PaddlePaddle/PaddleOCR · error · ValueError

neither {file_name}.json nor {file_name}.pdmodel was found i

Error message

neither {file_name}.json nor {file_name}.pdmodel was found in {model_dir}.

What it means

Companion check to the .pdiparams gate: after finding a params file (model.* or inference.*), create_predictor requires the matching program file — either <name>.pdmodel or <name>.json (the new Paddle 3 serialized format) — in the same directory. Its absence raises this ValueError, meaning the model directory is half-populated (weights without the graph).

Source

Thrown at tools/infer/utility.py:257

            None,
            None,
        )

    else:
        file_names = ["model", "inference"]
        for file_name in file_names:
            params_file_path = f"{model_dir}/{file_name}.pdiparams"
            if os.path.exists(params_file_path):
                break

        if not os.path.exists(params_file_path):
            raise ValueError(f"not find {file_name}.pdiparams in {model_dir}")

        if not (
            os.path.exists(f"{model_dir}/{file_name}.pdmodel")
            or os.path.exists(f"{model_dir}/{file_name}.json")
        ):
            raise ValueError(
                f"neither {file_name}.json nor {file_name}.pdmodel was found in {model_dir}."
            )

        if os.path.exists(f"{model_dir}/{file_name}.json"):
            model_file_path = f"{model_dir}/{file_name}.json"
        else:
            model_file_path = f"{model_dir}/{file_name}.pdmodel"

        config = inference.Config(model_file_path, params_file_path)

        if hasattr(args, "precision"):
            if args.precision == "fp16" and args.use_tensorrt:
                precision = inference.PrecisionType.Half
            elif args.precision == "int8":
                precision = inference.PrecisionType.Int8
            else:
                precision = inference.PrecisionType.Float32
        else:

View on GitHub (pinned to 2661c7c0ef)

Solutions

1. Check the directory for the matching prefix: if inference.pdiparams exists, you need inference.pdmodel or inference.json
2. Re-export the inference model with tools/export_model.py
3. Keep the prefix consistent — do not rename model.pdiparams to inference.pdiparams without renaming the program file too

Example fix

# before
ls ./inference/rec
# inference.pdiparams  inference.pdiparams.info   (no program file) -> ValueError

# after
python tools/export_model.py -c configs/rec/PP-OCRv4/rec_PP-OCRv4_mobile.yml \
  -o Global.pretrained_model=./pretrain_models/rec_mobile \
  Global.save_inference_dir=./inference/rec

import os
def valid_infer_dir(d):
    for p in ('model', 'inference'):
        if os.path.exists(f'{d}/{p}.pdiparams'):
            return os.path.exists(f'{d}/{p}.pdmodel') or os.path.exists(f'{d}/{p}.json')
    return False
assert valid_infer_dir(model_dir), f'{model_dir} has params but no .pdmodel/.json program file'

try:
    utility.create_predictor(args, mode, logger)
except ValueError as e:
    if 'pdmodel' in str(e) or 'json' in str(e):
        raise SystemExit(f'{model_dir}: re-export with tools/export_model.py — program file missing')
    raise

When it happens

Trigger: A model dir containing inference.pdiparams but neither inference.pdmodel nor inference.json — e.g. weights copied without the program file, or an incomplete export.

Common situations: Manual copying between machines dropping the .pdmodel; export_model.py interrupted mid-write; mixing file naming (model.* vs inference.*) so params and program use different prefixes.

Related errors

• not find {file_name}.pdiparams in {model_dir}
• ${modelRole} in inference.yml must define model_name.
• ${modelRole} in inference.yml declares model_name "${declare
• The `{mask_name}` should be specified for {len(self.layers)}

AI-assisted analysis of PaddlePaddle/PaddleOCR@2661c7c0ef (2026-08-14). Data as JSON: /api/errors/5497937717bcbcb5. Report an issue: GitHub.