ValueError: negative dimensions are not allowed

[ljdhhhhh]

When I run test.py, this error will appear at the end

[lfxx]

When I run test.py, this error will appear at the end

i get this error too.and i solve it by modify the test.py code refer to openpcdet

[LinearBasis]

You should figure out where your negative dimensions come from. I had a similar error; it turned out that the box type was not specified in the config, which is why the size was set to -1. Change the config type passed here (https://github.com/PJLab-ADG/DetZero/blob/12c1358de8bcd0a0f5d51312a0a976e388a4d2ba/detection/detzero_det/datasets/waymo/waymo_eval_detection.py#L87) to the one you need

[zw-92]

You should figure out where your negative dimensions come from. I had a similar error; it turned out that the box type was not specified in the config, which is why the size was set to -1. Change the config type passed here (

https://github.com/PJLab-ADG/DetZero/blob/12c1358de8bcd0a0f5d51312a0a976e388a4d2ba/detection/detzero_det/datasets/waymo/waymo_eval_detection.py#L87 ) to the one you need

Hello, may I ask where the specific configuration needs to be changed. thank.

[llz666ha]

Traceback (most recent call last): File "test.py", line 203, in main() File "test.py", line 199, in main eval_single_ckpt(model, test_loader, args, eval_output_dir, logger, epoch_id, dist_test=dist_test) File "test.py", line 64, in eval_single_ckpt eval_utils.eval_one_epoch( File "/home/ubt-346/devdata1/llz/DetZero/detection/tools/eval_utils.py", line 141, in eval_one_epoch result_str, result_dict = dataset.evaluation( File "/home/ubt-346/devdata1/llz/DetZero/detection/detzero_det/datasets/waymo/waymo_dataset.py", line 126, in evaluation ap_result_str, ap_dict = waymo_eval(eval_det_annos, eval_gt_annos) File "/home/ubt-346/devdata1/llz/DetZero/detection/detzero_det/datasets/waymo/waymo_dataset.py", line 112, in waymo_eval ap_dict = eval.waymo_evaluation( File "/home/ubt-346/devdata1/llz/DetZero/detection/detzero_det/datasets/waymo/waymo_eval_detection.py", line 256, in waymo_evaluation metrics = self.build_graph(graph, config_type) File "/home/ubt-346/devdata1/llz/DetZero/detection/detzero_det/datasets/waymo/waymo_eval_detection.py", line 159, in build_graph metrics = detection_metrics.get_detection_metric_ops( File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/waymo_open_dataset/metrics/python/detection_metrics.py", line 154, in get_detection_metric_ops variable_and_update_ops[name] = _update(name, update, init_shape, dtype) File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/waymo_open_dataset/metrics/python/detection_metrics.py", line 40, in _update v = tf.compat.v1.get_local_variable( File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py", line 1727, in get_local_variable return get_variable( File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py", line 1579, in get_variable return get_variable_scope().get_variable( File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py", line 1322, in get_variable return var_store.get_variable( File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py", line 578, in get_variable return _true_getter( File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py", line 531, in _true_getter return self._get_single_variable( File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py", line 952, in _get_single_variable v = variables.VariableV1( File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variables.py", line 260, in call return cls._variable_v1_call(*args, **kwargs) File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variables.py", line 206, in _variable_v1_call return previous_getter( File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variables.py", line 199, in previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs) File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py", line 2612, in default_variable_creator return resource_variable_ops.ResourceVariable( File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variables.py", line 264, in call return super(VariableMetaclass, cls).call(*args, **kwargs) File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/resource_variable_ops.py", line 1584, in init self._init_from_args( File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/resource_variable_ops.py", line 1722, in _init_from_args initial_value = initial_value() File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/waymo_open_dataset/metrics/python/detection_metrics.py", line 39, in initializer = lambda: tf.constant([], shape=init_shape, dtype=dtype) File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py", line 264, in constant return _constant_impl(value, dtype, shape, name, verify_shape=False, File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py", line 281, in _constant_impl tensor_util.make_tensor_proto( File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/framework/tensor_util.py", line 455, in make_tensor_proto nparray = np.empty(shape, dtype=np_dt) ValueError: negative dimensions are not allowed

Is this related to data sets? Instead of using the complete waymo dataset, I downloaded only part of v1.4.0, and then modified the contents of train.txt, val.txt, and text.txt. During the training, there was an error report of "AttributeError:'str 'object has no attribute' exists'". I solved it by modifying waymo_utils. At the test step, the error occurred again in the evaluation part.

[llz666ha]

When I use the pre training model： Traceback (most recent call last): File "test.py", line 203, in main() File "test.py", line 199, in main eval_single_ckpt(model, test_loader, args, eval_output_dir, logger, epoch_id, dist_test=dist_test) File "test.py", line 64, in eval_single_ckpt eval_utils.eval_one_epoch( File "/home/ubt-346/devdata1/llz/DetZero/detection/tools/eval_utils.py", line 141, in eval_one_epoch result_str, result_dict = dataset.evaluation( File "/home/ubt-346/devdata1/llz/DetZero/detection/detzero_det/datasets/waymo/waymo_dataset.py", line 126, in evaluation ap_result_str, ap_dict = waymo_eval(eval_det_annos, eval_gt_annos) File "/home/ubt-346/devdata1/llz/DetZero/detection/detzero_det/datasets/waymo/waymo_dataset.py", line 112, in waymo_eval ap_dict = eval.waymo_evaluation( File "/home/ubt-346/devdata1/llz/DetZero/detection/detzero_det/datasets/waymo/waymo_eval_detection.py", line 223, in waymo_evaluation print(f"Prediction boxes3d min values: {pd_boxes3d.min(axis=0)}") File "/home/ubt-346/anaconda3/envs/detzero/lib/python3.8/site-packages/numpy/core/_methods.py", line 43, in _amin return umr_minimum(a, axis, None, out, keepdims, initial, where) ValueError: zero-size array to reduction operation minimum which has no identity

[XuMian-xm]

I got this error when I run train.py

Traceback (most recent call last): File "train.py", line 215, in main() File "train.py", line 205, in main repeat_eval_ckpt( File "/root/DetZero/detection/tools/test.py", line 122, in repeat_eval_ckpt tb_dict = eval_utils.eval_one_epoch( File "/root/DetZero/detection/tools/eval_utils.py", line 140, in eval_one_epoch result_str, result_dict = dataset.evaluation( File "/root/DetZero/detection/detzero_det/datasets/waymo/waymo_dataset.py", line 126, in evaluation ap_result_str, ap_dict = waymo_eval(eval_det_annos, eval_gt_annos) File "/root/DetZero/detection/detzero_det/datasets/waymo/waymo_dataset.py", line 112, in waymo_eval ap_dict = eval.waymo_evaluation( File "/root/DetZero/detection/detzero_det/datasets/waymo/waymo_eval_detection.py", line 232, in waymo_evaluation metrics = self.build_graph(graph, config_type) File "/root/DetZero/detection/detzero_det/datasets/waymo/waymo_eval_detection.py", line 148, in build_graph metrics = detection_metrics.get_detection_metric_ops( File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/waymo_open_dataset/metrics/python/detection_metrics.py", line 154, in get_detection_metric_ops variable_and_update_ops[name] = _update(name, update, init_shape, dtype) File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/waymo_open_dataset/metrics/python/detection_metrics.py", line 40, in _update v = tf.compat.v1.get_local_variable( File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py", line 1727, in get_local_variable return get_variable( File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py", line 1579, in get_variable return get_variable_scope().get_variable( File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py", line 1322, in get_variable return var_store.get_variable( File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py", line 578, in get_variable return _true_getter( File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py", line 531, in _true_getter return self._get_single_variable( File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py", line 952, in _get_single_variable v = variables.VariableV1( File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variables.py", line 260, in call return cls._variable_v1_call(*args, **kwargs) File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variables.py", line 206, in _variable_v1_call return previous_getter( File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variables.py", line 199, in previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs) File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variable_scope.py", line 2612, in default_variable_creator return resource_variable_ops.ResourceVariable( File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/variables.py", line 264, in call return super(VariableMetaclass, cls).call(*args, **kwargs) File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/resource_variable_ops.py", line 1584, in init self._init_from_args( File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/ops/resource_variable_ops.py", line 1722, in _init_from_args initial_value = initial_value() File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/waymo_open_dataset/metrics/python/detection_metrics.py", line 39, in initializer = lambda: tf.constant([], shape=init_shape, dtype=dtype) File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py", line 264, in constant return _constant_impl(value, dtype, shape, name, verify_shape=False, File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/framework/constant_op.py", line 281, in _constant_impl tensor_util.make_tensor_proto( File "/root/miniconda3/envs/detzero/lib/python3.8/site-packages/tensorflow/python/framework/tensor_util.py", line 455, in make_tensor_proto nparray = np.empty(shape, dtype=np_dt) ValueError: negative dimensions are not allowed