该问题是因为 rknn-toolkit2 已经不支持了facenet的模型转换吗?
W __init__: rknn-toolkit2 version: 1.3.0-11912b58
W config: 'target_platform' is None, use rk3566 as default, Please set according to the actual platform!
config done
--> Loading model
W load_tensorflow: inputs name should be a tensor name instead of node name
2022-07-14 16:26:03.647684: I tensorflow/tools/graph_transforms/transform_graph.cc:317] Applying strip_unused_nodes
2022-07-14 16:26:03.787548: I tensorflow/tools/graph_transforms/transform_graph.cc:317] Applying sort_by_execution_order
2022-07-14 16:26:03.867908: I tensorflow/tools/graph_transforms/transform_graph.cc:317] Applying fold_constants
2022-07-14 16:26:04.358690: I tensorflow/tools/graph_transforms/transform_graph.cc:317] Applying fold_batch_norms
2022-07-14 16:26:04.506355: I tensorflow/tools/graph_transforms/transform_graph.cc:317] Applying fold_old_batch_norms
2022-07-14 16:26:05.596624: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 AVX512F FMA
2022-07-14 16:26:05.620279: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2200000000 Hz
2022-07-14 16:26:05.622388: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x556b7a5042e0 executing computations on platform Host. Devices:
2022-07-14 16:26:05.622431: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): <undefined>, <undefined>
E load_tensorflow: Catch exception when loading tensorflow model: 20180402-114759/20180402-114759.pb!
E load_tensorflow: Traceback (most recent call last):
E load_tensorflow: File "/home/ame/anaconda3/envs/npu/lib/python3.6/site-packages/tensorflow/python/framework/importer.py", line 427, in import_graph_def
E load_tensorflow: graph._c_graph, serialized, options) # pylint: disable=protected-access
E load_tensorflow: tensorflow.python.framework.errors_impl.InvalidArgumentError: Node 'InceptionResnetV1/Bottleneck/BatchNorm/cond_1/AssignMovingAvg_1/Switch' expects to be colocated with unknown node 'InceptionResnetV1/Bottleneck/BatchNorm/moving_variance'
E load_tensorflow: During handling of the above exception, another exception occurred:
E load_tensorflow: Traceback (most recent call last):
E load_tensorflow: File "rknn/api/rknn_base.py", line 990, in rknn.api.rknn_base.RKNNBase.load_tensorflow
E load_tensorflow: File "rknn/base/convertor/tensorflow2onnx/tf2onnx/convert.py", line 589, in rknn.base.convertor.tensorflow2onnx.tf2onnx.convert.from_graph_def
E load_tensorflow: File "rknn/base/convertor/tensorflow2onnx/tf2onnx/convert.py", line 590, in rknn.base.convertor.tensorflow2onnx.tf2onnx.convert.from_graph_def
E load_tensorflow: File "rknn/base/convertor/tensorflow2onnx/tf2onnx/convert.py", line 591, in rknn.base.convertor.tensorflow2onnx.tf2onnx.convert.from_graph_def
E load_tensorflow: File "rknn/base/convertor/tensorflow2onnx/tf2onnx/convert.py", line 592, in rknn.base.convertor.tensorflow2onnx.tf2onnx.convert.from_graph_def
E load_tensorflow: File "/home/ame/anaconda3/envs/npu/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
E load_tensorflow: return func(*args, **kwargs)
E load_tensorflow: File "/home/ame/anaconda3/envs/npu/lib/python3.6/site-packages/tensorflow/python/framework/importer.py", line 431, in import_graph_def
E load_tensorflow: raise ValueError(str(e))
E load_tensorflow: ValueError: Node 'InceptionResnetV1/Bottleneck/BatchNorm/cond_1/AssignMovingAvg_1/Switch' expects to be colocated with unknown node 'InceptionResnetV1/Bottleneck/BatchNorm/moving_variance'
done
--> Building model
E build: The model has not been loaded, please load it first!
done
E export_rknn: RKNN model is None, please load & build model first!
|