When converting the Faster RCNN model to ONNX, numerous warning messages are output, including the error 'PermissionError: [Errno 13] Permission denied: 'model.ts'.owing

[JeongHanJun]

1. Full runnable code or full changes you made:
   • https://github.com/facebookresearch/detectron2/tree/main/tools/deploy
   • I used the code used for conversion to ONNX provided by detectron2.
   • The detailed code is below.

#!/usr/bin/env python
# Copyright (c) Facebook, Inc. and its affiliates.
import argparse
import os
from typing import Dict, List, Tuple

import detectron2.data.transforms as T
import torch
from detectron2.checkpoint import DetectionCheckpointer
from detectron2.config import get_cfg
from detectron2.data import build_detection_test_loader, detection_utils
from detectron2.evaluation import COCOEvaluator, inference_on_dataset, print_csv_format
from detectron2.export import (
    dump_torchscript_IR,
    scripting_with_instances,
    STABLE_ONNX_OPSET_VERSION,
    TracingAdapter,
)
from detectron2.modeling import build_model, GeneralizedRCNN, RetinaNet
from detectron2.modeling.postprocessing import detector_postprocess
from detectron2.projects.point_rend import add_pointrend_config
from detectron2.structures import Boxes
from detectron2.utils.env import TORCH_VERSION
from detectron2.utils.file_io import PathManager
from detectron2.utils.logger import setup_logger
from torch import nn, Tensor

def setup_cfg(args):
    cfg = get_cfg()
    # cuda context is initialized before creating dataloader, so we don't fork anymore
    cfg.DATALOADER.NUM_WORKERS = 0
    add_pointrend_config(cfg)
    cfg.merge_from_file(args.config_file)
    cfg.merge_from_list(args.opts)
    cfg.freeze()
    return cfg

def export_caffe2_tracing(cfg, torch_model, inputs):
    from detectron2.export import Caffe2Tracer

    tracer = Caffe2Tracer(cfg, torch_model, inputs)
    if args.format == "caffe2":
        caffe2_model = tracer.export_caffe2()
        caffe2_model.save_protobuf(args.output)
        # draw the caffe2 graph
        caffe2_model.save_graph(os.path.join(args.output, "model.svg"), inputs=inputs)
        return caffe2_model
    elif args.format == "onnx":
        import onnx

        onnx_model = tracer.export_onnx()
        onnx.save(onnx_model, os.path.join(args.output, "model.onnx"))
    elif args.format == "torchscript":
        ts_model = tracer.export_torchscript()
        with PathManager.open(os.path.join(args.output, "model.ts"), "wb") as f:
            torch.jit.save(ts_model, f)
        dump_torchscript_IR(ts_model, args.output)

# experimental. API not yet final
def export_scripting(torch_model):
    assert TORCH_VERSION >= (1, 8)
    fields = {
        "proposal_boxes": Boxes,
        "objectness_logits": Tensor,
        "pred_boxes": Boxes,
        "scores": Tensor,
        "pred_classes": Tensor,
        "pred_masks": Tensor,
        "pred_keypoints": torch.Tensor,
        "pred_keypoint_heatmaps": torch.Tensor,
    }
    assert args.format == "torchscript", "Scripting only supports torchscript format."

    class ScriptableAdapterBase(nn.Module):
        # Use this adapter to workaround https://github.com/pytorch/pytorch/issues/46944
        # by not retuning instances but dicts. Otherwise the exported model is not deployable
        def __init__(self):
            super().__init__()
            self.model = torch_model
            self.eval()

    if isinstance(torch_model, GeneralizedRCNN):

        class ScriptableAdapter(ScriptableAdapterBase):
            def forward(
                self, inputs: Tuple[Dict[str, torch.Tensor]]
            ) -> List[Dict[str, Tensor]]:
                instances = self.model.inference(inputs, do_postprocess=False)
                return [i.get_fields() for i in instances]

    else:

        class ScriptableAdapter(ScriptableAdapterBase):
            def forward(
                self, inputs: Tuple[Dict[str, torch.Tensor]]
            ) -> List[Dict[str, Tensor]]:
                instances = self.model(inputs)
                return [i.get_fields() for i in instances]

    ts_model = scripting_with_instances(ScriptableAdapter(), fields)
    with PathManager.open(os.path.join(args.output, "model.ts"), "wb") as f:
        torch.jit.save(ts_model, f)
    dump_torchscript_IR(ts_model, args.output)
    # TODO inference in Python now missing postprocessing glue code
    return None

# experimental. API not yet final
def export_tracing(torch_model, inputs):
    assert TORCH_VERSION >= (1, 8)
    image = inputs[0]["image"]
    inputs = [{"image": image}]  # remove other unused keys

    if isinstance(torch_model, GeneralizedRCNN):

        def inference(model, inputs):
            # use do_postprocess=False so it returns ROI mask
            inst = model.inference(inputs, do_postprocess=False)[0]
            return [{"instances": inst}]

    else:
        inference = None  # assume that we just call the model directly

    traceable_model = TracingAdapter(torch_model, inputs, inference)

    if args.format == "torchscript":
        ts_model = torch.jit.trace(traceable_model, (image,))
        with PathManager.open(os.path.join(args.output, "model.ts"), "wb") as f:
            torch.jit.save(ts_model, f)
        dump_torchscript_IR(ts_model, args.output)
    elif args.format == "onnx":
        with PathManager.open(os.path.join(args.output, "model.onnx"), "wb") as f:
            torch.onnx.export(
                traceable_model, (image,), f, opset_version=STABLE_ONNX_OPSET_VERSION
            )
    logger.info("Inputs schema: " + str(traceable_model.inputs_schema))
    logger.info("Outputs schema: " + str(traceable_model.outputs_schema))

    if args.format != "torchscript":
        return None
    if not isinstance(torch_model, (GeneralizedRCNN, RetinaNet)):
        return None

    def eval_wrapper(inputs):
        """
        The exported model does not contain the final resize step, which is typically
        unused in deployment but needed for evaluation. We add it manually here.
        """
        input = inputs[0]
        instances = traceable_model.outputs_schema(ts_model(input["image"]))[0][
            "instances"
        ]
        postprocessed = detector_postprocess(instances, input["height"], input["width"])
        return [{"instances": postprocessed}]

    return eval_wrapper

def get_sample_inputs(args):

    if args.sample_image is None:
        # get a first batch from dataset
        data_loader = build_detection_test_loader(cfg, cfg.DATASETS.TEST[0])
        first_batch = next(iter(data_loader))
        return first_batch
    else:
        # get a sample data
        original_image = detection_utils.read_image(
            args.sample_image, format=cfg.INPUT.FORMAT
        )
        # Do same preprocessing as DefaultPredictor
        aug = T.ResizeShortestEdge(
            [cfg.INPUT.MIN_SIZE_TEST, cfg.INPUT.MIN_SIZE_TEST], cfg.INPUT.MAX_SIZE_TEST
        )
        height, width = original_image.shape[:2]
        image = aug.get_transform(original_image).apply_image(original_image)
        image = torch.as_tensor(image.astype("float32").transpose(2, 0, 1))

        inputs = {"image": image, "height": height, "width": width}

        # Sample ready
        sample_inputs = [inputs]
        return sample_inputs

def main() -> None:
    global logger, cfg, args
    parser = argparse.ArgumentParser(description="Export a model for deployment.")
    parser.add_argument(
        "--format",
        choices=["caffe2", "onnx", "torchscript"],
        help="output format",
        default="torchscript",
    )
    parser.add_argument(
        "--export-method",
        choices=["caffe2_tracing", "tracing", "scripting"],
        help="Method to export models",
        default="tracing",
    )
    parser.add_argument(
        "--config-file", default="", metavar="FILE", help="path to config file"
    )
    parser.add_argument(
        "--sample-image", default=None, type=str, help="sample image for input"
    )
    parser.add_argument("--run-eval", action="store_true")
    parser.add_argument("--output", help="output directory for the converted model")
    parser.add_argument(
        "opts",
        help="Modify config options using the command-line",
        default=None,
        nargs=argparse.REMAINDER,
    )
    args = parser.parse_args()
    logger = setup_logger()
    logger.info("Command line arguments: " + str(args))
    PathManager.mkdirs(args.output)
    # Disable re-specialization on new shapes. Otherwise --run-eval will be slow
    torch._C._jit_set_bailout_depth(1)

    cfg = setup_cfg(args)

    # create a torch model
    torch_model = build_model(cfg)
    DetectionCheckpointer(torch_model).resume_or_load(cfg.MODEL.WEIGHTS)
    torch_model.eval()

    # convert and save model
    if args.export_method == "caffe2_tracing":
        sample_inputs = get_sample_inputs(args)
        exported_model = export_caffe2_tracing(cfg, torch_model, sample_inputs)
    elif args.export_method == "scripting":
        exported_model = export_scripting(torch_model)
    elif args.export_method == "tracing":
        sample_inputs = get_sample_inputs(args)
        exported_model = export_tracing(torch_model, sample_inputs)

    # run evaluation with the converted model
    if args.run_eval:
        assert exported_model is not None, (
            "Python inference is not yet implemented for "
            f"export_method={args.export_method}, format={args.format}."
        )
        logger.info(
            "Running evaluation ... this takes a long time if you export to CPU."
        )
        dataset = cfg.DATASETS.TEST[0]
        data_loader = build_detection_test_loader(cfg, dataset)
        # NOTE: hard-coded evaluator. change to the evaluator for your dataset
        evaluator = COCOEvaluator(dataset, output_dir=args.output)
        metrics = inference_on_dataset(exported_model, data_loader, evaluator)
        print_csv_format(metrics)
    logger.info("Success.")

if __name__ == "__main__":
    main()  # pragma: no cover

2. What exact command you run:
   • The currently trained Faster RCNN model is saved in .pth format.
   • What I want to do is convert the trained model in .pth format to a model in .onnx format and save it.

The command to execute the above code is as follows. $ python detectron2/tools/deploy/export_model.py --sample-image sample_image.jpg --config-file unbiased-teacher-v2/faster_rcnn_R_101_DC5_3x_DPC_train_config.json --export-method tracing --output ./ MODEL.WEIGHTS unbiased-teacher-v2/faster_rcnn_R_101_DC5_3x_DPC_model.pth MODEL.DEVICE cpu

3. Full logs or other relevant observations:

   [02/02 01:19:50 detectron2]: Command line arguments: Namespace(config_file='unbiased-teacher-v2/faster_rcnn_R_101_DC5_3x_DPC_train_config.json', export_method='tracing', format='torchscript', opts=['MODEL.WEIGHTS', 'unbiased-teacher-v2/faster_rcnn_R_101_DC5_3x_DPC_model.pth', 'MODEL.DEVICE', 'cpu'], output='./', run_eval=False, sample_image='sample_image.jpg')
   [02/02 01:19:51 d2.checkpoint.detection_checkpoint]: [DetectionCheckpointer] Loading from unbiased-teacher-v2/faster_rcnn_R_101_DC5_3x_DPC_model.pth ...
   /home/appuser/detectron2_repo/detectron2/structures/image_list.py:85: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert t.shape[:-2] == tensors[0].shape[:-2], t.shape
   /home/appuser/detectron2_repo/detectron2/structures/boxes.py:155: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert tensor.dim() == 2 and tensor.size(-1) == 4, tensor.size()
   /home/appuser/detectron2_repo/detectron2/structures/boxes.py:155: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert tensor.dim() == 2 and tensor.size(-1) == 4, tensor.size()
   /home/appuser/detectron2_repo/detectron2/modeling/proposal_generator/proposal_utils.py:106: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   if not valid_mask.all():
   /home/appuser/detectron2_repo/detectron2/structures/boxes.py:191: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert torch.isfinite(self.tensor).all(), "Box tensor contains infinite or NaN!"
   /home/appuser/.local/lib/python3.8/site-packages/torch/tensor.py:587: RuntimeWarning: Iterating over a tensor might cause the trace to be incorrect. Passing a tensor of different shape won't change the number of iterations executed (and might lead to errors or silently give incorrect results).
   warnings.warn('Iterating over a tensor might cause the trace to be incorrect. '
   /home/appuser/detectron2_repo/detectron2/layers/nms.py:15: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert boxes.shape[-1] == 4
   /home/appuser/.local/lib/python3.8/site-packages/torch/__init__.py:594: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert condition, message
   /home/appuser/detectron2_repo/detectron2/layers/roi_align.py:55: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert rois.dim() == 2 and rois.size(1) == 5
   /home/appuser/detectron2_repo/detectron2/modeling/roi_heads/fast_rcnn.py:138: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   if not valid_mask.all():
   /home/appuser/detectron2_repo/detectron2/structures/boxes.py:155: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert tensor.dim() == 2 and tensor.size(-1) == 4, tensor.size()
   /home/appuser/detectron2_repo/detectron2/structures/boxes.py:191: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert torch.isfinite(self.tensor).all(), "Box tensor contains infinite or NaN!"
   /home/appuser/.local/lib/python3.8/site-packages/torch/tensor.py:587: RuntimeWarning: Iterating over a tensor might cause the trace to be incorrect. Passing a tensor of different shape won't change the number of iterations executed (and might lead to errors or silently give incorrect results).
   warnings.warn('Iterating over a tensor might cause the trace to be incorrect. '
   /home/appuser/detectron2_repo/detectron2/modeling/roi_heads/fast_rcnn.py:155: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   if num_bbox_reg_classes == 1:
   /home/appuser/detectron2_repo/detectron2/layers/nms.py:15: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert boxes.shape[-1] == 4
   /home/appuser/detectron2_repo/detectron2/structures/image_list.py:85: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert t.shape[:-2] == tensors[0].shape[:-2], t.shape
   /home/appuser/detectron2_repo/detectron2/structures/boxes.py:155: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert tensor.dim() == 2 and tensor.size(-1) == 4, tensor.size()
   /home/appuser/detectron2_repo/detectron2/structures/boxes.py:155: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert tensor.dim() == 2 and tensor.size(-1) == 4, tensor.size()
   /home/appuser/detectron2_repo/detectron2/modeling/proposal_generator/proposal_utils.py:106: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   if not valid_mask.all():
   /home/appuser/detectron2_repo/detectron2/structures/boxes.py:191: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert torch.isfinite(self.tensor).all(), "Box tensor contains infinite or NaN!"
   /home/appuser/.local/lib/python3.8/site-packages/torch/tensor.py:587: RuntimeWarning: Iterating over a tensor might cause the trace to be incorrect. Passing a tensor of different shape won't change the number of iterations executed (and might lead to errors or silently give incorrect results).
   warnings.warn('Iterating over a tensor might cause the trace to be incorrect. '
   /home/appuser/detectron2_repo/detectron2/layers/nms.py:15: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert boxes.shape[-1] == 4
   /home/appuser/.local/lib/python3.8/site-packages/torch/__init__.py:594: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert condition, message
   /home/appuser/detectron2_repo/detectron2/layers/roi_align.py:55: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert rois.dim() == 2 and rois.size(1) == 5
   /home/appuser/detectron2_repo/detectron2/modeling/roi_heads/fast_rcnn.py:138: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   if not valid_mask.all():
   /home/appuser/detectron2_repo/detectron2/structures/boxes.py:155: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert tensor.dim() == 2 and tensor.size(-1) == 4, tensor.size()
   /home/appuser/detectron2_repo/detectron2/structures/boxes.py:191: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert torch.isfinite(self.tensor).all(), "Box tensor contains infinite or NaN!"
   /home/appuser/.local/lib/python3.8/site-packages/torch/tensor.py:587: RuntimeWarning: Iterating over a tensor might cause the trace to be incorrect. Passing a tensor of different shape won't change the number of iterations executed (and might lead to errors or silently give incorrect results).
   warnings.warn('Iterating over a tensor might cause the trace to be incorrect. '
   /home/appuser/detectron2_repo/detectron2/modeling/roi_heads/fast_rcnn.py:155: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   if num_bbox_reg_classes == 1:
   /home/appuser/detectron2_repo/detectron2/layers/nms.py:15: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
   assert boxes.shape[-1] == 4
   Traceback (most recent call last):
   File "detectron2/tools/deploy/export_model.py", line 261, in <module>
   main()  # pragma: no cover
   File "detectron2/tools/deploy/export_model.py", line 240, in main
   exported_model = export_tracing(torch_model, sample_inputs)
   File "detectron2/tools/deploy/export_model.py", line 131, in export_tracing
   with PathManager.open(os.path.join(args.output, "model.ts"), "wb") as f:
   File "/home/appuser/.local/lib/python3.8/site-packages/iopath/common/file_io.py", line 1012, in open
   bret = handler._open(path, mode, buffering=buffering, **kwargs)  # type: ignore
   File "/home/appuser/.local/lib/python3.8/site-packages/iopath/common/file_io.py", line 604, in _open
   return open(  # type: ignore
   PermissionError: [Errno 13] Permission denied: 'model.ts'

4. please simplify the steps as much as possible so they do not require additional resources to run, such as a private dataset.

• The directory structure and file location were accurately confirmed to be correct.
• I don't know why a file called 'model.ts' appears. I have never saved, used or run any of these files.
• Regarding Permission denied error, we are currently working on the detectron2 docker container, and modification permission has been granted to the user appuser.

Environment:

Provide your environment information using the following command:

wget -nc -q https://github.com/facebookresearch/detectron2/raw/main/detectron2/utils/collect_env.py && python collect_env.py

The result of executing the above command is as follows.

-------------------------------  -------------------------------------------------------------------------------------------------------------------------------------------------------
sys.platform                     linux
Python                           3.8.10 (default, Nov 22 2023, 10:22:35) [GCC 9.4.0]
numpy                            1.24.4
detectron2                       0.6 @/home/appuser/detectron2_repo/detectron2
detectron2._C                    not built correctly: /home/appuser/detectron2_repo/detectron2/_C.cpython-38-x86_64-linux-gnu.so: undefined symbol: _ZNK2at10TensorBase8data_ptrIdEEPT_v
Compiler ($CXX)                  c++ (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
CUDA compiler                    Build cuda_11.1.TC455_06.29190527_0
detectron2 arch flags            3.5, 3.7, 5.0, 5.2, 5.3, 6.0, 6.1, 7.0, 7.5
DETECTRON2_ENV_MODULE            <not set>
PyTorch                          1.8.1+cu102 @/home/appuser/.local/lib/python3.8/site-packages/torch
PyTorch debug build              False
torch._C._GLIBCXX_USE_CXX11_ABI  False
GPU available                    Yes
GPU 0,1                          NVIDIA TITAN RTX (arch=7.5)
Driver version                   525.125.06
CUDA_HOME                        /usr/local/cuda
TORCH_CUDA_ARCH_LIST             Kepler;Kepler+Tesla;Maxwell;Maxwell+Tegra;Pascal;Volta;Turing
Pillow                           10.2.0
torchvision                      0.9.1+cu102 @/home/appuser/.local/lib/python3.8/site-packages/torchvision
torchvision arch flags           3.5, 5.0, 6.0, 7.0, 7.5
fvcore                           0.1.5.post20221221
iopath                           0.1.9
cv2                              4.2.0
-------------------------------  -------------------------------------------------------------------------------------------------------------------------------------------------------
PyTorch built with:
  - GCC 7.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v1.7.0 (Git Hash 7aed236906b1f7a05c0917e5257a1af05e9ff683)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 10.2
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70
  - CuDNN 7.6.5
  - Magma 2.5.2
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=10.2, CUDNN_VERSION=7.6.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.8.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, 

Testing NCCL connectivity ... this should not hang.
NCCL succeeded.

I don't know why so many warnings occurred, and I don't know how to solve it. Are various operations used in the Faster RCNN model not supported? How can I convert the trained Faster RCNN model to ONNX?? If there is anyone who has successfully converted the Faster RCNN model to ONNX format, I would appreciate it if you could provide detailed advice.

And I have no idea about 'model.ts'. Why does this error occur?? What role does ‘model.ts’ play when converting to ONNX?

[github-actions[bot]]

You've chosen to report an unexpected problem or bug. Unless you already know the root cause of it, please include details about it by filling the issue template. The following information is missing: "Instructions To Reproduce the Issue and Full Logs";

[github-actions[bot]]

Requested information was not provided in 7 days, so we're closing this issue.

Please open new issue if information becomes available. Otherwise, use github discussions for free-form discussions.