| --- |
| license: apache-2.0 |
| tags: |
| - executorch |
| - xnnpack |
| - pte |
| - on-device |
| - image-to-text |
| - text-recognition |
| --- |
| # docTR CRNN-MobileNetV3-Small — ExecuTorch |
|
|
| Text **recognition**: reads one word crop. The other half of the pair is |
| [DB-MobileNetV3-Large](https://huggingface.co/mlboydaisuke/docTR-DB-MobileNetV3-Large-ExecuTorch), |
| which finds the crops. |
|
|
| - **Source**: [mindee/doctr](https://github.com/mindee/doctr) `crnn_mobilenet_v3_small`, |
| 2.1M parameters |
| - **License**: Apache-2.0 |
| - **Input**: `[1, 3, 32, 128]`, normalised with docTR's own mean (0.694, 0.695, 0.693) and |
| std (0.299, 0.296, 0.301) |
| - **Output**: `[1, 32, 127]` — 32 timesteps over a 126-symbol alphabet plus the CTC blank |
|
|
| Logits, not probabilities: greedy CTC only needs the argmax per timestep, so a softmax would |
| be thrown away. The alphabet is |
| `0123456789`, `a-z`, `A-Z`, punctuation, `°£€¥¢฿`, and accented Latin — read it out of |
| `crnn_mobilenet_v3_small().cfg["vocab"]` rather than retyping it. |
|
|
| ## Verification (Mac arm64, 2026-08-23) |
|
|
| | build | size | latency | worst corr | |
| |---|---|---|---| |
| | XNNPACK fp32 | 8.8 MB | 3.2 ms | 1.000000 | |
| | XNNPACK fp16 | 6.5 MB | 4.0 ms | 0.997143 | |
| | Core ML fp32 | 6.2 MB | **0.3 ms** | 0.999530 | |
|
|
| Eager fp32 for the same input is 121 ms. |
|
|
| **Read end to end** with the detector, on a London street photograph |
| (`convert/check_doctr.py`): |
|
|
| ``` |
| boxes: 10 |
| read: TIUZABXPRESS | Chrisiophers | Place | STREE! | LAG | BAR! |
| ``` |
|
|
| The signs say PIZZA EXPRESS and Christopher's Place. |
|
|
| ## Cropping it |
|
|
| docTR's own `Resize` for this model is `preserve_aspect_ratio=True, symmetric_pad=False`: |
| the crop keeps its shape, sits at the top-left, and the rest of the strip is black. The |
| check does the same. |
|
|
| That is the principled choice rather than a measured improvement. Over four street |
| photographs neither it nor a plain squeeze won: one picture reads `Chrisiophers` squeezed |
| and `Clridabers` padded, another reads `TRAFFIC` padded and `TRAEFIC` squeezed. |
|
|
| ## Not shipped, and why |
|
|
| - **int8**: worst corr **0.883**, against a 0.95 gate, for 6.1 MB against 8.8. Recognition |
| is the half where a wrong character is the whole answer, so this one is not close enough. |
|
|
| ## Conversion |
|
|
| ```bash |
| python convert/export_doctr.py recognise |
| ``` |
|
|
| docTR's `forward` runs CTC decoding in numpy whether or not it was asked to, which |
| `torch.export` refuses. The model carries an `exportable` flag that skips it and returns raw |
| logits; the wrapper sets that. |
|
|
| **Feed it contiguous tensors.** ExecuTorch reads a tensor in memory order rather than by its |
| strides, and a crop built with `np.transpose` is not contiguous. The detector half of this |
| pair scored 1.000000 against eager on random input and then returned a map that thresholded |
| to zero boxes on a real photograph, entirely because of that. |
|
|
| (conversion scripts: [executorch-models](https://github.com/john-rocky/executorch-models)) |
|
|
