PaddlePaddle
3d_vision PointNet++分类训练报错UnavailableError: There are no kernels which are registered in the fill_constant operator.
刚入门小白，遇到了问题恳请各位大神帮忙！谢谢
AI Studio
PaddlePaddle2.0.0
3d_vision PointNet++分类训练报错UnavailableError: There are no kernels which are registered in the fill_constant operator.具体如下
aistudio@jupyter-622623-1481923:~/PointNet++$ python train_cls.py --model=MSG --batch_size=16 --save_dir=checkpoints_msg_cls
2021-02-02 16:17:38,539-INFO: ----------- Configuration Arguments -----------
2021-02-02 16:17:38,539-INFO: batch_size: 16
2021-02-02 16:17:38,539-INFO: bn_momentum: 0.99
2021-02-02 16:17:38,539-INFO: data_dir: dataset/ModelNet40/modelnet40_ply_hdf5_2048
2021-02-02 16:17:38,539-INFO: decay_steps: 12500
2021-02-02 16:17:38,540-INFO: enable_ce: False
2021-02-02 16:17:38,540-INFO: epoch: 201
2021-02-02 16:17:38,540-INFO: log_interval: 1
2021-02-02 16:17:38,540-INFO: lr: 0.01
2021-02-02 16:17:38,540-INFO: lr_decay: 0.7
2021-02-02 16:17:38,540-INFO: model: MSG
2021-02-02 16:17:38,540-INFO: num_classes: 40
2021-02-02 16:17:38,540-INFO: num_points: 2048
2021-02-02 16:17:38,540-INFO: resume: None
2021-02-02 16:17:38,540-INFO: save_dir: checkpoints_msg_cls
2021-02-02 16:17:38,540-INFO: use_gpu: True
2021-02-02 16:17:38,540-INFO: weight_decay: 1e-05
2021-02-02 16:17:38,540-INFO: ------------------------------------------------
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layers/math_op_patch.py:298: UserWarning: /home/aistudio/PointNet++/models/pointnet2_modules.py:53
The behavior of expression A - B has been unified with elementwise_sub(X, Y, axis=-1) from Paddle 2.0. If your code works well in the older versions but crashes in this version, try to use elementwise_sub(X, Y, axis=0) instead of A - B. This transitional warning will be dropped in the future.
op_type, op_type, EXPRESSION_MAP[method_name]))
W0202 16:17:39.180770 1631 device_context.cc:362] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 10.1, Runtime API Version: 10.1
W0202 16:17:39.185834 1631 device_context.cc:372] device: 0, cuDNN Version: 7.6.
Traceback (most recent call last):
File "train_cls.py", line 308, in
File "train_cls.py", line 308, in <module>
train()
File "train_cls.py", line 166, in train
optimizer.minimize(train_loss, parameter_list=params)
File "</opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/decorator.py:decorator-gen-104>", line 2, in minimize
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/base.py", line 260, in __impl__
return func(*args, **kwargs)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/optimizer.py", line 951, in minimize
loss, startup_program=startup_program, params_grads=params_grads)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/optimizer.py", line 862, in apply_optimize
optimize_ops = self.apply_gradients(params_grads)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/optimizer.py", line 836, in apply_gradients
optimize_ops = self._create_optimization_pass(params_grads)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/optimizer.py", line 664, in _create_optimization_pass
[p[0] for p in parameters_and_grads if p[0].trainable])
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/optimizer.py", line 2048, in _create_accumulators
type=core.VarDesc.VarType.LOD_TENSOR, device='cpu')
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/optimizer.py", line 577, in _add_accumulator
var, initializer=Constant(value=float(fill_value)))
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/layer_helper_base.py", line 448, in set_variable_initializer
initializer=initializer)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/framework.py", line 2851, in create_var
kwargs['initializer'](var, self)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/initializer.py", line 165, in __call__
stop_gradient=True)
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/framework.py", line 3104, in _prepend_op
attrs=kwargs.get("attrs", None))
File "/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/framework.py", line 2102, in __init__
for frame in traceback.extract_stack():
UnavailableError: There are no kernels which are registered in the fill_constant operator.
[Hint: Expected kernels_iter != all_op_kernels.end(), but received kernels_iter == all_op_kernels.end().] (at /paddle/paddle/fluid/framework/operator.cc:1179)
[operator < fill_constant > error]
aistudio@jupyter-622623-1481923:~/PointNet++$
[Hint: Expected kernel_iter != kernels.end(), but received kernel_iter == kernels.end().] (at /paddle/paddle/fluid/imperative/prepared_operator.cc:419) [operator < transpose2 > error]
我也一样
Traceback (most recent call last):
File "tools/train.py", line 209, in
