量化报错ValueError: Unsupport file -0.886949! 不做量化可以完成编译

[cwr250]

量化报错ValueError: Unsupport file -0.886949! 不做量化可以完成编译。请问下是什么原因引起的呢？

报错信息如下： onnx::MatMul_10842 0.27 0.24 16.054, 14.695 model.encoders.48.self_attn.fsmn_block.weight 0.67 0.99 16.378 onnx::MatMul_11042 0.23 0.23 12.550 onnx::MatMul_11064 0.16 0.16 20.878, 20.629, 20.454, 20.446, 20.082 onnx::MatMul_11084 0.16 0.13 23.561, 23.303, 23.017, 22.497 onnx::MatMul_11104 0.16 0.13 24.980, 22.636 onnx::MatMul_11124 0.16 0.16 32.679, 32.335, 32.284, 32.228, 32.042 onnx::MatMul_11144 0.16 0.14 28.649, 27.235, 27.162, 26.938 onnx::MatMul_11164 0.16 0.14 27.306 onnx::MatMul_11184 0.16 0.13 15.910 onnx::MatMul_11424 0.16 0.14 -12.338 onnx::MatMul_11444 0.18 0.27 -14.326 D sparse_weight ... E build: Unsupport file -0.886949! W build: ===================== WARN(3) ===================== E rknn-toolkit2 version: 2.2.0 E build: Traceback (most recent call last): File "rknn/api/rknn_log.py", line 309, in rknn.api.rknn_log.error_catch_decorator.error_catch_wrapper File "rknn/api/rknn_base.py", line 1941, in rknn.api.rknn_base.RKNNBase.build File "rknn/api/graph_optimizer.py", line 2304, in rknn.api.graph_optimizer.GraphOptimizer.sparse_weight File "rknn/api/sparse_weight.py", line 528, in rknn.api.sparse_weight.sparse_weight File "rknn/api/sparse_weight.py", line 75, in rknn.api.sparse_weight._range_input File "rknn/api/rknn_log.py", line 95, in rknn.api.rknn_log.RKNNLog.e ValueError: Unsupport file -0.886949!

I ===================== WARN(0) ===================== E rknn-toolkit2 version: 2.2.0 Traceback (most recent call last): File "rknn/api/rknn_log.py", line 309, in rknn.api.rknn_log.error_catch_decorator.error_catch_wrapper File "rknn/api/rknn_base.py", line 1941, in rknn.api.rknn_base.RKNNBase.build File "rknn/api/graph_optimizer.py", line 2304, in rknn.api.graph_optimizer.GraphOptimizer.sparse_weight File "rknn/api/sparse_weight.py", line 528, in rknn.api.sparse_weight.sparse_weight File "rknn/api/sparse_weight.py", line 75, in rknn.api.sparse_weight._range_input File "rknn/api/rknn_log.py", line 95, in rknn.api.rknn_log.RKNNLog.e ValueError: Unsupport file -0.886949!

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/will/SenseVoice-ONNX/sensevoice/convert.py", line 31, in ret = rknn.build(dataset=DATASET_PATH, do_quantization=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/will/miniforge3/envs/rknn/lib/python3.11/site-packages/rknn/api/rknn.py", line 192, in build return self.rknn_base.build(do_quantization=do_quantization, dataset=dataset, expand_batch_size=rknn_batch_size) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "rknn/api/rknn_log.py", line 314, in rknn.api.rknn_log.error_catch_decorator.error_catch_wrapper File "rknn/api/rknn_log.py", line 95, in rknn.api.rknn_log.RKNNLog.e ValueError: Traceback (most recent call last): File "rknn/api/rknn_log.py", line 309, in rknn.api.rknn_log.error_catch_decorator.error_catch_wrapper File "rknn/api/rknn_base.py", line 1941, in rknn.api.rknn_base.RKNNBase.build File "rknn/api/graph_optimizer.py", line 2304, in rknn.api.graph_optimizer.GraphOptimizer.sparse_weight File "rknn/api/sparse_weight.py", line 528, in rknn.api.sparse_weight.sparse_weight File "rknn/api/sparse_weight.py", line 75, in rknn.api.sparse_weight._range_input File "rknn/api/rknn_log.py", line 95, in rknn.api.rknn_log.RKNNLog.e ValueError: Unsupport file -0.886949!

[zen-xingle]

量化数据集里面，有名字异常的文件名

[cwr250]

量化数据集里面，有名字异常的文件名

确实是这个原因，找到问题所在了，多谢