search

facebookresearch / detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
https://detectron2.readthedocs.io/en/latest/
Apache License 2.0
30.02k stars 7.41k forks source link

caffe2_converter.py error #832

Closed mathpopo closed 4 years ago

mathpopo commented 4 years ago
e@Nitro-AN515:~/Downloads/detectron2$ python tools/caffe2_converter.py --config-file configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml --output ./caffe2_model --run-eval MODEL.WEIGHTS detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl MODEL.DEVICE cpu [02/10 15:35:27 detectron2]: Command line arguments: Namespace(config_file='configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml', opts=['MODEL.WEIGHTS', 'detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl', 'MODEL.DEVICE', 'cpu'], output='./caffe2_model', run_eval=True) [02/10 15:35:28 d2.data.datasets.coco]: Loaded 5000 images in COCO format from datasets/coco/annotations/instances_val2017.json [02/10 15:35:28 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

[02/10 15:35:29 d2.export.caffe2_export]: Exporting a Caffe2GeneralizedRCNN model via ONNX ... /home/chenxin/Downloads/detectron2/detectron2/export/c10.py:29: 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) in [4, 5], tensor.size() /home/chenxin/Downloads/detectron2/detectron2/export/c10.py:92: TracerWarning: Converting a tensor to a Python index 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! return len(self.indices) /home/chenxin/Downloads/detectron2/detectron2/export/c10.py:344: 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 box_regression.shape[1] % 4 == 0 /home/chenxin/Downloads/detectron2/detectron2/export/c10.py:353: 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 input_tensor_mode /home/chenxin/Downloads/detectron2/detectron2/export/c10.py:359: 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 input_tensor_mode: /home/chenxin/Downloads/detectron2/detectron2/export/c10.py:402: 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! legacy_plus_one=False, /home/chenxin/anaconda/envs/detectron2/lib/python3.7/site-packages/torch/tensor.py:461: 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). 'incorrect results).', category=RuntimeWarning) /home/chenxin/Downloads/detectron2/detectron2/export/c10.py:416: TracerWarning: Converting a tensor to a Python number 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! for i, b in enumerate(int(x.item()) for x in roi_batch_splits_nms) /home/chenxin/Downloads/detectron2/detectron2/export/c10.py:73: TracerWarning: Converting a tensor to a Python index 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! data_len = len(value) Segmentation fault (core dumped)

ppwwyyxx commented 4 years ago

Should be a duplicate of https://github.com/facebookresearch/detectron2/issues/793#issuecomment-582258650