已下载CBIS-DDSM数据集，即DICOM格式的修订版DDSM数据集。使用此数据集，我一直在尝试根据YouTuber＆quot; sentdex＆＃39;使用的代码运行CNN。大部分数据集的预处理已经整理出来，但正确运行CNN已经变得令人不安。我认为这一行阻止了整个CNN代码的功能：
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction,
labels=y))
即使我改变了部分
'labels=y'
到
'labels=tf.reshape(y, [1,2])'
，我仍然有相同的错误消息。我试图绕过＆＃39; tf.nn.softmax_cross_entropy_with_logits＆＃39;与数字不稳定的版本。然后，可以运行CNN。但我只得到了＆＃39; nan＆＃39;。关于我应该做什么的任何建议？我真的卡住了。
这是我的代码的摘录
IMG_SIZE_PX = 256
N_CLASSES = 2
def convolutional_neural_network(x):
weights = {'W_conv1':tf.Variable(tf.random_normal([5,5,1,32])),
'W_conv2':tf.Variable(tf.random_normal([5,5,32,64])),
'W_fc':tf.Variable(tf.random_normal([IMG_SIZE_PX*IMG_SIZE_PX,1024])),
'out':tf.Variable(tf.random_normal([1024, N_CLASSES]))}
biases = {'b_conv1':tf.Variable(tf.random_normal([32])),
'b_conv2':tf.Variable(tf.random_normal([64])),
'b_fc':tf.Variable(tf.random_normal([1024])),
'out':tf.Variable(tf.random_normal([N_CLASSES]))}
x = tf.reshape(x, shape=[-1, IMG_SIZE_PX, IMG_SIZE_PX, 1])
conv1 = tf.nn.relu(conv2d(x, weights['W_conv1']) + biases['b_conv1'])
conv1 = maxpool2d(conv1)
conv1Shape = conv1.get_shape().as_list()
print ("Conv1 Shape! : " + str(conv1Shape))
conv2 = tf.nn.relu(conv2d(conv1, weights['W_conv2']) + biases['b_conv2'])
conv2 = maxpool2d(conv2)
conv2Shape = conv2.get_shape().as_list()
print ("Conv2 Shape! : " + str(conv2Shape))
fc = tf.reshape(conv2,[-1, 64 * 64 * 16])
fc = tf.nn.relu(tf.matmul(fc, weights['W_fc'])+biases['b_fc'])
fc = tf.nn.dropout(fc, KEEP_RATE)
output = tf.matmul(fc, weights['out'])+biases['out']
return output
def train_neural_network(x, EnableUnstableNumericalCalc = False):
# Loading the Input File; list of (Numpy array, label)
Data_Chunk = np.load('MTrain-test-calc-256.npy')
train_data = Data_Chunk[:NegNumber]
validation_data = Data_Chunk[NegNumber:]
# Training part
prediction = convolutional_neural_network(x)
predShape = prediction.get_shape().as_list()
if EnableUnstableNumericalCalc == False:
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction,
labels=y))
else:
intermed = tf.nn.softmax(prediction)
cost = -tf.reduce_sum(y * tf.log(intermed), 1)
optimizer = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(cost)
hm_epochs = NB_EPOCHS
print("===============================================================================================")
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
successful_runs = 0
total_runs = 0
for epoch in range(hm_epochs):
epoch_loss = 0
for data in train_data:
total_runs += 1
X = data[0]
Y = data[1]
# try:
_, c = sess.run([optimizer, cost], feed_dict={x: X, y: Y})
epoch_loss += c
successful_runs += 1
"""
except InvalidArgumentError:
print("***** Error(Training): Invalid Arument Error! *****")
'''
print("X = {}".format(X))
print("Y = {}".format(Y))
print(str(e))
'''
pass
"""
try:
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
print('Epoch', epoch + 1, 'completed out of', hm_epochs,'loss:', epoch_loss)
print('Accuracy:',accuracy.eval({x:[i[0] for i in validation_data], y:[i[1] for i in validation_data]}))
except Exception as e:
print("!: Invalid information. Accuracy and fitment percent could not be computed.!")
这是错误信息：
Traceback (most recent call last):
File "C:\Pythons\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1323, in _do_call
return fn(*args)
File "C:\Pythons\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1302, in _run_fn
status, run_metadata)
File "C:\Pythons\Python35\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 473, in __exit__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: logits and labels must be same size: logits_size=[4,2] labels_size=[1,2]
[[Node: SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"](Reshape_2, Reshape_3)]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "ConvNet.py", line 149, in <module>
train_neural_network(x)
File "ConvNet.py", line 120, in train_neural_network
_, c = sess.run([optimizer, cost], feed_dict={x: X, y: Y})
File "C:\Pythons\Python35\lib\site-packages\tensorflow\python\client\session.py", line 889, in run
run_metadata_ptr)
File "C:\Pythons\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1120, in _run
feed_dict_tensor, options, run_metadata)
File "C:\Pythons\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1317, in _do_run
options, run_metadata)
File "C:\Pythons\Python35\lib\site-packages\tensorflow\python\client\session.py", line 1336, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: logits and labels must be same size: logits_size=[4,2] labels_size=[1,2]
[[Node: SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"](Reshape_2, Reshape_3)]]
Caused by op 'SoftmaxCrossEntropyWithLogits', defined at:
File "ConvNet.py", line 149, in <module>
train_neural_network(x)
File "ConvNet.py", line 95, in train_neural_network
labels=y))
File "C:\Pythons\Python35\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 1783, in softmax_cross_entropy_with_logits
precise_logits, labels, name=name)
File "C:\Pythons\Python35\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py", line 4363, in _softmax_cross_entropy_with_logits
name=name)
File "C:\Pythons\Python35\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "C:\Pythons\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 2956, in create_op
op_def=op_def)
File "C:\Pythons\Python35\lib\site-packages\tensorflow\python\framework\ops.py", line 1470, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): logits and labels must be same size: logits_size=[4,2] labels_size=[1,2]
[[Node: SoftmaxCrossEntropyWithLogits = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"](Reshape_2, Reshape_3)]]