yolo v2 代码报错jupyter notebook
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\ops\math_ops.py in binary_op_wrapper(x, y)
1244 r_op = getattr(y, "__r%s__" % op_name)
-> 1245 out = r_op(x)
1246 if out is NotImplemented:
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\ops\math_ops.py in r_binary_op_wrapper(y, x)
1265 # r_binary_op_wrapper use different force_same_dtype values.
-> 1266 y, x = maybe_promote_tensors(y, x)
1267 return func(x, y, name=name)
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\ops\math_ops.py in maybe_promote_tensors(force_same_dtype, *tensors)
1201 promoted_tensors.append(
-> 1202 ops.convert_to_tensor(tensor, dtype, name="x"))
1203 return promoted_tensors
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\profiler\trace.py in wrapped(*args, **kwargs)
162 return func(*args, **kwargs)
--> 163 return func(*args, **kwargs)
164
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\framework\ops.py in convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, dtype_hint, ctx, accepted_result_types)
1565 if ret is None:
-> 1566 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
1567
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\framework\constant_op.py in _constant_tensor_conversion_function(v, dtype, name, as_ref)
338 _ = as_ref
--> 339 return constant(v, dtype=dtype, name=name)
340
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\framework\constant_op.py in constant(value, dtype, shape, name)
263 """
--> 264 return _constant_impl(value, dtype, shape, name, verify_shape=False,
265 allow_broadcast=True)
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\framework\constant_op.py in _constant_impl(value, dtype, shape, name, verify_shape, allow_broadcast)
275 return _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
--> 276 return _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
277
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\framework\constant_op.py in _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
300 """Implementation of eager constant."""
--> 301 t = convert_to_eager_tensor(value, ctx, dtype)
302 if shape is None:
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\framework\constant_op.py in convert_to_eager_tensor(value, ctx, dtype)
97 ctx.ensure_initialized()
---> 98 return ops.EagerTensor(value, ctx.device_name, dtype)
99
D:\pictureprocess\anaconda\lib\site-packages\keras\engine\keras_tensor.py in __array__(self)
243 def __array__(self):
--> 244 raise TypeError(
245 'Cannot convert a symbolic Keras input/output to a numpy array. '
TypeError: Cannot convert a symbolic Keras input/output to a numpy array. This error may indicate that you're trying to pass a symbolic value to a NumPy call, which is not supported. Or, you may be trying to pass Keras symbolic inputs/outputs to a TF API that does not register dispatching, preventing Keras from automatically converting the API call to a lambda layer in the Functional Model.
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
<ipython-input-1-bcf61aa1007c> in <module>
112 #Now yolo_eval function selects the best boxes using filtering and non-max suppression techniques.
113 # If you want to dive in more to see how this works, refer keras_yolo.py file in yad2k/models
--> 114 boxes, scores, classes = yolo_eval(yolo_outputs, image_shape)
115
116
~\yad2k\models\keras_yolo.py in yolo_eval(yolo_outputs, image_shape, max_boxes, score_threshold, iou_threshold)
337 image_dims = K.stack([height, width, height, width])
338 image_dims = K.reshape(image_dims, [1, 4])
--> 339 boxes = boxes * image_dims
340
341 # TODO: Something must be done about this ugly hack!
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\ops\math_ops.py in binary_op_wrapper(x, y)
1248 return out
1249 except (TypeError, ValueError):
-> 1250 raise e
1251 else:
1252 raise
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\ops\math_ops.py in binary_op_wrapper(x, y)
1232 # r_binary_op_wrapper use different force_same_dtype values.
1233 x, y = maybe_promote_tensors(x, y, force_same_dtype=False)
-> 1234 return func(x, y, name=name)
1235 except (TypeError, ValueError) as e:
1236 # Even if dispatching the op failed, the RHS may be a tensor aware
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\ops\math_ops.py in _mul_dispatch(x, y, name)
1573 return sparse_tensor.SparseTensor(y.indices, new_vals, y.dense_shape)
1574 else:
-> 1575 return multiply(x, y, name=name)
1576
1577
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\util\dispatch.py in wrapper(*args, **kwargs)
208 # Note: convert_to_eager_tensor currently raises a ValueError, not a
209 # TypeError, when given unexpected types. So we need to catch both.
--> 210 result = dispatch(wrapper, args, kwargs)
211 if result is not OpDispatcher.NOT_SUPPORTED:
212 return result
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\util\dispatch.py in dispatch(op, args, kwargs)
124 return result
125 for dispatcher in _GLOBAL_DISPATCHERS:
--> 126 result = dispatcher.handle(op, args, kwargs)
127 if result is not OpDispatcher.NOT_SUPPORTED:
128 return result
D:\pictureprocess\anaconda\lib\site-packages\keras\layers\core.py in handle(self, op, args, kwargs)
1464 isinstance(x, keras_tensor.KerasTensor)
1465 for x in tf.nest.flatten([args, kwargs])):
-> 1466 return TFOpLambda(op)(*args, **kwargs)
1467 else:
1468 return self.NOT_SUPPORTED
D:\pictureprocess\anaconda\lib\site-packages\keras\engine\base_layer.py in __call__(self, *args, **kwargs)
943 # >> model = tf.keras.Model(inputs, outputs)
944 if _in_functional_construction_mode(self, inputs, args, kwargs, input_list):
--> 945 return self._functional_construction_call(inputs, args, kwargs,
946 input_list)
947
D:\pictureprocess\anaconda\lib\site-packages\keras\engine\base_layer.py in _functional_construction_call(self, inputs, args, kwargs, input_list)
1081 layer=self, inputs=inputs, build_graph=True, training=training_value):
1082 # Check input assumptions set after layer building, e.g. input shape.
-> 1083 outputs = self._keras_tensor_symbolic_call(
1084 inputs, input_masks, args, kwargs)
1085
D:\pictureprocess\anaconda\lib\site-packages\keras\engine\base_layer.py in _keras_tensor_symbolic_call(self, inputs, input_masks, args, kwargs)
814 return tf.nest.map_structure(keras_tensor.KerasTensor, output_signature)
815 else:
--> 816 return self._infer_output_signature(inputs, args, kwargs, input_masks)
817
818 def _infer_output_signature(self, inputs, args, kwargs, input_masks):
D:\pictureprocess\anaconda\lib\site-packages\keras\engine\base_layer.py in _infer_output_signature(self, inputs, args, kwargs, input_masks)
854 self._maybe_build(inputs)
855 inputs = self._maybe_cast_inputs(inputs)
--> 856 outputs = call_fn(inputs, *args, **kwargs)
857
858 self._handle_activity_regularization(inputs, outputs)
D:\pictureprocess\anaconda\lib\site-packages\keras\layers\core.py in _call_wrapper(*args, **kwargs)
1341 # Decorate the function to produce this layer's call method
1342 def _call_wrapper(*args, **kwargs):
-> 1343 return self._call_wrapper(*args, **kwargs)
1344 self.call = tf.__internal__.decorator.make_decorator(function, _call_wrapper)
1345
D:\pictureprocess\anaconda\lib\site-packages\keras\layers\core.py in _call_wrapper(self, *args, **kwargs)
1373 # multiple ops w/ the same name when the layer is reused)
1374 kwargs.pop('name', None)
-> 1375 result = self.function(*args, **kwargs)
1376 self._check_variables(created_variables, tape.watched_variables())
1377 return result
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\util\dispatch.py in wrapper(*args, **kwargs)
204 """Call target, and fall back on dispatchers if there is a TypeError."""
205 try:
--> 206 return target(*args, **kwargs)
207 except (TypeError, ValueError):
208 # Note: convert_to_eager_tensor currently raises a ValueError, not a
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\ops\math_ops.py in multiply(x, y, name)
528 """
529
--> 530 return gen_math_ops.mul(x, y, name)
531
532
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\ops\gen_math_ops.py in mul(x, y, name)
6246 pass # Add nodes to the TensorFlow graph.
6247 # Add nodes to the TensorFlow graph.
-> 6248 _, _, _op, _outputs = _op_def_library._apply_op_helper(
6249 "Mul", x=x, y=y, name=name)
6250 _result = _outputs[:]
D:\pictureprocess\anaconda\lib\site-packages\tensorflow\python\framework\op_def_library.py in _apply_op_helper(op_type_name, name, **keywords)
618 if input_arg.type_attr in attrs:
619 if attrs[input_arg.type_attr] != attr_value:
--> 620 raise TypeError(
621 "Input '%s' of '%s' Op has type %s that does not "
622 "match type %s of argument '%s'." %
TypeError: Input 'y' of 'Mul' Op has type float64 that does not match type float32 of argument 'x'.
检查下输入，这个报错是说网络限定float32的数据，但是你的输入是float64的。或者你可以强制用numpy或者torch将float64的转成float32的
您好，我是有问必答小助手，您的问题已经有小伙伴解答了，您看下是否解决，可以追评进行沟通哦~
如果有您比较满意的答案 / 帮您提供解决思路的答案，可以点击【采纳】按钮，给回答的小伙伴一些鼓励哦～～
ps:问答VIP仅需29元，即可享受5次/月 有问必答服务，了解详情>>>https://vip.csdn.net/askvip?utm_source=1146287632