我正在尝试将用Keras创建的UNet模型转换为.nn文件，以便在Unity的神经网络后端中使用。然而，我遇到了这个错误。我的模型导出时生成了一个’.h5’文件，我将其转换成了二进制的’.pb’文件，之后我使用了tensorflow_to_barracuda.py。有没有人在Unity中有一个工作的分割程序？
Converting unet_person.bytes to unet_person.nnIGNORED: PlaceholderWithDefault unknown layerIGNORED: Switch unknown layerIGNORED: Switch unknown layerIGNORED: Shape unknown layerIGNORED: Switch unknown layerIGNORED: Merge unknown layerIGNORED: Shape unknown layerIGNORED: Shape unknown layer---------------------------------------------------------------------------UnboundLocalError Traceback (most recent call last)<ipython-input-22-d09d8c6d2c1a> in <module> 1 from mlagents.trainers import tensorflow_to_barracuda as tb 2 ----> 3 tb.convert('unet_person.bytes', 'unet_person.nn')/anaconda3/lib/python3.6/site-packages/mlagents/trainers/tensorflow_to_barracuda.py in convert(source_file, target_file, trim_unused_by_output, verbose, compress_f16)938 o_model = barracuda.Model()939 o_model.layers, o_input_shapes, o_model.tensors, o_model.memories = \--> 940 process_model(i_model, args)941 942 # Cleanup unconnected Identities (they might linger after processing complex node patterns like LSTM)/anaconda3/lib/python3.6/site-packages/mlagents/trainers/tensorflow_to_barracuda.py in process_model(model, args)870 nodes = nodes_as_array[node_index:pattern_end]871 name = nodes[-1].name--> 872 var_tensors, const_tensors = get_tensors(nodes)873 if args.print_patterns or args.verbose:874 print('PATTERN:', name, '~~', pattern_name, pattern, '<-', var_tensors, '+', [t.name for t in const_tensors])/anaconda3/lib/python3.6/site-packages/mlagents/trainers/tensorflow_to_barracuda.py in get_tensors(pattern_nodes)845 tensor_nodes = [n for n in pattern_nodes if n.op == 'Const']846 tensors = [Struct(name = n.name, obj = n.attr["value"].tensor, shape = get_tensor_dims(n.attr["value"].tensor), data = get_tensor_data(n.attr["value"].tensor))--> 847 for n in tensor_nodes]848 849 # TODO: unify / reuse code from process_layer/anaconda3/lib/python3.6/site-packages/mlagents/trainers/tensorflow_to_barracuda.py in <listcomp>(.0)845 tensor_nodes = [n for n in pattern_nodes if n.op == 'Const']846 tensors = [Struct(name = n.name, obj = n.attr["value"].tensor, shape = get_tensor_dims(n.attr["value"].tensor), data = get_tensor_data(n.attr["value"].tensor))--> 847 for n in tensor_nodes]848 849 # TODO: unify / reuse code from process_layer/anaconda3/lib/python3.6/site-packages/mlagents/trainers/tensorflow_to_barracuda.py in get_tensor_data(tensor)492 if tensor.bool_val:493 data = np.array(tensor.bool_val, dtype=float)--> 494 return np.array(data).reshape(dims)495 496 def flatten(items,enter=lambda x:isinstance(x, list)):UnboundLocalError: local variable 'data' referenced before assignment回答：
在Barracuda 1.0中，有一种方法可以使用Keras2ONNX pip包将Keras (.h5) 模型转换为ONNX模型。
你需要安装keras2ONNX，然后运行以下代码：
import keras2onnxonnx_model = keras2onnx.convert_keras(unet, name='unet')keras2onnx.save_model(onnx_model, "unet.onnx")请注意，你可能需要使用以下标志：channel_first_inputs=[unet.layers[0].layers[0]]
onnx_model = keras2onnx.convert_keras(unet, name='unet')由于Barracuda的输入是通道优先的，这意味着对于一个批次大小 x 宽度 x 高度 x rgb的图像，排序是rgb x 宽度 x 高度 x 批次大小。
