Some question about evaluation

[YuRui-Learning]

hello, when i run test or train function , i will also meet this question in eval. It is some issue aboud tensorflow ? Traceback (most recent call last): File "eval.py", line 207, in <module> main() File "eval.py", line 203, in main eval_single_ckpt(model, test_loader, args, eval_output_dir, logger, epoch_id, dist_test=dist_test) File "eval.py", line 65, in eval_single_ckpt eval_result.eval_one_epoch( File "/root/MSF/tools/eval_utils/eval_result.py", line 62, in eval_one_epoch result_str, result_dict = dataset.evaluation( File "/root/MSF/tools/../pcdet/datasets/waymo/waymo_dataset.py", line 476, in evaluation ap_result_str, ap_dict = waymo_eval(eval_det_annos, eval_gt_annos) File "/root/MSF/tools/../pcdet/datasets/waymo/waymo_dataset.py", line 459, in waymo_eval ap_dict = eval.waymo_evaluation( File "/root/MSF/tools/../pcdet/datasets/waymo/waymo_eval.py", line 211, in waymo_evaluation metrics = self.build_graph(graph) File "/root/MSF/tools/../pcdet/datasets/waymo/waymo_eval.py", line 127, in build_graph metrics = detection_metrics.get_detection_metric_ops( File "/root/.local/lib/python3.8/site-packages/waymo_open_dataset/metrics/python/detection_metrics.py", line 134, in get_detection_metric_ops ground_truth_speed = tf.zeros((num_gt_boxes, 2), tf.float32) File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/util/dispatch.py", line 206, in wrapper return target(*args, **kwargs) File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/ops/array_ops.py", line 2912, in wrapped tensor = fun(*args, **kwargs) File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/ops/array_ops.py", line 2962, in zeros output = _constant_if_small(zero, shape, dtype, name) File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/ops/array_ops.py", line 2897, in _constant_if_small if np.prod(shape) < 1000: File "<__array_function__ internals>", line 200, in prod File "/usr/local/lib/python3.8/dist-packages/numpy/core/fromnumeric.py", line 3076, in prod return _wrapreduction(a, np.multiply, 'prod', axis, dtype, out, File "/usr/local/lib/python3.8/dist-packages/numpy/core/fromnumeric.py", line 86, in _wrapreduction return ufunc.reduce(obj, axis, dtype, out, **passkwargs) File "/usr/local/lib/python3.8/dist-packages/tensorflow/python/framework/ops.py", line 867, in __array__ raise NotImplementedError( NotImplementedError: Cannot convert a symbolic Tensor (strided_slice:0) to a numpy array. This error may indicate that you're trying to pass a Tensor to a NumPy call, which is not supported eval: 0%| | 0/4931 [02:31<?, ?it/s]

[github-actions[bot]]

This issue is stale because it has been open for 30 days with no activity.

[github-actions[bot]]

This issue was closed because it has been inactive for 14 days since being marked as stale.