Тонкая настройка DenseNet 201 с использованием кофе и цифр

Question

Я пытаюсь настроить мой набор данных с использованием моделей DenseNet (доступно здесь ) и системы Nvidia-Digits. Я уже прочитал все вопросы и внес некоторые изменения в свою собственную сеть, но этовыдает мне следующую ошибку:

conv2_1/x2/bn needs backward computation.
conv2_1/x1 needs backward computation.
relu2_1/x1 needs backward computation.
conv2_1/x1/scale needs backward computation.
conv2_1/x1/bn needs backward computation.
pool1_pool1_0_split needs backward computation.
pool1 needs backward computation.
relu1 needs backward computation.
conv1/scale needs backward computation.
conv1/bn needs backward computation.
conv1 needs backward computation.
label_val-data_1_split does not need backward computation.
val-data does not need backward computation.
This network produces output accuracy
This network produces output loss
Network initialization done.
Solver scaffolding done.
Finetuning from /home/ubuntu/models/DenseNet-Caffe/densenet201.caffemodel
Ignoring source layer input
Check failed: target_blobs.size() == source_layer.blobs_size() (5 vs. 3) Incompatible number of blobs for layer conv1/bn

вот моя сеть, я использовал оригинальный прототекст и внес некоторые изменения, как показано ниже

layer {
 name: "train-data"
 type: "Data"
 top: "data"
 top: "label"
 include {
   stage: "train"
 }
 transform_param {
   crop_size: 224
 }
 data_param {
   batch_size: 126
 }
}
layer {
 name: "val-data"
 type: "Data"
 top: "data"
 top: "label"
 include {
   stage: "val"
 }
 transform_param {
   crop_size: 224
 }
 data_param {
   batch_size: 64
 }
}
layer {
 name: "conv1"
 type: "Convolution"
 bottom: "data"
 top: "conv1"
 convolution_param {
   num_output: 64
   bias_term: false
   pad: 3
   kernel_size: 7
   stride: 2
 }
}
layer {
 name: "conv1/bn"
 type: "BatchNorm"
 bottom: "conv1"
 top: "conv1/bn"
 batch_norm_param {
   eps: 1e-5
 }
}
layer {
 name: "conv1/scale"
 type: "Scale"
 bottom: "conv1/bn"
 top: "conv1/bn"
 scale_param {
   bias_term: true
 }
}
layer {
 name: "relu1"
 type: "ReLU"
 bottom: "conv1/bn"
 top: "conv1/bn"
}
.
.
.
.
layer {
 name: "fc6new"
 type: "Convolution"
 bottom: "pool5"
 top: "fc6new"
 convolution_param {
   num_output: 35
   kernel_size: 1
 }
}

layer {
 name: "loss"
 type: "SoftmaxWithLoss"
 bottom: "fc6new"
 bottom: "label"
 top: "loss"
 exclude {
   stage: "deploy"
 }
}
layer {
 name: "accuracy"
 type: "Accuracy"
 bottom: "fc6new"
 bottom: "label"
 top: "accuracy"
 include {
   stage: "val"
 }
}
layer {
 name: "accuracy_train"
 type: "Accuracy"
 bottom: "fc6new"
 bottom: "label"
 top: "accuracy_train"
 include {
   stage: "train"
 }
 accuracy_param {
   top_k: 5
 }
}
layer {
 name: "softmax"
 type: "Softmax"
 bottom: "fc6new"
 top: "softmax"
 include {
   stage: "deploy"
 }
}