{"record":{"id":"f370f2eb8fb4f7a4","repo":"rohitg00/ai-engineering-from-scratch","slug":"image-size-image-size-must-be-divisible-by-pat","errorCode":null,"errorMessage":"image_size ({image_size}) must be divisible by patch_size ({patch_size})","messagePattern":"image_size \\((.+?)\\) must be divisible by patch_size \\((.+?)\\)","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"phases/12-multimodal-ai/01-vision-transformer-patch-tokens/code/main.py","lineNumber":44,"sourceCode":"    registers: int = 0\n    cls_token: bool = True\n\n\nZOO = [\n    ViTConfig(\"ViT-B/16 @ 224\", 224, 16, 768, 12, 12),\n    ViTConfig(\"ViT-L/14 @ 336 (CLIP)\", 336, 14, 1024, 24, 16),\n    ViTConfig(\"DINOv2 ViT-g/14 @ 224\", 224, 14, 1536, 40, 24, registers=4),\n    ViTConfig(\"SigLIP SO400m/14 @ 378\", 378, 14, 1152, 27, 16, registers=4,\n              cls_token=False),\n    ViTConfig(\"Qwen2.5-VL ViT @ 896x896\", 896, 14, 1280, 32, 16),\n]\n\n\ndef grid_shape(image_size: int, patch_size: int) -> tuple[int, int]:\n    if image_size <= 0 or patch_size <= 0:\n        raise ValueError(f\"image_size and patch_size must be positive, got {image_size=} {patch_size=}\")\n    if image_size % patch_size != 0:\n        raise ValueError(f\"image_size ({image_size}) must be divisible by patch_size ({patch_size})\")\n    g = image_size // patch_size\n    return (g, g)\n\n\ndef seq_length(cfg: ViTConfig) -> int:\n    h, w = grid_shape(cfg.image_size, cfg.patch_size)\n    extra = (1 if cfg.cls_token else 0) + cfg.registers\n    return h * w + extra\n\n\ndef patch_embed_params(cfg: ViTConfig) -> int:\n    p = cfg.patch_size\n    return 3 * p * p * cfg.hidden + cfg.hidden\n\n\ndef pos_embed_params(cfg: ViTConfig) -> int:\n    return seq_length(cfg) * cfg.hidden\n","sourceCodeStart":26,"sourceCodeEnd":62,"githubUrl":"https://github.com/rohitg00/ai-engineering-from-scratch/blob/39ea8a1c6d0b61f071226eff7ede4d4105fed820/phases/12-multimodal-ai/01-vision-transformer-patch-tokens/code/main.py#L26-L62","documentation":"Error \"image_size ({image_size}) must be divisible by patch_size ({patch_size})\" thrown in rohitg00/ai-engineering-from-scratch.","triggerScenarios":"Thrown at phases/12-multimodal-ai/01-vision-transformer-patch-tokens/code/main.py:44 when the library encounters an invalid state.","commonSituations":"See trigger scenarios.","solutions":[],"exampleFix":null,"handlingStrategy":null,"validationCode":null,"typeGuard":null,"tryCatchPattern":null,"preventionTips":[],"tags":[],"backgroundTag":null,"analyzedSha":"39ea8a1c6d0b61f071226eff7ede4d4105fed820","analyzedAt":"2026-08-26T03:13:46.626Z","schemaVersion":2},"datasetVersion":"2026-08-26T07:17:17.940Z"}