python3 tools/train.py -c configs/ppyolo/ppyolov2_r50vd_dcn_365e_coco.yml
/home/max/anaconda3/lib/python3.8/site-packages/matplotlib/__init__.py:202: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
if LooseVersion(module.__version__) < minver:
/home/max/anaconda3/lib/python3.8/site-packages/setuptools/_distutils/version.py:351: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
other = LooseVersion(other)
/home/max/anaconda3/lib/python3.8/site-packages/matplotlib/backend_bases.py:60: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
if LooseVersion(PILLOW_VERSION) >= "3.4":
/home/max/anaconda3/lib/python3.8/site-packages/setuptools/_distutils/version.py:351: DeprecationWarning: distutils Version classes are deprecated. Use packaging.version instead.
other = LooseVersion(other)
/home/max/anaconda3/lib/python3.8/site-packages/paddle/tensor/creation.py:130: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe.
Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations
if data.dtype == np.object:
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
[02/16 18:03:54] ppdet.utils.checkpoint INFO: ['backbone.res5.res5a.branch2b.norm._mean', 'backbone.res5.res5a.branch2b.norm._variance', 'backbone.res5.res5b.branch2b.norm.bias', 'backbone.res5.res5b.branch2b.norm.weight', 'backbone.res5.res5c.branch2c.conv.weight', 'backbone.res5.res5c.branch2c.norm._mean'] in pretrained weight is not used in the model, and its will not be loaded
[02/16 18:03:54] ppdet.utils.checkpoint INFO: Finish loading model weights: /home/max/.cache/paddle/weights/ResNet50_vd_ssld_pretrained.pdparams
[02/16 18:04:14] ppdet.engine INFO: Epoch: [0] [0/2] learning_rate: 0.000000 loss_xy: 1.019501 loss_wh: 2.678878 loss_iou: 3.295408 loss_iou_aware: 0.818068 loss_obj: 4319.671875 loss_cls: 1.567525 loss: 4329.051270 eta: 2 days, 5:38:53 batch_cost: 19.3133 data_cost: 1.2697 ips: 0.6213 images/s
已杀死