# Image Classification on ImageNet-1k 64x64 downscaled (val) Source: [Image Classification on ImageNet-1k 64x64 downscaled (val)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:06:57.939Z Evaluation of Image Classification performance on the 64x64 downscaled validation split of ImageNet-1K, reporting Top-1 and Top-5 accuracy. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Image Classification | | Dataset (including any stated split) | ImageNet-1k 64x64 downscaled (val) | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 5 of 5 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Top-1 Accuracy](): Higher is better; unit: PERCENT. - [Top-5 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | WaveMix-256/7 | 56.66 | Not recorded | 68fa6bf11e209131cea310ce | | ResNet-101 | 56.05 | Not recorded | 68fa6bf11e209131cea310ce | | ResNet-50 | 55.66 | Not recorded | 68fa6bf11e209131cea310ce | | ResNet-34 | 55.04 | Not recorded | 68fa6bf11e209131cea310ce | | ResNet-18 | 50.67 | Not recorded | 68fa6bf11e209131cea310ce | ### WaveMix-256/7 Top-1 Accuracy: 56.66. Result ID: 698eaa98ffc3901de09f9aec. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"GPU(GB)":"9.0","Max Batch Size":"112","Batch Size":"64","Image Size":"64x64","GPU Memory Capacity":"16 GB"}. This record does not assert independent reproduction. ### ResNet-101 Top-1 Accuracy: 56.05. Result ID: 698eaa98ffc3901de09f9aeb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"GPU(GB)":"15.1","Max Batch Size":"64","Batch Size":"64","Image Size":"64x64","GPU Memory Capacity":"16 GB"}. This record does not assert independent reproduction. ### ResNet-50 Top-1 Accuracy: 55.66. Result ID: 698eaa98ffc3901de09f9aea. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"GPU(GB)":"11.3","Max Batch Size":"96","Batch Size":"64","Image Size":"64x64","GPU Memory Capacity":"16 GB"}. This record does not assert independent reproduction. ### ResNet-34 Top-1 Accuracy: 55.04. Result ID: 698eaa98ffc3901de09f9ae9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"GPU(GB)":"3.5","Max Batch Size":"288","Batch Size":"64","Image Size":"64x64","GPU Memory Capacity":"16 GB"}. This record does not assert independent reproduction. ### ResNet-18 Top-1 Accuracy: 50.67. Result ID: 698eaa98ffc3901de09f9ae8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"GPU(GB)":"2.6","Max Batch Size":"384","Batch Size":"64","Image Size":"64x64","GPU Memory Capacity":"16 GB"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.