ghost
commented
2 years ago Meanwhile, I have tried tracing method, after the above caffe2_tracing method.
Instructions To Reproduce the 🐛 Bug:
-
Full runnable code or full changes you made:
I use the original repo and do not change anything. -
What exact command do you run:
export DETECTRON2_DATASETS=/data/datasets/
python3 export_model.py \ --config-file ../../configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x.yaml \ --output /data/output/ \ --export-method tracing \ --format onnx \ MODEL.WEIGHTS /data/model/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x/139514544/model_final_dbfeb4.pkl \ MODEL.DEVICE cpu
I have already prepared the COCO dataset in `/data/datasets/`.
4. __Full logs__ or other relevant observations:| [06/23 06:47:50 detectron2]: Command line arguments: Namespace(format='onnx', export_method='tracing', config_file='../../configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x.yaml', sample_image=None, run_eval=False, output='/data/output/', opts=['MODEL.WEIGHTS', '/data/model/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x/139514544/model_final_dbfeb4.pkl', 'MODEL.DEVICE', 'cpu']) [W init.cpp:759] Warning: Use _jit_set_fusion_strategy, bailout depth is deprecated. Setting to (STATIC, 1) (function operator()) [06/23 06:47:52 d2.data.datasets.coco]: Loaded 5000 images in COCO format from /data/datasets/coco/annotations/instances_val2017.json [06/23 06:47:52 d2.data.datasets.coco]: Loaded 5000 images with semantic segmentation from /data/datasets/coco/val2017 [06/23 06:47:52 d2.data.build]: Distribution of instances among all 80 categories: | category | #instances | category | #instances | category | #instances |
|---|---|---|---|---|---|---|
| person | 10777 | bicycle | 314 | car | 1918 | |
| motorcycle | 367 | airplane | 143 | bus | 283 | |
| train | 190 | truck | 414 | boat | 424 | |
| traffic light | 634 | fire hydrant | 101 | stop sign | 75 | |
| parking meter | 60 | bench | 411 | bird | 427 | |
| cat | 202 | dog | 218 | horse | 272 | |
| sheep | 354 | cow | 372 | elephant | 252 | |
| bear | 71 | zebra | 266 | giraffe | 232 | |
| backpack | 371 | umbrella | 407 | handbag | 540 | |
| tie | 252 | suitcase | 299 | frisbee | 115 | |
| skis | 241 | snowboard | 69 | sports ball | 260 | |
| kite | 327 | baseball bat | 145 | baseball gl.. | 148 | |
| skateboard | 179 | surfboard | 267 | tennis racket | 225 | |
| bottle | 1013 | wine glass | 341 | cup | 895 | |
| fork | 215 | knife | 325 | spoon | 253 | |
| bowl | 623 | banana | 370 | apple | 236 | |
| sandwich | 177 | orange | 285 | broccoli | 312 | |
| carrot | 365 | hot dog | 125 | pizza | 284 | |
| donut | 328 | cake | 310 | chair | 1771 | |
| couch | 261 | potted plant | 342 | bed | 163 | |
| dining table | 695 | toilet | 179 | tv | 288 | |
| laptop | 231 | mouse | 106 | remote | 283 | |
| keyboard | 153 | cell phone | 262 | microwave | 55 | |
| oven | 143 | toaster | 9 | sink | 225 | |
| refrigerator | 126 | book | 1129 | clock | 267 | |
| vase | 274 | scissors | 36 | teddy bear | 190 | |
| hair drier | 11 | toothbrush | 57 | |||
| total | 36335 |
[06/23 06:47:52 d2.data.dataset_mapper]: [DatasetMapper] Augmentations used in inference: [ResizeShortestEdge(short_edge_length=(800, 800), max_size=1333, sample_style='choice')]
[06/23 06:47:52 d2.data.common]: Serializing 5000 elements to byte tensors and concatenating them all ...
[06/23 06:47:53 d2.data.common]: Serialized dataset takes 19.52 MiB
/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/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
/usr/local/lib/python3.10/dist-packages/torch/nn/functional.py:2498: UserWarning: floordiv is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
_verify_batch_size([input.size(0) * input.size(1) // num_groups, num_groups] + list(input.size()[2:]))
/usr/local/lib/python3.10/dist-packages/torch/functional.py:568: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:2228.)
return _VF.meshgrid(tensors, kwargs) # type: ignore[attr-defined]
/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/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()
/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/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():
/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/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!"
/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/detectron2/structures/boxes.py:192: TracerWarning: 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).
h, w = box_size
/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/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
/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/detectron2/structures/instances.py:74: TracerWarning: Using len to get tensor shape might cause the trace to be incorrect. Recommended usage would be tensor.shape[0]. Passing a tensor of different shape might lead to errors or silently give incorrect results.
data_len = len(value)
/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/detectron2/modeling/poolers.py:231: 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 len(box_lists) == x[0].size(
/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/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
/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/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():
/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/detectron2/modeling/roi_heads/fast_rcnn.py:143: UserWarning: floordiv is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
num_bbox_reg_classes = boxes.shape[1] // 4
/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/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:
/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/detectron2/modeling/roi_heads/mask_head.py:139: 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 cls_agnostic_mask:
Traceback (most recent call last):
File "/data/detectron2/tools/deploy/export_model.py", line 221, in
5. please simplify the steps as much as possible so they do not require additional resources to
run, such as a private dataset.
## Expected behavior:
I expected that the official code [export_model.py](https://github.com/facebookresearch/detectron2/blob/main/tools/deploy/export_model.py) can help me to export onnx model.
## Environment:
Provide your environment information using the following command:(same as the above)
If your issue looks like an installation issue / environment issue,
please first try to solve it yourself with the instructions in
https://detectron2.readthedocs.io/tutorials/install.html#common-installation-issues
shining-love
FrancescoMandru
azhurkevich
VladMVLX
anshudaur
frankvp11
suhanshaikh33
vincedupuis
thiagocrepaldi
ppwwyyxx
solarflarefx
jonas-doevenspeck
htlbayytq
Zalways
Instructions To Reproduce the 🐛 Bug:
Full runnable code or full changes you made:
What exact command do you run:
python3 export_model.py \ --config-file ../../configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x.yaml \ --output /data/output/ \ --export-method caffe2_tracing \ --format onnx \ MODEL.WEIGHTS /data/model/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x/139514544/model_final_dbfeb4.pkl \ MODEL.DEVICE cpu
[06/23 06:22:35 d2.data.dataset_mapper]: [DatasetMapper] Augmentations used in inference: [ResizeShortestEdge(short_edge_length=(800, 800), max_size=1333, sample_style='choice')] [06/23 06:22:35 d2.data.common]: Serializing 5000 elements to byte tensors and concatenating them all ... [06/23 06:22:35 d2.data.common]: Serialized dataset takes 19.52 MiB Traceback (most recent call last): File "/data/detectron2/tools/deploy/export_model.py", line 217, in
exported_model = export_caffe2_tracing(cfg, torch_model, sample_inputs)
File "/data/detectron2/tools/deploy/export_model.py", line 36, in export_caffe2_tracing
from detectron2.export import Caffe2Tracer
ImportError: cannot import name 'Caffe2Tracer' from 'detectron2.export' (/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/detectron2/export/init.py)
sys.platform linux Python 3.10.4 (main, Apr 2 2022, 09:04:19) [GCC 11.2.0] numpy 1.22.4 detectron2 0.6 @/usr/local/lib/python3.10/dist-packages/detectron2-0.6-py3.10-linux-x86_64.egg/detectron2 Compiler GCC 11.2 CUDA compiler not available DETECTRON2_ENV_MODULE
PyTorch 1.11.0+cpu @/usr/local/lib/python3.10/dist-packages/torch
PyTorch debug build False
GPU available No: torch.cuda.is_available() == False
Pillow 9.1.1
torchvision 0.12.0+cpu @/usr/local/lib/python3.10/dist-packages/torchvision
fvcore 0.1.5.post20220512
iopath 0.1.9
cv2 4.6.0
PyTorch built with:
If your issue looks like an installation issue / environment issue, please first try to solve it yourself with the instructions in https://detectron2.readthedocs.io/tutorials/install.html#common-installation-issues
Finally, thanks to your effects that contribute such excellent repo!