我正在尝试进行分类。我一共有9节课。我的损失函数有 3 个潜力，但在训练中我只考虑了一个。我已将两个损失函数的权重设置为零，因此只考虑损失函数中的一项。训练运行良好。但是，当我测试时，我的所有班级值都得到了 NAN。有人可以指导我吗？我使用的 caffe 下面是我的 prototxt 文件。“angle_head”是我感兴趣的潜力。
name: "Zeiler_conv5"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 224
input_dim: 224
input: "rois"
input_dim: 1 # to be changed on-the-fly to num ROIs
input_dim: 5 # [batch ind, x1, y1, x2, y2] zero-based indexing
input_dim: 1
input_dim: 1
input: "labels"
input_dim: 1 # to be changed on-the-fly to match num ROIs
input_dim: 1
input_dim: 1
input_dim: 1
input: "bbox_targets"
input_dim: 1 # to be changed on-the-fly to match num ROIs
input_dim: 84 # 4 * (K+1) (=21) classes
input_dim: 1
input_dim: 1
input: "bbox_loss_weights"
input_dim: 1 # to be changed on-the-fly to match num ROIs
input_dim: 84 # 4 * (K+1) (=21) classes
input_dim: 1
input_dim: 1
input: "angle_head"
input_dim: 1 # to be changed on-the-fly to match num ROIs
input_dim: 1 # 9 (-180:45:180) classes
input_dim: 1
input_dim: 1
input: "angle_head_weight"
input_dim: 1 # to be changed on-the-fly to match num ROIs
input_dim: 1 # 9 (-180:45:180) classes
input_dim: 1
input_dim: 1
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 0.0
}
param {
lr_mult: 0.0
}
convolution_param {
num_output: 96
kernel_size: 7
pad: 3
stride: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "norm1"
type: "LRN"
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 3
alpha: 0.00005
beta: 0.75
norm_region: WITHIN_CHANNEL
}
}
layer {
name: "pool1"
type: "Pooling"
bottom: "norm1"
top: "pool1"
pooling_param {
kernel_size: 3
stride: 2
pad: 1
pool: MAX
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 0.0
}
param {
lr_mult: 0.0
}
convolution_param {
num_output: 256
kernel_size: 5
pad: 2
stride: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "norm2"
type: "LRN"
bottom: "conv2"
top: "norm2"
lrn_param {
local_size: 3
alpha: 0.00005
beta: 0.75
norm_region: WITHIN_CHANNEL
}
}
layer {
name: "pool2"
type: "Pooling"
bottom: "norm2"
top: "pool2"
pooling_param {
kernel_size: 3
stride: 2
pad: 1
pool: MAX
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult: 0.0
}
param {
lr_mult: 0.0
}
convolution_param {
num_output: 384
kernel_size: 3
pad: 1
stride: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
param {
lr_mult: 0.0
}
param {
lr_mult: 0.0
}
convolution_param {
num_output: 384
kernel_size: 3
pad: 1
stride: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
param {
lr_mult: 0.0
}
param {
lr_mult: 0.0
}
convolution_param {
num_output: 256
kernel_size: 3
pad: 1
stride: 1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
bottom: "conv5"
bottom: "rois"
top: "pool5"
name: "roi_pool5"
type: "ROIPooling"
roi_pooling_param {
pooled_w: 6
pooled_h: 6
spatial_scale: 0.0625 # (1/16)
}
}
layer {
bottom: "pool5"
top: "fc6"
name: "fc6"
param {
lr_mult: 1.0
}
param {
lr_mult: 2.0
}
type: "InnerProduct"
inner_product_param {
num_output: 4096
}
}
layer {
bottom: "fc6"
top: "fc6"
name: "relu6"
type: "ReLU"
}
layer {
bottom: "fc6"
top: "fc6"
name: "drop6"
type: "Dropout"
dropout_param {
dropout_ratio: 0.5
scale_train: false
}
}
layer {
bottom: "fc6"
top: "fc7"
name: "fc7"
param {
lr_mult: 1.0
}
param {
lr_mult: 2.0
}
type: "InnerProduct"
inner_product_param {
num_output: 4096
}
}
layer {
bottom: "fc7"
top: "fc7"
name: "relu7"
type: "ReLU"
}
layer {
bottom: "fc7"
top: "fc7"
name: "drop7"
type: "Dropout"
dropout_param {
dropout_ratio: 0.5
scale_train: false
}
}
layer {
bottom: "fc7"
top: "cls_score"
name: "cls_score"
param {
lr_mult: 1.0
}
param {
lr_mult: 2.0
}
type: "InnerProduct"
inner_product_param {
num_output: 21
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
bottom: "fc7"
top: "angle_pred"
name: "angle_pred"
type: "InnerProduct"
param {
lr_mult: 1.0
}
param {
lr_mult: 2.0
}
inner_product_param {
num_output: 9
weight_filler {
type: "gaussian"
std: 0.001
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
bottom: "fc7"
top: "bbox_pred"
name: "bbox_pred"
type: "InnerProduct"
param {
lr_mult: 1.0
}
param {
lr_mult: 2.0
}
inner_product_param {
num_output: 84
weight_filler {
type: "gaussian"
std: 0.001
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "cls_score"
bottom: "labels"
top: "loss_cls"
loss_weight: 0
}
layer {
name: "accuarcy"
type: "Accuracy"
bottom: "cls_score"
bottom: "labels"
top: "accuarcy"
}
layer {
name: "loss_angle"
type: "SoftmaxWithLoss"
bottom: "angle_pred"
bottom: "angle_head"
bottom: "angle_head_weight"
top: "loss_angle"
loss_weight: 1
}
layer {
name: "loss_bbox"
type: "SmoothL1Loss"
bottom: "bbox_pred"
bottom: "bbox_targets"
bottom: "bbox_loss_weights"
top: "loss_bbox"
loss_weight: 0
}