我實現與tensorflow經典圖像分類的問題,我有9個班,首先我用softmax_cross_entropy_with_logits
作爲分類和鐵路網絡,更糟糕經過一些步驟,它提供了約99%的火車準確性,sparse_softmax_cross_entropy_with_logits結果比softmax_cross_entropy_with_logits
然後與sparse_softmax_cross_entropy_with_logits
測試同樣的問題這一次不收斂可言,(火車精度大約爲0.10和0.20)
僅供信息,softmax_cross_entropy_with_logits
,我用[batch_size時,num_classes]與D型FLOAT32的標籤,和sparse_softmax_cross_entropy_with_logits
我使用[batch_size]與dtype int32 fo r標籤。
有沒有人有什麼想法?
更新:
this is code:
def costFun(self):
self.y_ = tf.reshape(self.y_, [-1])
return tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(self.score_, self.y_))
def updateFun(self):
return tf.train.AdamOptimizer(learning_rate = self.lr_).minimize(self.cost_)
def perfFun(self):
correct_pred = tf.equal(tf.argmax(self.score_,1), tf.argmax(y,1))
return(tf.reduce_mean(tf.cast(correct_pred, tf.float32)))
def __init__(self,x,y,lr,lyr1FilterNo,lyr2FilterNo,lyr3FilterNo,fcHidLyrSize,inLyrSize,outLyrSize, keepProb):
self.x_ = x
self.y_ = y
self.lr_ = lr
self.inLyrSize = inLyrSize
self.outLyrSize_ = outLyrSize
self.lyr1FilterNo_ = lyr1FilterNo
self.lyr2FilterNo_ = lyr2FilterNo
self.lyr3FilterNo_ = lyr3FilterNo
self.fcHidLyrSize_ = fcHidLyrSize
self.keepProb_ = keepProb
[self.params_w_, self.params_b_] = ConvNet.paramsFun(self)
self.score_, self.PackShow_ = ConvNet.scoreFun (self)
self.cost_ = ConvNet.costFun (self)
self.update_ = ConvNet.updateFun(self)
self.perf_ = ConvNet.perfFun (self)
主:
lyr1FilterNo = 32
lyr2FilterNo = 64
lyr3FilterNo = 128
fcHidLyrSize = 1024
inLyrSize = 32 * 32
outLyrSize = 9
lr = 0.001
batch_size = 300
dropout = 0.5
x = tf.placeholder(tf.float32, [None, inLyrSize ])
y = tf.placeholder(tf.int32, None )
ConvNet_class = ConvNet(x,y,lr,lyr1FilterNo,lyr2FilterNo,lyr3FilterNo,fcHidLyrSize,inLyrSize,outLyrSize, keepProb)
initVar = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(initVar)
for step in range(10000):
trData_i = np.reshape(trData_i , (-1, 32 * 32))
trLabel_i = np.reshape(trLabel_i, (-1, 1 ))
update_i, PackShow, wLyr1_i, wLyr2_i, wLyr3_i = sess.run([ConvNet_class.update_, ConvNet_class.PackShow_,
ConvNet_class.params_w_['wLyr1'], ConvNet_class.params_w_['wLyr2'], ConvNet_class.params_w_['wLyr3']],
feed_dict = { x:trData_i, y:trLabel_i, keepProb:dropout})
這兩個操作應該對單一熱點('tf.train.softmax_cross_entropy_with_logits()')或稀疏('tf.train.sparse_softmax_cross_entropy_with_logits()')格式中的相同的logits和相同的標籤產生相同的結果。你有沒有檢查過這兩個操作是否爲相同的輸入計算相同的損失?你能顯示你使用的每個版本的代碼嗎? – mrry
@mrry謝謝你的迴應,不,我沒有得到相同的結果與稀疏和softmax相同的logits,我也張貼我的代碼,我使用32x32輸入形狀,9類和其他東西,我刪除了一些部分更易讀,再次感謝您的關注 –