Scores on benchmarks

Model rank shown below is with respect to all public models.
.113 average_vision rank 374
81 benchmarks
.113
0
ceiling
best
median
.207 neural_vision rank 355
38 benchmarks
.207
0
ceiling
best
median
.019 behavior_vision rank 408
43 benchmarks
.019
0
ceiling
best
median

How to use

from brainscore_vision import load_model
model = load_model("resnet50_FractalDB")
model.start_task(...)
model.start_recording(...)
model.look_at(...)

Benchmarks bibtex

Layer Commitment

Region Layer
V1 layer2
V2 layer3
V4 layer3
IT layer3

Visual Angle

8 degrees