Home › Census › drop_path

drop_path

Syntologyfunction-name censuscensus 2026-09-22battery b986f7e04d79all samples with this name

drop_path: 27 implementations from 61 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 5 distinct outputs across 2 buckets, one shared input per bucket.

Identical values to six decimals (the recorded digest) on the shared input are agreement on those inputs, not equivalence. Implementations are compared only within one bucket, the positional (rank, kind, dtype) of each array argument; the argument name is not part of the key because the harness draws the shared array from (rank, kind) and casts it to the dtype, whatever the name; each bucket's shared input is fixed by that key, so members of one bucket saw bitwise-identical inputs under their own scalar arguments. A cluster is the set of members whose recorded output digest is identical. Nothing here says which computation a paper's method intended, and nothing reproduces a paper's results.

Not compared, and not in the tables or the counts above:

Bucket 1 of 2: arg 1: rank 4, kind float, dtype float32

18 implementations from 36 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 3 distinct outputs, largest cluster first. Values are the first 8 of the recorded output, flattened.

Cluster (same digest to six decimals)MembersShared output on this bucket's input
7 implementations
16 papers
a8c38328240c
recorded values identical
one code sha held from 5 papers' repositories
src/models/dwiseneuro.py 971ae8d2
recorded x:4/float/float32; drop_prob=0.5, training=True, scale_by_keep=True
one code sha held from 3 papers' repositories
mono/model/backbones/ViT_DINO.py c157f5b1
recorded x:4/float/float32; drop_prob=0.5, training=True
one code sha held from 2 papers' repositories
pypots/nn/modules/tslanet/backbone.py 87577b3f
recorded x:4/float/float32; drop_prob=0.5, training=True, scale_by_keep=True
one code sha held from 2 papers' repositories
networks.py e3aa4e8e
recorded x:4/float/float32; drop_prob=0.5, training=True, scale_by_keep=True
one code sha held from 2 papers' repositories
models/croco.py f9a19005
recorded x:4/float/float32; drop_prob=0.5, training=True, scale_by_keep=True

src/dust3r/model.py aea279a2
recorded x:4/float/float32; drop_prob=0.5, training=True, scale_by_keep=True

nas_ood_single/search/models/model_search.py b1286732
recorded x:4/float/float32; drop_prob=0.5
[0, 0, 0, 0, 0, -0, -0, 0, …]
shape [2, 3, 4, 4] · float32 · Tensor
7 implementations
10 papers
fae90c40e485
recorded values identical
one code sha held from 2 papers' repositories
towhee/models/uniformer/uniformer.py 39eace7e
recorded x:4/float/float32; drop_prob=0.5, training=True
one code sha held from 2 papers' repositories
model/OpenCity/OpenCity.py 9bdf2492
recorded x:4/float/float32; drop_prob=0.5, training=True
one code sha held from 2 papers' repositories
model/impl/actionformer.py a34c005b
recorded x:4/float/float32; drop_prob=0.5, training=True

src/model/backbones/swin.py 2ec78252
recorded x:4/float/float32; drop_prob=0.5, training=True

network/RerankTransformer.py 3c83cad2
recorded x:4/float/float32; drop_prob=0.5, training=True

networks/embedding_translation.py 68b7ffb3
recorded x:4/float/float32; p=0.5, training=True

networks/RetrievalNet.py e37b79de
recorded x:4/float/float32; drop_prob=0.5, training=True
[0, 0, 0, 0, 0, -0, -0, 0, …]
shape [2, 3, 4, 4] · float32 · Tensor
4 implementations
10 papers
780f05c32657
recorded values identical
one code sha held from 4 papers' repositories
basicsr/archs/swinir_arch.py 52d96aa3
recorded x:4/float/float32; drop_prob=0.2, training=True
one code sha held from 4 papers' repositories
net.py fe7d4321
recorded x:4/float/float32; drop_prob=0.2, training=True

models/network_vrt.py 9ea4d5b8
recorded x:4/float/float32; drop_prob=0.2, training=True

dyn_slim/models/dyn_slim_net.py a86440e3
recorded inputs:4/float/float32; training=True, drop_path_rate=0.2
[0.903881, 0.816349, 1.80761, 1.37318, 1.42162, -0.249909, -0.339359, 1.03997, …]
shape [2, 3, 4, 4] · float32 · Tensor

Bucket 2 of 2: arg 1: rank 2, kind float, dtype float32

9 implementations from 25 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 2 distinct outputs, largest cluster first. Values are the first 8 of the recorded output, flattened.

Cluster (same digest to six decimals)MembersShared output on this bucket's input
8 implementations
23 papers
9913fdcbb256
recorded values identical
one code sha held from 8 papers' repositories
basicsr/models/archs/Xformer_arch.py 55120f20
recorded x:2/float/float32; drop_prob=0.5, training=True
one code sha held from 5 papers' repositories
seaformer-cls/seaformer.py 3ac6b7d7
recorded x:2/float/float32; drop_prob=0.5, training=True
one code sha held from 3 papers' repositories
src/vit.py 6bb74926
recorded x:2/float/float32; drop_prob=0.5, training=True
one code sha held from 2 papers' repositories
VLog/model/models.py 10e67144
recorded x:2/float/float32; drop_prob=0.5, training=True
one code sha held from 2 papers' repositories
models/base_model_ts.py 314973a7
recorded x:2/float/float32; drop_prob=0.5, training=True

vissl/models/trunks/beit_transformer.py 0233d6e8
recorded x:2/float/float32; drop_prob=0.5, training=True

look2hear/models/TDANet.py 04e8544d
recorded x:2/float/float32; drop_prob=0.5, training=True

fourm/models/fm.py e60d6e23
recorded x:2/float/float32; drop_prob=0.5, training=True
[0, -0, 0, -0, -0, -0, -0, 0, …]
shape [4, 8] · float32 · Tensor
1 implementation
2 papers
3159ee4a7683
one code sha held from 2 papers' repositories
units/models/model.py f5ab7648
recorded x:2/float/float32; drop_prob=0.5, training=True, scale_by_keep=True
[0, -0, 0, -0, -0, -0, -0, 0, …]
shape [4, 8] · float32 · Tensor

Identical values to six decimals (the recorded digest) on the shared input are agreement on those inputs, not equivalence; where a cluster's members carry recorded values, the largest difference among them is shown under the cluster. Paper titles are the archive's archive 2025-07-28 where the paper is in the archive and the graph's where it was added by Syntology; papers with no page here are shown by their recorded paper id only. A paper count above the implementation count means one implementation (one code sha) is held from several papers' repositories and counts once. Per-sample status, licence and fingerprint records for each paper are on its paper page. JSON twin: /census/drop-path.json.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections