908-741e1595c678
ex:Linear-Layer
labelbeam/a38a0bc2-6ed2-4089-b908-741e1595c678
nn.Linear(128, 128)
input-featuresbeam/a38a0bc2-6ed2-4089-b908-741e1595c678
128
output-featuresbeam/a38a0bc2-6ed2-4089-b908-741e1595c678
128
connectedTobeam/a38a0bc2-6ed2-4089-b908-741e1595c678
ex:relu-activation

References (5)

5 references
  1. ctx:claims/beam/d44e9c4d-c972-419c-8213-b4acc06875e1
    • full textbeam-chunk
      text/plain1 KBdoc:beam/d44e9c4d-c972-419c-8213-b4acc06875e1
      Show excerpt
      return token['access_token'] def authorize(token, resource): userinfo = keycloak_openid.userinfo(token) if 'roles' in userinfo and resource in userinfo['roles']: return True return False def rerank_results(model, d
  2. ctx:claims/beam/e949b3bf-5972-4a2e-ac8c-633577808057
  3. ctx:claims/beam/3f0767b1-b662-4a63-8084-d6ad5cd59ba6
    • full textbeam-chunk
      text/plain1 KBdoc:beam/3f0767b1-b662-4a63-8084-d6ad5cd59ba6
      Show excerpt
      [Turn 9556] User: I'm experiencing performance issues with my application, and I've noticed that the security memory is capped at 1.5GB. I'm trying to reduce spikes by 15% for 22,000 operations, but I'm not sure how to optimize the memory u
  4. ctx:claims/beam/ab59c72f-e670-464a-abad-d22f2c0027aa
    • full textbeam-chunk
      text/plain1 KBdoc:beam/ab59c72f-e670-464a-abad-d22f2c0027aa
      Show excerpt
      [Turn 9564] User: I'm trying to optimize the memory usage of my application, and I've noticed that the current implementation is not efficient. I'm using Keycloak 22.0.5 for access control, and I've been reading about the different configur
  5. ctx:claims/beam/a38a0bc2-6ed2-4089-b908-741e1595c678
    • full textbeam-chunk
      text/plain1 KBdoc:beam/a38a0bc2-6ed2-4089-b908-741e1595c678
      Show excerpt
      ### 6. Use `torch.cuda.empty_cache()` Periodically calling `torch.cuda.empty_cache()` can help free up unused memory on the GPU. ### 7. Use `torch.autograd.profiler` Profiling your code can help identify bottlenecks and areas where memory

See also

Keep researching

Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.