caffe模型训练个人出错集锦

5、想把yolov3的模型转换为caffe

使用工具：pytorch-caffe-darknet-convert

注意事项：

caffe中必须已经添加了

upsample_layer.cpp

upsample_layer.cu

upsample_layer.hpp

message UpsampleParameter{
  optional int32 scale = 1 [default = 1];
}

然后使用yolov3_darknet2caffe.py

python yolov3_darknet2caffe.py yolov3.cfg yolov3.weights yolov3.prototxt yolov3.caffemodel

error

ValueError: need more than 1 value to unpack

出错不能转换，排查错误

Training应该注释掉，正确应该是

6.多标签分类 0 1 0 1 0 0 0 0 255 255 255

没有加入ignore_label,导致loos为nan和loss超级大

layer {
  name: "cross_entropy"
  type: "SigmoidCrossEntropyLoss"
  bottom: "pedestrian-conv1000"
  bottom: "label"
  top: "cross_entropy"
  loss_param {
    ignore_label: 255
  }
}

template <typename Dtype>
void SigmoidCrossEntropyLossLayer<Dtype>::Forward_cpu(
    const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
  // The forward pass computes the sigmoid outputs.
  sigmoid_bottom_vec_[0] = bottom[0];
  sigmoid_layer_->Forward(sigmoid_bottom_vec_, sigmoid_top_vec_);
  // Compute the loss (negative log likelihood)
  // Stable version of loss computation from input data
  const Dtype* input_data = bottom[0]->cpu_data();
  const Dtype* target = bottom[1]->cpu_data();
  int valid_count = 0;
  Dtype loss = 0;
  for (int i = 0; i < bottom[0]->count(); ++i) {
    const int target_value = static_cast<int>(target[i]);
    if (has_ignore_label_ && target_value == ignore_label_) {
      continue;
    }
    loss -= input_data[i] * (target[i] - (input_data[i] >= 0)) -
        log(1 + exp(input_data[i] - 2 * input_data[i] * (input_data[i] >= 0)));
    ++valid_count;
  }
  normalizer_ = get_normalizer(normalization_, valid_count);
  top[0]->mutable_cpu_data()[0] = loss / normalizer_;
}

template <typename Dtype>
void SigmoidCrossEntropyLossLayer<Dtype>::Backward_cpu(
    const vector<Blob<Dtype>*>& top, const vector<bool>& propagate_down,
    const vector<Blob<Dtype>*>& bottom) {
  if (propagate_down[1]) {
    LOG(FATAL) << this->type()
               << " Layer cannot backpropagate to label inputs.";
  }
  if (propagate_down[0]) {
    // First, compute the diff
    const int count = bottom[0]->count();
    const Dtype* sigmoid_output_data = sigmoid_output_->cpu_data();
    const Dtype* target = bottom[1]->cpu_data();
    Dtype* bottom_diff = bottom[0]->mutable_cpu_diff();
    caffe_sub(count, sigmoid_output_data, target, bottom_diff);
    // Zero out gradient of ignored targets.
    if (has_ignore_label_) {
      for (int i = 0; i < count; ++i) {
        const int target_value = static_cast<int>(target[i]);
        if (target_value == ignore_label_) {
          bottom_diff[i] = 0;
        }
      }
    }
    // Scale down gradient
    Dtype loss_weight = top[0]->cpu_diff()[0] / normalizer_;
    caffe_scal(count, loss_weight, bottom_diff);
  }
}

7.预训练模型尽量加上，会快速降低loss

如果是目标检测的预训练模型，也可以用在目标分类上

8.可以尝试对网络剪枝

比如yolov3-tiny通道数目减半，只要数据可以，不会影响网络整体的效果