我正在做CS231N分配2并遇到此问题。
我正在使用TensorFlow-GPU 1.5.0
代码如下
# define our input (e.g. the data that changes every batch)
# The first dim is None, and gets sets automatically based on batch size fed in
X = tf.placeholder(tf.float32, [None, 32, 32, 3])
y = tf.placeholder(tf.int64, [None])
is_training = tf.placeholder(tf.bool)
# define model
def complex_model(X,y,is_training):
pass
y_out = complex_model(X,y,is_training)
# Now we're going to feed a random batch into the model
# and make sure the output is the right size
x = np.random.randn(64, 32, 32,3)
with tf.Session() as sess:
with tf.device("/cpu:0"): #"/cpu:0" or "/gpu:0"
tf.global_variables_initializer().run()
ans = sess.run(y_out,feed_dict={X:x,is_training:True})
%timeit sess.run(y_out,feed_dict={X:x,is_training:True})
print(ans.shape)
print(np.array_equal(ans.shape, np.array([64, 10])))
完成追溯
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-6-97f0b6c5a72e> in <module>()
6 tf.global_variables_initializer().run()
7
----> 8 ans = sess.run(y_out,feed_dict={X:x,is_training:True})
9 get_ipython().run_line_magic('timeit', 'sess.run(y_out,feed_dict={X:x,is_training:True})')
10 print(ans.shape)
c:userskasperappdatalocalprogramspythonpython36libsite- packagestensorflowpythonclientsession.py in run(self, fetches, feed_dict, options, run_metadata)
893 try:
894 result = self._run(None, fetches, feed_dict, options_ptr,
--> 895 run_metadata_ptr)
896 if run_metadata:
897 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
c:userskasperappdatalocalprogramspythonpython36libsite-packagestensorflowpythonclientsession.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
1111 # Create a fetch handler to take care of the structure of fetches.
1112 fetch_handler = _FetchHandler(
-> 1113 self._graph, fetches, feed_dict_tensor, feed_handles=feed_handles)
1114
1115 # Run request and get response.
c:userskasperappdatalocalprogramspythonpython36libsite-packagestensorflowpythonclientsession.py in __init__(self, graph, fetches, feeds, feed_handles)
419 with graph.as_default():
--> 420 self._fetch_mapper = _FetchMapper.for_fetch(fetches)
421 self._fetches = []
422 self._targets = []
c:userskasperappdatalocalprogramspythonpython36libsite-packagestensorflowpythonclientsession.py in for_fetch(fetch)
235 if fetch is None:
236 raise TypeError('Fetch argument %r has invalid type %r' %
--> 237 (fetch, type(fetch)))
238 elif isinstance(fetch, (list, tuple)):
239 # NOTE(touts): This is also the code path for namedtuples.
TypeError: Fetch argument None has invalid type <class 'NoneType'>
我以前在此网站上提出过类似的问题,但是这些问题似乎并没有解决我的问题。
任何帮助将不胜感激,谢谢!
问题是 y_out
参数为 sess.run()
是 None
,而它必须是 tf.Tensor
(或类似张量的对象,例如 tf.Variable
(或 tf.Operation
。
在您的示例中,y_out
由以下代码定义:
# define model
def complex_model(X,y,is_training):
pass
y_out = complex_model(X,y,is_training)
complex_model()
不返回值,因此y_out = complex_model(...)
将y_out
设置为None
。我不确定此功能是否代表您的真实代码,但是您的实际complex_model()
功能也可能缺少return
语句。
我相信 mrry 是正确的。
如果您再看笔记本分配2 -tensorflow.ipynb,您将注意到描述单元格,如下:
训练特定模型
在本节中,我们将指定一个供您构建的模型。 这里的目标不是要获得良好的表现(那将是下一个(,而是 相反,要了解张量 文档并配置自己的型号。
使用上面提供的代码作为指导,并使用以下 TensorFlow文档,指定具有以下方式的模型 建筑:
7x7 Convolutional Layer with 32 filters and stride of 1 ReLU Activation Layer Spatial Batch Normalization Layer (trainable parameters, with scale and centering) 2x2 Max Pooling layer with a stride of 2 Affine layer with 1024 output units ReLU Activation Layer Affine layer from 1024 input units to 10 outputs
要求您在功能中定义模型
# define model
def complex_model(X,y,is_training):
pass
就像他们在
中一样def simple_model(X,y):
# define our weights (e.g. init_two_layer_convnet)
# setup variables
Wconv1 = tf.get_variable("Wconv1", shape=[7, 7, 3, 32])
bconv1 = tf.get_variable("bconv1", shape=[32])
W1 = tf.get_variable("W1", shape=[5408, 10])
b1 = tf.get_variable("b1", shape=[10])
# define our graph (e.g. two_layer_convnet)
a1 = tf.nn.conv2d(X, Wconv1, strides=[1,2,2,1], padding='VALID') + bconv1
h1 = tf.nn.relu(a1)
h1_flat = tf.reshape(h1,[-1,5408])
y_out = tf.matmul(h1_flat,W1) + b1
return y_out
希望这会有所帮助!