1
我正在開發項目,需要識別給定人臉部的臉部特徵。我將其制定爲迴歸問題,並希望從簡單的conv網絡開始並定義下面的網絡。日誌記錄權重和caffe中的偏差
我注意到輸出預測總是相同的,稍後再調試一些,我發現評分層的權重和梯度在迭代過程中不會改變。我使用固定的學習率〜5e-2來生成下面的示例。隨着迭代的進行,訓練損失似乎減少,但我無法理解爲什麼。我還記錄了其他圖層:'conv1'
,'conv2'
, 'fc1'
,並看到在迭代過程中保持不變的相同行爲。由於損失似乎減少了,所以有些事情必須改變,我的猜測是,記錄我在下面的做法可能是不正確的。
你能否給我一些指點檢查?請讓我知道如果你需要更多的信息
修改lenet:
# Modified LeNet. Added relu1, relu2 and, dropout.
# Loss function is an Euclidean distance
def lenet(hdf5_list, batch_size=64, dropout_ratio=0.5, train=True):
# our version of LeNet: a series of linear and simple nonlinear transformations
n = caffe.NetSpec()
n.data, n.label = L.HDF5Data(batch_size=batch_size, source=hdf5_list, ntop=2)
n.conv1 = L.Convolution(n.data, kernel_size=5, num_output=20, weight_filler=dict(type='xavier'), bias_filler=dict(type='constant', value=0.1))
n.relu1 = L.ReLU(n.conv1, in_place=False, relu_param=dict(negative_slope=0.1))
n.pool1 = L.Pooling(n.relu1, kernel_size=2, stride=2, pool=P.Pooling.MAX)
n.conv2 = L.Convolution(n.pool1, kernel_size=5, num_output=50, weight_filler=dict(type='xavier'), bias_filler=dict(type='constant', value=0.1))
n.relu2 = L.ReLU(n.conv2, in_place=False, relu_param=dict(negative_slope=0.1))
n.pool2 = L.Pooling(n.relu2, kernel_size=2, stride=2, pool=P.Pooling.MAX)
if train:
n.drop3 = fc1_input = L.Dropout(n.pool2, in_place=True, dropout_param = dict(dropout_ratio=dropout_ratio))
else:
fc1_input = n.pool2
n.fc1 = L.InnerProduct(fc1_input, num_output=500, weight_filler=dict(type='xavier'), bias_filler=dict(type='constant', value=0.1))
n.relu3 = L.ReLU(n.fc1, in_place=True, relu_param=dict(negative_slope=0.1))
n.score = L.InnerProduct(n.relu3, num_output=30, weight_filler=dict(type='xavier'))
n.loss = L.EuclideanLoss(n.score, n.label)
return n.to_proto()
求解循環:
#custom solver loop
for it in range(niter):
solver.step(1)
train_loss[it] = solver.net.blobs['loss'].data
score_weights.append(solver.net.params['score'][0].data)
score_biases.append(solver.net.params['score'][1].data)
score_weights_diff.append(solver.net.params['score'][0].diff)
score_biases_diff.append(solver.net.params['score'][1].diff)
if (it % val_interval) == 0 or (it == niter - 1):
val_error_this = 0
for test_it in range(niter_val_error):
solver.test_nets[0].forward()
val_error_this += euclidean_loss(solver.test_nets[0].blobs['score'].data ,
solver.test_nets[0].blobs['label'].data)/niter_val_error
val_error[it // val_interval] = val_error_this
打印成績:
print score_weights_diff[0].shape
for i in range(10):
score_weights_i = score_weights_diff[i]
print score_weights_i[0:30:10,0]
print score_biases_diff[0].shape
for i in range(5):
score_biases_i = score_biases_diff[i]
print score_biases_i[0:30:6]
輸出:
(30, 500)
[ -3.71852257e-05 7.34565838e-05 2.61445384e-04]
[ -3.71852257e-05 7.34565838e-05 2.61445384e-04]
[ -3.71852257e-05 7.34565838e-05 2.61445384e-04]
[ -3.71852257e-05 7.34565838e-05 2.61445384e-04]
[ -3.71852257e-05 7.34565838e-05 2.61445384e-04]
[ -3.71852257e-05 7.34565838e-05 2.61445384e-04]
[ -3.71852257e-05 7.34565838e-05 2.61445384e-04]
[ -3.71852257e-05 7.34565838e-05 2.61445384e-04]
[ -3.71852257e-05 7.34565838e-05 2.61445384e-04]
[ -3.71852257e-05 7.34565838e-05 2.61445384e-04]
131
(30,)
[ 3.22921231e-04 5.66378840e-05 -5.15143370e-07 -1.51118627e-04
2.30352176e-04]
[ 3.22921231e-04 5.66378840e-05 -5.15143370e-07 -1.51118627e-04
2.30352176e-04]
[ 3.22921231e-04 5.66378840e-05 -5.15143370e-07 -1.51118627e-04
2.30352176e-04]
[ 3.22921231e-04 5.66378840e-05 -5.15143370e-07 -1.51118627e-04
2.30352176e-04]
[ 3.22921231e-04 5.66378840e-05 -5.15143370e-07 -1.51118627e-04
2.30352176e-04]
謝謝@Shai。那樣做了。 – r3t2