| schema_version: 1.0.0 | |
| report_type: image-to-image | |
| task_type: image-to-image | |
| title: ESRGAN x4 INT8 — ExecuTorch + XNNPACK | |
| description: >- | |
| INT8-quantized 4× single-image super-resolution models for enhancing low-resolution RGB images, | |
| especially urban scenes with fine repetitive details. Built on a 23-block RRDBNet backbone, they use | |
| tiled 128×128 inputs and produce 512×512 outputs per tile, balancing image fidelity with reduced | |
| model size and faster inference on ARM-oriented runtimes. | |
| id: Arm/esrgan-int8-xnnpack-executorch-graviton-g4 | |
| filename: esrgan-x4-int8-executorch.pte | |
| base_model_id: kadirnar/RRDB_PSNR_x4 | |
| profile: Arm-Optimized | |
| weight_dtype: int8 | |
| model_size_mb: 23.176 | |
| parameter_count: 16697987 | |
| format: pte | |
| quantization: | |
| method: PTQ-static | |
| weight_bits: 8 | |
| activation_bits: 8 | |
| symmetric: true | |
| mode: static | |
| weight_granularity: per-channel | |
| calibration: | |
| dataset_name: urban100 | |
| sample_count: 100 | |
| selection: random | |