{"record":{"id":"b5558c09c167b022","repo":"rohitg00/ai-engineering-from-scratch","slug":"expected-4d-input-b-c-h-w-got-shape-tuple-x-sh","errorCode":null,"errorMessage":"expected 4D input (B,C,H,W), got shape {tuple(x.shape)}","messagePattern":"expected 4D input \\(B,C,H,W\\), got shape (.+?)","errorType":"validation","errorClass":"ValueError","httpStatus":null,"severity":"error","filePath":"phases/19-capstone-projects/58-vision-encoder-patches/code/main.py","lineNumber":89,"sourceCode":"\n    Output shape on a (B, C, H, W) input is (B, N, hidden) where\n    N = (H / patch_size) * (W / patch_size).\n    \"\"\"\n\n    def __init__(self, cfg: FrontEndConfig) -> None:\n        super().__init__()\n        self.cfg = cfg\n        self.proj = nn.Conv2d(\n            cfg.in_channels,\n            cfg.hidden,\n            kernel_size=cfg.patch_size,\n            stride=cfg.patch_size,\n            bias=True,\n        )\n\n    def forward(self, x: torch.Tensor) -> torch.Tensor:\n        if x.dim() != 4:\n            raise ValueError(f\"expected 4D input (B,C,H,W), got shape {tuple(x.shape)}\")\n        if x.shape[1] != self.cfg.in_channels:\n            raise ValueError(\n                f\"channel mismatch: got {x.shape[1]}, expected {self.cfg.in_channels}\"\n            )\n        if x.shape[2] != self.cfg.image_size or x.shape[3] != self.cfg.image_size:\n            raise ValueError(\n                f\"spatial mismatch: got {tuple(x.shape[2:])}, expected \"\n                f\"({self.cfg.image_size}, {self.cfg.image_size})\"\n            )\n        out = self.proj(x)\n        b = out.shape[0]\n        out = out.flatten(2).transpose(1, 2)\n        return out\n\n\nclass VisionFrontEnd(nn.Module):\n    \"\"\"Patch embed + CLS prepend + 2D sinusoidal position.\n","sourceCodeStart":71,"sourceCodeEnd":107,"githubUrl":"https://github.com/rohitg00/ai-engineering-from-scratch/blob/39ea8a1c6d0b61f071226eff7ede4d4105fed820/phases/19-capstone-projects/58-vision-encoder-patches/code/main.py#L71-L107","documentation":"Error \"expected 4D input (B,C,H,W), got shape {tuple(x.shape)}\" thrown in rohitg00/ai-engineering-from-scratch.","triggerScenarios":"Thrown at phases/19-capstone-projects/58-vision-encoder-patches/code/main.py:89 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"}