brain-score/vision
A framework for evaluating models on their alignment to brain and behavioral measurements (50+ benchmarks)
Jupyter NotebookMIT
Issues
- 6
VGG16 scoring model taking up > 500 GB of RAM
#1305 opened by ShreyaKapoor18 - 4
Get individual layer score
#1297 opened by amirozhan - 2
Builds fail due to package mismatch
#1233 opened by akgokce - 2
Requirements missing for temporal_model_videomae
#1195 opened by YingtianDt - 0
Kar2019 testing score assertion errors
#1198 opened by samwinebrake - 0
Marques score assertion errors
#1197 opened by samwinebrake - 0
Unable to access some model weights
#1196 opened by benlonnqvist - 1
Installation error
#1171 opened by badooki - 0
- 1
Disallow nonconverted models to be scored
#1082 opened by mike-ferguson - 0
Score models on new Ferguson2024 benchmarks
#864 opened by deirdre-k - 0
Merge and Deploy Ferguson2024 Benchmark
#863 opened by deirdre-k - 0
Score Models on Baker2022 Benchmark
#1001 opened by mike-ferguson - 1
Merge Matching Models
#936 opened by pellegreene - 0
This is a sample issue
#1021 opened by mike-ferguson - 0
Merge and Deploy Baker 2022 Benchmark
#1000 opened by mike-ferguson - 2
Run top 25 models on Sanghavi
#932 opened by pellegreene - 0
Improve efficiency of test_look_at_neural_V1
#998 opened by deirdre-k - 0
Remove trailing >> from benchmark Init files
#935 opened by mike-ferguson - 1
Update Jenkins repo with all the config files
#902 opened by mike-ferguson - 1
Update Jenkins Documentation
#901 opened by mike-ferguson - 3
- 1
Figure out how to handle unconvertible models
#881 opened by mike-ferguson - 0
"Create Benchmark" tutorial incorrect import
#931 opened by mschrimpf - 0
- 1
StimulusSet data types may clash with DataAssembly data types after s3 upload
#905 opened by benlonnqvist - 1
- 0
Add a message to dataset/stimulus upload to say whether the uploaded files are private or public access
#911 opened by benlonnqvist - 1
Allow uploading pre-computed feature .nc files to s3 buckets using similar functionality as for DataAssemblies/StimulusSets
#904 opened by benlonnqvist - 5
Test alexnet scoring on Rajalingham2018public-i2n
#876 opened by deirdre-k - 0
Update Quickstart Text
#891 opened by mike-ferguson - 2
Allow users to see benchmarks they own
#892 opened by mike-ferguson - 3
Remove the gather_index in DataAssembly
#875 opened by YingtianDt - 0
Create 2 science benchmarks
#865 opened by deirdre-k - 2
- 0
Create Mini Table of Public benchmark scores
#890 opened by mike-ferguson - 0
Run Model resnet50-VITO-8deg-cc on 1.0
#883 opened by mike-ferguson - 0
- 0
Finalize Conversion process docs for UROP
#877 opened by mike-ferguson - 0
Centralize Competition Models and Top 25 Models
#878 opened by mike-ferguson - 0
Rerun rank 12 and rank 18 models
#879 opened by mike-ferguson - 0
Change score_plugins job email to be generic
#874 opened by deirdre-k - 0
Investigate automerge not happening
#873 opened by deirdre-k - 0
Review jenkins after OM downtime
#872 opened by deirdre-k - 0
- 0
- 0
change plugin limit to 1
#869 opened by deirdre-k - 0
Fix Travis AWS Credential errors
#868 opened by deirdre-k - 0
Document remaining models to be converted
#867 opened by deirdre-k - 0
Handle large submissions in tests
#866 opened by deirdre-k