Download OCR_INDRA/tools/indra_eval/inspect_models.py from prosperious/ocr-projects-archive: direct link, hf CLI and curl.
- Browser
- Download file 5.92 kB
-
https://huggingface.co/prosperious/ocr-projects-archive/resolve/main/OCR_INDRA/tools/indra_eval/inspect_models.py
- Command line
-
hf download hf://prosperious/ocr-projects-archive/OCR_INDRA/tools/indra_eval/inspect_models.py
-
curl -L -o inspect_models.py https://huggingface.co/prosperious/ocr-projects-archive/resolve/main/OCR_INDRA/tools/indra_eval/inspect_models.py
5.92 kB
| """Inspect rec.onnx graph structure and model.safetensors weights. | |
| Answers: | |
| - exact input/output shapes and names of the recognizer graph | |
| - op sequence: conv attributes (strides, padding), activations, pooling | |
| - whether BN is folded into convs | |
| - parameter count from the safetensors and cross-check with ONNX initializers | |
| """ | |
| import json | |
| from pathlib import Path | |
| import numpy as np | |
| import onnx | |
| import safetensors.numpy | |
| MODEL_DIR = Path("/mnt/c/Users/Dell/Desktop/OCR_INDRA/models/indra-ocr-v3.1.1") | |
| def graph_summary(model): | |
| g = model.graph | |
| print("== INPUTS ==") | |
| for i in g.input: | |
| dims = [(d.dim_param or d.dim_value) for d in i.type.tensor_type.shape.dim] | |
| print(f" {i.name}: dims={dims} dtype={i.type.tensor_type.elem_type}") | |
| print("== OUTPUTS ==") | |
| for o in g.output: | |
| dims = [(d.dim_param or d.dim_value) for d in o.type.tensor_type.shape.dim] | |
| print(f" {o.name}: dims={dims} dtype={o.type.tensor_type.elem_type}") | |
| print(f"== {len(g.node)} nodes, {len(g.initializer)} initializers ==") | |
| ops = {} | |
| for n in g.node: | |
| ops[n.op_type] = ops.get(n.op_type, 0) + 1 | |
| print(" op counts:", dict(sorted(ops.items(), key=lambda x: -x[1]))) | |
| imp = model.opset_import | |
| for i in imp: | |
| print(f" opset domain={i.domain!r} version={i.version}") | |
| def shape_of(t): | |
| dims = getattr(t, "dims", None) or [] | |
| return list(dims) | |
| def initializer_map(model): | |
| # large models may be external; these are small | |
| return {t.name: onnx.numpy_helper.to_array(t) for t in model.graph.initializer} | |
| def conv_attrs(model): | |
| return { | |
| n.name: {a.name: onnx.helper.get_attribute_value(a) for a in n.attribute} | |
| for n in model.graph.node | |
| if n.op_type in ("Conv",) | |
| } | |
| def tensors_of(model, prefix=""): | |
| # ValueInfo for nursing intermediate shapes | |
| return model.graph | |
| def main(): | |
| print("### rec.onnx graph ###") | |
| m = onnx.load(str(MODEL_DIR / "rec.onnx")) | |
| graph_summary(m) | |
| # print the full node sequence with attrs for the main ops | |
| print("\n== node sequence (abbrev) ==") | |
| for k, n in enumerate(m.graph.node): | |
| attrs = {a.name: onnx.helper.get_attribute_value(a) for a in n.attribute} | |
| if n.op_type == "Constant": | |
| continue | |
| ins = ", ".join(n.input[:2]) | |
| outs = ", ".join(n.output[:1]) | |
| if k < 200 and n.op_type in ("Conv", "ConvTranspose", "BatchNormalization", | |
| "Relu", "LeakyRelu", "Sigmoid", "Multiply", | |
| "Add", "ReduceMean", "Div", "GlobalAveragePool", | |
| "AveragePool", "MaxPool", "Resize", "Squeeze", | |
| "Unsqueeze", "Concat", "Transpose", "Reshape", | |
| "Cast", "ArgMax", "ReduceMax", "ReduceArgMax", | |
| "Gather", "Shape", "Less", "Greater", "Where"): | |
| print(f" {k:3d} {n.op_type:22s} {outs} <- {ins} {dict(list(attrs.items())[:6])}") | |
| elif k < 3 or n.op_type not in ("Cast", "Shape", "Gather", "Concat", "Unsqueeze", | |
| "Squeeze", "Reshape", "Sub", "Mul", "Div", | |
| "Slice", "Constant"): | |
| pass | |
| # count up to 60 first 20 lines then finalize | |
| print("\n(total nodes:", len(m.graph.node), ")") | |
| def main2(): | |
| print("\n### conv attributes (kernel/dilation/pad only) ###") | |
| m = onnx.load(str(MODEL_DIR / "rec.onnx")) | |
| for n in m.graph.node: | |
| if n.op_type != "Conv": | |
| continue | |
| attrs = {a.name: onnx.helper.get_attribute_value(a) for a in n.attribute} | |
| w = attrs.get("kernel_shape") | |
| print(f" {n.name:20s} kernel={w} stride={attrs.get('strides')} " | |
| f"dil={attrs.get('dilations')} pad_mode={attrs.get('auto_pad')} " | |
| f"group={attrs.get('group', 1)} pads={attrs.get('pads')}") | |
| def main3(): | |
| print("\n### safetensors ###") | |
| with open(MODEL_DIR / "model.safetensors", "rb") as f: | |
| header_size = int.from_bytes(f.read(8), "little") | |
| header = json.loads(f.read(header_size)) | |
| tensors = {k: v for k, v in header.items() if k != "__metadata__"} | |
| print(f"{len(tensors)} tensors") | |
| total = 0 | |
| for name, info in list(tensors.items()): | |
| n = int(np.prod(info["shape"])) if info["shape"] else 1 | |
| total += n | |
| print(f" {name:44s} {str(info['shape']):24s} {info['dtype']:6s} {n}") | |
| print(f"{total} total parameters") | |
| def main4(): | |
| print("\n### crosscheck: rec.onnx initializer count/params ###") | |
| m = onnx.load(str(MODEL_DIR / "rec.onnx")) | |
| init = {t.name: onnx.numpy_helper.to_array(t) for t in m.graph.initializer} | |
| tot = sum(int(np.prod(a.shape)) if a.ndim else 1 for a in init.values()) | |
| print(f"{len(init)} initializers, {tot} parameters") | |
| # show the head and first block names: | |
| sizes = sorted( | |
| [(n, a.shape) for n, a in init.items() if a.ndim >= 1], | |
| key=lambda x: -int(np.prod(x[1])) if len(x[1]) else 0, | |
| )[:10] | |
| for n, s in sizes: | |
| print(f" big: {n:36s} {s}") | |
| def main5(): | |
| print("\n### other models: graph I/O ###") | |
| for f in ["det.onnx", "orient.onnx", "order.onnx", "script.onnx", "rec_cjk.onnx"]: | |
| m = onnx.load(str(MODEL_DIR / f)) | |
| print(f"\n{f}:") | |
| for i in m.graph.input: | |
| dims = [(d.dim_param or d.dim_value) for d in i.type.tensor_type.shape.dim] | |
| print(f" in {i.name}: dims={dims}") | |
| for o in m.graph.output: | |
| dims = [(d.dim_param or d.dim_value) for d in o.type.tensor_type.shape.dim] | |
| print(f" out {o.name}: dims={dims}") | |
| ops = {} | |
| for n in m.graph.node: | |
| ops[n.op_type] = ops.get(n.op_type, 0) + 1 | |
| print(" ops:", ops) | |
| if __name__ == "__main__": | |
| main() | |
| main2() | |
| main3() | |
| main4() | |
| main5() | |