0
我只是試圖用我自己的lmdb文件來訓練提供的Caffenet網絡。 我改變了完全連接到深度4096和自定義frame_size的卷積層。嘗試使用新數據運行自定義caffenet時出錯
下面是代碼：
weight_param = dict(lr_mult=1, decay_mult=1)
bias_param = dict(lr_mult=2, decay_mult=0)
learned_param = [weight_param, bias_param]
batch_size = 256
# 0 means non updating parameters
frozen_param = [dict(lr_mult=0)] * 2
def conv_relu(bottom, ks, nout, stride=1, pad=0, group=1,
param=learned_param,
weight_filler=dict(type='gaussian', std=0.01),
bias_filler=dict(type='constant', value=0.1),
kernel_h=None, kernel_w=None):
if (kernel_h is not None and kernel_w is not None):
conv = L.Convolution(bottom, kernel_h=kernel_h, kernel_w=kernel_w,
num_output=nout, pad=pad, group=group,
param=param, weight_filler=weight_filler,
bias_filler=bias_filler)
else:
conv = L.Convolution(bottom, kernel_size=ks, stride=stride,
num_output=nout, pad=pad, group=group,
param=param, weight_filler=weight_filler,
bias_filler=bias_filler)
return conv, L.ReLU(conv, in_place=True)
def fc_relu(bottom, nout, param=learned_param,
weight_filler=dict(type='gaussian', std=0.005),
bias_filler=dict(type='constant', value=0.1)):
fc = L.InnerProduct(bottom, num_output=nout, param=param,
weight_filler=weight_filler,
bias_filler=bias_filler)
return fc, L.ReLU(fc, in_place=True)
def max_pool(bottom, ks, stride=1):
return L.Pooling(bottom, pool=P.Pooling.MAX, kernel_size=ks, stride=stride)
def caffenet(lmdb, train=True, num_classes=1000,
classifier_name='fc8', learn_all=False):
"""Returns a NetSpec specifying CaffeNet, following the original proto text
specification (./models/bvlc_reference_caffenet/train_val.prototxt).
This implementation force to train the 3 last fc layers.
"""
n = caffe.NetSpec()
n.data, n.label = L.Data(batch_size=batch_size, backend=P.Data.LMDB,
source=lmdb, ntop=2)
param = learned_param if learn_all else frozen_param
n.conv1, n.relu1 = conv_relu(n.data, 11, 96, stride=2, param=param)
n.pool1 = max_pool(n.relu1, 3, stride=2)
n.norm1 = L.LRN(n.pool1, local_size=5, alpha=1e-4, beta=0.75)
n.conv2, n.relu2 = conv_relu(n.norm1, 5, 256, pad=2, group=2, param=param)
n.pool2 = max_pool(n.relu2, 3, stride=2)
n.norm2 = L.LRN(n.pool2, local_size=5, alpha=1e-4, beta=0.75)
n.conv3, n.relu3 = conv_relu(n.norm2, 3, 384, pad=1, param=param)
n.conv4, n.relu4 = conv_relu(n.relu3, 3, 384, pad=1, group=2, param=param)
n.conv5, n.relu5 = conv_relu(n.relu4, 3, 256, pad=1, group=2, param=param)
n.pool5 = max_pool(n.relu5, 3, stride=2)
# Convert FC layer to CONV layer to handle different sizes
#n.fc6, n.relu6 = fc_relu(n.pool5, 4096, param=learned_param)
n.fc6, n.relu6 = conv_relu(n.pool5, 7, 4096, pad=0, param=learned_param,
kernel_h=7, kernel_w=10)
if train:
n.drop6 = fc7input = L.Dropout(n.relu6, in_place=True)
else:
fc7input = n.relu6
# n.fc7, n.relu7 = fc_relu(fc7input, 4096, param=learned_param)
n.fc7, n.relu7 = conv_relu(n.drop6, 1, 4096, pad=0, param=learned_param)
if train:
n.drop7 = fc8input = L.Dropout(n.relu7, in_place=True)
else:
fc8input = n.relu7
# always learn fc8 (param=learned_param)
fc8 = L.InnerProduct(fc8input, num_output=num_classes, param=learned_param)
# give fc8 the name specified by argument `classifier_name`
n.__setattr__(classifier_name, fc8)
if not train:
n.probs = L.Softmax(fc8)
n.loss = L.SoftmaxWithLoss(fc8, n.label)
n.acc = L.Accuracy(fc8, n.label)
# write the net to a temporary file and return its filename
with open('phiNet.prototxt', 'w') as f:
f.write(str(n.to_proto()))
return f.name
編譯時我收到此錯誤：
data_transformer.cpp:168] Check failed: height <= datum_height (254 vs. 221)
我的圖片是336 * 254。
這個錯誤是什麼意思？
感謝
添加完整的日誌使我們更容易理解。它看起來像從LMDB讀取的圖像的高度爲221，而模型期望高度爲254的圖像。 –