C++ CHECK_EQ函数代码示例

void BaseConvolutionLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
  // Configure the kernel size, padding, stride, and inputs.
  ConvolutionParameter conv_param = this->layer_param_.convolution_param();
  force_nd_im2col_ = conv_param.force_nd_im2col();
  channel_axis_ = bottom[0]->CanonicalAxisIndex(conv_param.axis());
  const int first_spatial_axis = channel_axis_ + 1;
  const int num_axes = bottom[0]->num_axes();
  num_spatial_axes_ = num_axes - first_spatial_axis;
  CHECK_GE(num_spatial_axes_, 0);
  vector<int> bottom_dim_blob_shape(1, num_spatial_axes_ + 1);
  vector<int> spatial_dim_blob_shape(1, std::max(num_spatial_axes_, 1));
  // Setup filter kernel dimensions (kernel_shape_).
  kernel_shape_.Reshape(spatial_dim_blob_shape);
  int* kernel_shape_data = kernel_shape_.mutable_cpu_data();
  if (conv_param.has_kernel_h() || conv_param.has_kernel_w()) {
    CHECK_EQ(num_spatial_axes_, 2)
        << "kernel_h & kernel_w can only be used for 2D convolution.";
    CHECK_EQ(0, conv_param.kernel_size_size())
        << "Either kernel_size or kernel_h/w should be specified; not both.";
    kernel_shape_data[0] = conv_param.kernel_h();
    kernel_shape_data[1] = conv_param.kernel_w();
  } else {
    const int num_kernel_dims = conv_param.kernel_size_size();
    CHECK(num_kernel_dims == 1 || num_kernel_dims == num_spatial_axes_)
        << "kernel_size must be specified once, or once per spatial dimension "
        << "(kernel_size specified " << num_kernel_dims << " times; "
        << num_spatial_axes_ << " spatial dims).";
      for (int i = 0; i < num_spatial_axes_; ++i) {
        kernel_shape_data[i] =
            conv_param.kernel_size((num_kernel_dims == 1) ? 0 : i);
      }
  }
  for (int i = 0; i < num_spatial_axes_; ++i) {
    CHECK_GT(kernel_shape_data[i], 0) << "Filter dimensions must be nonzero.";
  }
  // Setup stride dimensions (stride_).
  stride_.Reshape(spatial_dim_blob_shape);
  int* stride_data = stride_.mutable_cpu_data();
  if (conv_param.has_stride_h() || conv_param.has_stride_w()) {
    CHECK_EQ(num_spatial_axes_, 2)
        << "stride_h & stride_w can only be used for 2D convolution.";
    CHECK_EQ(0, conv_param.stride_size())
        << "Either stride or stride_h/w should be specified; not both.";
    stride_data[0] = conv_param.stride_h();
    stride_data[1] = conv_param.stride_w();
  } else {
    const int num_stride_dims = conv_param.stride_size();
    CHECK(num_stride_dims == 0 || num_stride_dims == 1 ||
          num_stride_dims == num_spatial_axes_)
        << "stride must be specified once, or once per spatial dimension "
        << "(stride specified " << num_stride_dims << " times; "
        << num_spatial_axes_ << " spatial dims).";
    const int kDefaultStride = 1;
    for (int i = 0; i < num_spatial_axes_; ++i) {
      stride_data[i] = (num_stride_dims == 0) ? kDefaultStride :
          conv_param.stride((num_stride_dims == 1) ? 0 : i);
      CHECK_GT(stride_data[i], 0) << "Stride dimensions must be nonzero.";
    }
  }
  // Setup pad dimensions (pad_).
  pad_.Reshape(spatial_dim_blob_shape);
  int* pad_data = pad_.mutable_cpu_data();
  if (conv_param.has_pad_h() || conv_param.has_pad_w()) {
    CHECK_EQ(num_spatial_axes_, 2)
        << "pad_h & pad_w can only be used for 2D convolution.";
    CHECK_EQ(0, conv_param.pad_size())
        << "Either pad or pad_h/w should be specified; not both.";
    pad_data[0] = conv_param.pad_h();
    pad_data[1] = conv_param.pad_w();
  } else {
    const int num_pad_dims = conv_param.pad_size();
    CHECK(num_pad_dims == 0 || num_pad_dims == 1 ||
          num_pad_dims == num_spatial_axes_)
        << "pad must be specified once, or once per spatial dimension "
        << "(pad specified " << num_pad_dims << " times; "
        << num_spatial_axes_ << " spatial dims).";
    const int kDefaultPad = 0;
    for (int i = 0; i < num_spatial_axes_; ++i) {
      pad_data[i] = (num_pad_dims == 0) ? kDefaultPad :
          conv_param.pad((num_pad_dims == 1) ? 0 : i);
    }
  }
  // Setup dilation dimensions (dilation_).
  dilation_.Reshape(spatial_dim_blob_shape);
  int* dilation_data = dilation_.mutable_cpu_data();
  const int num_dilation_dims = conv_param.dilation_size();
  CHECK(num_dilation_dims == 0 || num_dilation_dims == 1 ||
        num_dilation_dims == num_spatial_axes_)
      << "dilation must be specified once, or once per spatial dimension "
      << "(dilation specified " << num_dilation_dims << " times; "
      << num_spatial_axes_ << " spatial dims).";
  const int kDefaultDilation = 1;
  for (int i = 0; i < num_spatial_axes_; ++i) {
    dilation_data[i] = (num_dilation_dims == 0) ? kDefaultDilation :
                       conv_param.dilation((num_dilation_dims == 1) ? 0 : i);
  }
  // Special case: im2col is the identity for 1x1 convolution with stride 1
  // and no padding, so flag for skipping the buffer and transformation.
  is_1x1_ = true;
//.........这里部分代码省略.........

//.........这里部分代码省略.........
  if (!pool_param.has_pad_h()) {
    pad_h_ = pad_w_ = pool_param.pad();
  } else {
    pad_h_ = pool_param.pad_h();
    pad_w_ = pool_param.pad_w();
  }
  if (!pool_param.has_stride_h()) {
    stride_h_ = stride_w_ = pool_param.stride();
  } else {
    stride_h_ = pool_param.stride_h();
    stride_w_ = pool_param.stride_w();
  }
  if (global_pooling_) {
    CHECK(pad_h_ == 0 && pad_w_ == 0 && stride_h_ == 1 && stride_w_ == 1)
      << "With Global_pooling: true; only pad = 0 and stride = 1";
  }
  if (pad_h_ != 0 || pad_w_ != 0) {
    CHECK(this->layer_param_.pooling_param().pool()
        == PoolingParameter_PoolMethod_AVE
        || this->layer_param_.pooling_param().pool()
        == PoolingParameter_PoolMethod_MAX)
        << "Padding implemented only for average and max pooling.";
    CHECK_LT(pad_h_, kernel_h_);
    CHECK_LT(pad_w_, kernel_w_);
  }

  pooled_height_ = static_cast<int>(ceil(static_cast<float>(
      bottom[0]->height() + 2 * pad_h_ - kernel_h_) / stride_h_)) + 1;
  pooled_width_ = static_cast<int>(ceil(static_cast<float>(
      bottom[0]->height() + 2 * pad_w_ - kernel_w_) / stride_w_)) + 1;
  if (pad_h_ || pad_w_) {
    // If we have padding, ensure that the last pooling starts strictly
    // inside the image (instead of at the padding); otherwise clip the last.
    if ((pooled_height_ - 1) * stride_h_ >= bottom[0]->height() + pad_h_) {
      --pooled_height_;
    }
    if ((pooled_width_ - 1) * stride_w_ >= bottom[0]->height() + pad_w_) {
      --pooled_width_;
    }
    CHECK_LT((pooled_height_ - 1) * stride_h_, bottom[0]->height() + pad_h_);
    CHECK_LT((pooled_width_ - 1) * stride_w_, bottom[0]->height() + pad_w_);
  }

  size_t dim = 4;
  size_t src_sizes[4], src_strides[4];
  size_t dst_sizes[4], dst_strides[4];

  src_sizes[0] = bottom[0]->width();
  src_sizes[1] = bottom[0]->height();
  src_sizes[2] = bottom[0]->channels();
  src_sizes[3] = bottom[0]->num();

  src_strides[0] = 1;
  src_strides[1] = src_sizes[0];
  src_strides[2] = src_sizes[0]*src_sizes[1];
  src_strides[3] = src_sizes[0]*src_sizes[1]*src_sizes[2];

  dst_sizes[0] = pooled_width_;
  dst_sizes[1] = pooled_height_;
  dst_sizes[2] = src_sizes[2];
  dst_sizes[3] = src_sizes[3];

  dst_strides[0] = 1;
  dst_strides[1] = dst_sizes[0];
  dst_strides[2] = dst_sizes[0]*dst_sizes[1];
  dst_strides[3] = dst_sizes[0]*dst_sizes[1]*dst_sizes[2];

  src_offset[0] = -pad_w_;
  src_offset[1] = -pad_h_;

  kernel_stride[0] = stride_w_;
  kernel_stride[1] = stride_h_;

  kernel_size[0] = kernel_w_;
  kernel_size[1] = kernel_h_;

  dnnError_t e;
  e = dnnLayoutCreate<Dtype>(&fwd_bottom_data->layout_usr, dim, src_sizes,
          src_strides);
  CHECK_EQ(e, E_SUCCESS);
  e = dnnLayoutCreate<Dtype>(&fwd_top_data->layout_usr, dim, dst_sizes,
          dst_strides);
  CHECK_EQ(e, E_SUCCESS);
  e = dnnLayoutCreate<Dtype>(&bwd_bottom_diff->layout_usr, dim, src_sizes,
          src_strides);
  CHECK_EQ(e, E_SUCCESS);
  e = dnnLayoutCreate<Dtype>(&bwd_top_diff->layout_usr, dim, dst_sizes,
          dst_strides);
  CHECK_EQ(e, E_SUCCESS);

  // Names are for debugging only
  fwd_bottom_data->name = "fwd_bottom_data   @ " + this->layer_param_.name();
  fwd_top_data->name =    "fwd_top_data      @ " + this->layer_param_.name();
  bwd_top_diff->name =    "bwd_top_diff      @ " + this->layer_param_.name();
  bwd_bottom_diff->name = "bwd_bottom_diff   @ " + this->layer_param_.name();

  // Primitives will be allocated during the first fwd pass
  poolingFwd = NULL;
  poolingBwd = NULL;
}

static void* sender(void* arg) {
    SendArg* sa = (SendArg*)arg;
    int64_t value = 0;
    while (!brpc::IsAskedToQuit()) {
        braft::PeerId leader;
        // Select leader of the target group from RouteTable
        if (braft::rtb::select_leader(FLAGS_group, &leader) != 0) {
            // Leader is unknown in RouteTable. Ask RouteTable to refresh leader
            // by sending RPCs.
            butil::Status st = braft::rtb::refresh_leader(
                        FLAGS_group, FLAGS_timeout_ms);
            if (!st.ok()) {
                // Not sure about the leader, sleep for a while and the ask again.
                LOG(WARNING) << "Fail to refresh_leader : " << st;
                bthread_usleep(FLAGS_timeout_ms * 1000L);
            }
            continue;
        }

        // Now we known who is the leader, construct Stub and then sending
        // rpc
        brpc::Channel channel;
        if (channel.Init(leader.addr, NULL) != 0) {
            LOG(ERROR) << "Fail to init channel to " << leader;
            bthread_usleep(FLAGS_timeout_ms * 1000L);
            continue;
        }
        example::AtomicService_Stub stub(&channel);

        brpc::Controller cntl;
        cntl.set_timeout_ms(FLAGS_timeout_ms);
        example::CompareExchangeRequest request;
        example::AtomicResponse response;
        request.set_id(sa->id);
        request.set_expected_value(value);
        request.set_new_value(value + 1);

        stub.compare_exchange(&cntl, &request, &response, NULL);

        if (cntl.Failed()) {
            LOG(WARNING) << "Fail to send request to " << leader
                         << " : " << cntl.ErrorText();
            // Clear leadership since this RPC failed.
            braft::rtb::update_leader(FLAGS_group, braft::PeerId());
            bthread_usleep(FLAGS_timeout_ms * 1000L);
            continue;
        }

        if (!response.success()) {
            // A redirect response
            if (!response.has_old_value()) {
                LOG(WARNING) << "Fail to send request to " << leader
                             << ", redirecting to "
                             << (response.has_redirect() 
                                    ? response.redirect() : "nowhere");
                // Update route table since we have redirect information
                braft::rtb::update_leader(FLAGS_group, response.redirect());
                continue;
            }
            // old_value unmatches expected value check if this is the initial
            // request
            if (value == 0 || response.old_value() == value + 1) {
                //   ^^^                          ^^^
                // It's initalized value          ^^^
                //                          There was false negative
                value = response.old_value();
            } else {
                CHECK_EQ(value, response.old_value());
                exit(-1);
            }
        } else {
            value = response.new_value();
        }
        g_latency_recorder << cntl.latency_us();
        if (FLAGS_log_each_request) {
            LOG(INFO) << "Received response from " << leader
                      << " old_value=" << response.old_value()
                      << " new_value=" << response.new_value()
                      << " latency=" << cntl.latency_us();
            bthread_usleep(1000L * 1000L);
        }
    }
    return NULL;
}

void DataLayer<Dtype>::SetUp(const vector<Blob<Dtype>*>& bottom,
      vector<Blob<Dtype>*>* top) {
  CHECK_EQ(bottom.size(), 0) << "Data Layer takes no input blobs.";
  CHECK_GE(top->size(), 1) << "Data Layer takes at least one blob as output.";
  CHECK_LE(top->size(), 2) << "Data Layer takes at most two blobs as output.";
  if (top->size() == 1) {
    output_labels_ = false;
  } else {
    output_labels_ = true;
  }
  // Initialize the leveldb
  leveldb::DB* db_temp;
  leveldb::Options options;
  options.create_if_missing = false;
  options.max_open_files = 10;
  LOG(INFO) << "Opening leveldb " << this->layer_param_.data_param().source();
  leveldb::Status status = leveldb::DB::Open(
      options, this->layer_param_.data_param().source(), &db_temp);
  CHECK(status.ok()) << "Failed to open leveldb "
      << this->layer_param_.data_param().source() << std::endl
      << status.ToString();
  db_.reset(db_temp);
  iter_.reset(db_->NewIterator(leveldb::ReadOptions()));
  iter_->SeekToFirst();
  // Check if we would need to randomly skip a few data points
  if (this->layer_param_.data_param().rand_skip()) {
    unsigned int skip = caffe_rng_rand() %
                        this->layer_param_.data_param().rand_skip();
    LOG(INFO) << "Skipping first " << skip << " data points.";
    while (skip-- > 0) {
      iter_->Next();
      if (!iter_->Valid()) {
        iter_->SeekToFirst();
      }
    }
  }
  // Read a data point, and use it to initialize the top blob.
  Datum datum;
  datum.ParseFromString(iter_->value().ToString());
  // image
  int crop_size = this->layer_param_.data_param().crop_size();
  if (crop_size > 0) {
    (*top)[0]->Reshape(this->layer_param_.data_param().batch_size(),
                       datum.channels(), crop_size, crop_size);
    prefetch_data_.reset(new Blob<Dtype>(
        this->layer_param_.data_param().batch_size(), datum.channels(),
        crop_size, crop_size));
  } else {
    (*top)[0]->Reshape(
        this->layer_param_.data_param().batch_size(), datum.channels(),
        datum.height(), datum.width());
    prefetch_data_.reset(new Blob<Dtype>(
        this->layer_param_.data_param().batch_size(), datum.channels(),
        datum.height(), datum.width()));
  }
  LOG(INFO) << "output data size: " << (*top)[0]->num() << ","
      << (*top)[0]->channels() << "," << (*top)[0]->height() << ","
      << (*top)[0]->width();
  // label
  if (output_labels_) {
    (*top)[1]->Reshape(this->layer_param_.data_param().batch_size(), 1, 1, 1);
    prefetch_label_.reset(
        new Blob<Dtype>(this->layer_param_.data_param().batch_size(), 1, 1, 1));
  }
  // datum size
  datum_channels_ = datum.channels();
  datum_height_ = datum.height();
  datum_width_ = datum.width();
  datum_size_ = datum.channels() * datum.height() * datum.width();
  CHECK_GT(datum_height_, crop_size);
  CHECK_GT(datum_width_, crop_size);
  // check if we want to have mean
  if (this->layer_param_.data_param().has_mean_file()) {
    const string& mean_file = this->layer_param_.data_param().mean_file();
    LOG(INFO) << "Loading mean file from" << mean_file;
    BlobProto blob_proto;
    ReadProtoFromBinaryFileOrDie(mean_file.c_str(), &blob_proto);
    data_mean_.FromProto(blob_proto);
    CHECK_EQ(data_mean_.num(), 1);
    CHECK_EQ(data_mean_.channels(), datum_channels_);
    CHECK_EQ(data_mean_.height(), datum_height_);
    CHECK_EQ(data_mean_.width(), datum_width_);
  } else {
    // Simply initialize an all-empty mean.
    data_mean_.Reshape(1, datum_channels_, datum_height_, datum_width_);
  }
  // Now, start the prefetch thread. Before calling prefetch, we make two
  // cpu_data calls so that the prefetch thread does not accidentally make
  // simultaneous cudaMalloc calls when the main thread is running. In some
  // GPUs this seems to cause failures if we do not so.
  prefetch_data_->mutable_cpu_data();
  if (output_labels_) {
    prefetch_label_->mutable_cpu_data();
  }
  data_mean_.cpu_data();
  DLOG(INFO) << "Initializing prefetch";
  CreatePrefetchThread();
  DLOG(INFO) << "Prefetch initialized.";
}

void FilterLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
  CHECK_EQ(top.size(), bottom.size() - 1);
  first_reshape_ = true;
}

void ir_call_external_1(struct ir *ir, struct ir_value *addr) {
  CHECK_EQ(addr->type, VALUE_I64);

  struct ir_instr *instr = ir_append_instr(ir, OP_CALL_EXTERNAL, VALUE_V);
  ir_set_arg0(ir, instr, addr);
}

static status_t parseStreamMuxConfig(
        ABitReader *bits,
        unsigned *numSubFrames,
        unsigned *frameLengthType,
        ssize_t *fixedFrameLength,
        bool *otherDataPresent,
        unsigned *otherDataLenBits) {
    unsigned audioMuxVersion = bits->getBits(1);

    unsigned audioMuxVersionA = 0;
    if (audioMuxVersion == 1) {
        audioMuxVersionA = bits->getBits(1);
    }

    CHECK_EQ(audioMuxVersionA, 0u);  // otherwise future spec

    if (audioMuxVersion != 0) {
        return ERROR_UNSUPPORTED;  // XXX to be implemented;
    }
    CHECK_EQ(audioMuxVersion, 0u);  // XXX to be implemented

    unsigned allStreamsSameTimeFraming = bits->getBits(1);
    CHECK_EQ(allStreamsSameTimeFraming, 1u);  // There's only one stream.

    *numSubFrames = bits->getBits(6);
    unsigned numProgram = bits->getBits(4);
    CHECK_EQ(numProgram, 0u);  // disabled in RTP LATM

    unsigned numLayer = bits->getBits(3);
    CHECK_EQ(numLayer, 0u);  // disabled in RTP LATM

    if (audioMuxVersion == 0) {
        // AudioSpecificConfig
        CHECK_EQ(parseAudioSpecificConfig(bits, NULL /* asc */), (status_t)OK);
    } else {
        TRESPASS();  // XXX to be implemented
    }

    *frameLengthType = bits->getBits(3);
    *fixedFrameLength = -1;

    switch (*frameLengthType) {
        case 0:
        {
            /* unsigned bufferFullness = */bits->getBits(8);

            // The "coreFrameOffset" does not apply since there's only
            // a single layer.
            break;
        }

        case 1:
        {
            *fixedFrameLength = bits->getBits(9);
            break;
        }

        case 2:
        {
            // reserved
            TRESPASS();
            break;
        }

        case 3:
        case 4:
        case 5:
        {
            /* unsigned CELPframeLengthTableIndex = */bits->getBits(6);
            break;
        }

        case 6:
        case 7:
        {
            /* unsigned HVXCframeLengthTableIndex = */bits->getBits(1);
            break;
        }

        default:
            break;
    }

#ifdef STE_HARDWARE
    status_t parseResult = OK;
#endif
    *otherDataPresent = bits->getBits(1);
    *otherDataLenBits = 0;
    if (*otherDataPresent) {
        if (audioMuxVersion == 1) {
            TRESPASS();  // XXX to be implemented
#ifdef STE_HARDWARE
        } else if (bits->numBitsLeft() < 9) {
            parseResult = ERROR_MALFORMED;
#endif
        } else {
            *otherDataLenBits = 0;

            unsigned otherDataLenEsc;
            do {
//.........这里部分代码省略.........

void Net<Dtype>::Init(const NetParameter& in_param) {
  LOG(INFO) << "Initializing net from parameters: " << std::endl
            << in_param.DebugString();
  // Create a copy of in_param with splits added where necessary.
  NetParameter param;
  InsertSplits(in_param, &param);
  // Basically, build all the layers and set up its connections.
  name_ = param.name();
  map<string, int> blob_name_to_idx;
  set<string> available_blobs;
  int num_layers = param.layers_size();
  CHECK_EQ(param.input_size() * 4, param.input_dim_size())
      << "Incorrect bottom blob dimension specifications.";
  size_t memory_used = 0;
  // set the input blobs
  for (int i = 0; i < param.input_size(); ++i) {
    const string& blob_name = param.input(i);
    shared_ptr<Blob<Dtype> > blob_pointer(
        new Blob<Dtype>(param.input_dim(i * 4),
                        param.input_dim(i * 4 + 1),
                        param.input_dim(i * 4 + 2),
                        param.input_dim(i * 4 + 3)));
    blobs_.push_back(blob_pointer);
    blob_names_.push_back(blob_name);
    blob_need_backward_.push_back(param.force_backward());
    net_input_blob_indices_.push_back(i);
    net_input_blobs_.push_back(blob_pointer.get());
    blob_name_to_idx[blob_name] = i;
    available_blobs.insert(blob_name);
    memory_used += blob_pointer->count();
  }
  DLOG(INFO) << "Memory required for Data" << memory_used*sizeof(Dtype);
  // For each layer, set up their input and output
  bottom_vecs_.resize(param.layers_size());
  top_vecs_.resize(param.layers_size());
  bottom_id_vecs_.resize(param.layers_size());
  top_id_vecs_.resize(param.layers_size());
  for (int i = 0; i < param.layers_size(); ++i) {
    bool in_place = false;
    const LayerParameter& layer_param = param.layers(i);
    layers_.push_back(shared_ptr<Layer<Dtype> >(GetLayer<Dtype>(layer_param)));
    layer_names_.push_back(layer_param.name());
    LOG(INFO) << "Creating Layer " << layer_param.name();
    bool need_backward = param.force_backward();
    // Figure out this layer's input and output
    for (int j = 0; j < layer_param.bottom_size(); ++j) {
      const string& blob_name = layer_param.bottom(j);
      const int blob_id = blob_name_to_idx[blob_name];
      if (available_blobs.find(blob_name) == available_blobs.end()) {
        LOG(FATAL) << "Unknown blob input " << blob_name <<
            " to layer" << j;
      }
      LOG(INFO) << layer_param.name() << " <- " << blob_name;
      bottom_vecs_[i].push_back(
          blobs_[blob_id].get());
      bottom_id_vecs_[i].push_back(blob_id);
      // If a blob needs backward, this layer should provide it.
      need_backward |= blob_need_backward_[blob_id];
      available_blobs.erase(blob_name);
    }
    for (int j = 0; j < layer_param.top_size(); ++j) {
      const string& blob_name = layer_param.top(j);
      // Check if we are doing in-place computation
      if (layer_param.bottom_size() > j &&
          blob_name == layer_param.bottom(j)) {
        // In-place computation
        LOG(INFO) << layer_param.name() << " -> " << blob_name << " (in-place)";
        in_place = true;
        available_blobs.insert(blob_name);
        top_vecs_[i].push_back(
            blobs_[blob_name_to_idx[blob_name]].get());
        top_id_vecs_[i].push_back(blob_name_to_idx[blob_name]);
      } else if (blob_name_to_idx.find(blob_name) != blob_name_to_idx.end()) {
        // If we are not doing in-place computation but has duplicated blobs,
        // raise an error.
        LOG(FATAL) << "Duplicate blobs produced by multiple sources.";
      } else {
        // Normal output.
        LOG(INFO) << layer_param.name() << " -> " << blob_name;
        shared_ptr<Blob<Dtype> > blob_pointer(new Blob<Dtype>());
        blobs_.push_back(blob_pointer);
        blob_names_.push_back(blob_name);
        blob_need_backward_.push_back(param.force_backward());
        blob_name_to_idx[blob_name] = blob_names_.size() - 1;
        available_blobs.insert(blob_name);
        top_vecs_[i].push_back(blobs_[blob_names_.size() - 1].get());
        top_id_vecs_[i].push_back(blob_names_.size() - 1);
      }
    }
    // After this layer is connected, set it up.
    // LOG(INFO) << "Setting up " << layer_names_[i];
    layers_[i]->SetUp(bottom_vecs_[i], &top_vecs_[i]);
    for (int topid = 0; topid < top_vecs_[i].size(); ++topid) {
      LOG(INFO) << "Top shape: " << top_vecs_[i][topid]->num() << " "
          << top_vecs_[i][topid]->channels() << " "
          << top_vecs_[i][topid]->height() << " "
          << top_vecs_[i][topid]->width() << " ("
          << top_vecs_[i][topid]->count() << ")";
      if (!in_place)
        memory_used += top_vecs_[i][topid]->count();
//.........这里部分代码省略.........

 void constructor_sanity_check() {
   CHECK_EQ(0, this->param_.momentum())
       << "Momentum cannot be used with AdaGrad.";
 }

void LSTMLayer<Dtype>::FillUnrolledNet(NetParameter* net_param) const {
  const int num_output = this->layer_param_.recurrent_param().num_output();
  CHECK_GT(num_output, 0) << "num_output must be positive";
  const FillerParameter& weight_filler =
      this->layer_param_.recurrent_param().weight_filler();
  const FillerParameter& bias_filler =
      this->layer_param_.recurrent_param().bias_filler();

  // Add generic LayerParameter's (without bottoms/tops) of layer types we'll
  // use to save redundant code.
  LayerParameter hidden_param;
  hidden_param.set_type("InnerProduct");
  hidden_param.mutable_inner_product_param()->set_num_output(num_output * 4);
  hidden_param.mutable_inner_product_param()->set_bias_term(false);
  hidden_param.mutable_inner_product_param()->set_axis(2);
  hidden_param.mutable_inner_product_param()->
      mutable_weight_filler()->CopyFrom(weight_filler);

  LayerParameter biased_hidden_param(hidden_param);
  biased_hidden_param.mutable_inner_product_param()->set_bias_term(true);
  biased_hidden_param.mutable_inner_product_param()->
      mutable_bias_filler()->CopyFrom(bias_filler);

  LayerParameter sum_param;
  sum_param.set_type("Eltwise");
  sum_param.mutable_eltwise_param()->set_operation(
      EltwiseParameter_EltwiseOp_SUM);

  LayerParameter scale_param;
  scale_param.set_type("Scale");
  scale_param.mutable_scale_param()->set_axis(0);

  LayerParameter slice_param;
  slice_param.set_type("Slice");
  slice_param.mutable_slice_param()->set_axis(0);

  LayerParameter split_param;
  split_param.set_type("Split");

  vector<BlobShape> input_shapes;
  RecurrentInputShapes(&input_shapes);
  CHECK_EQ(2, input_shapes.size());

  LayerParameter* input_layer_param = net_param->add_layer();
  input_layer_param->set_type("Input");
  InputParameter* input_param = input_layer_param->mutable_input_param();

  input_layer_param->add_top("c_0");
  input_param->add_shape()->CopyFrom(input_shapes[0]);

  input_layer_param->add_top("h_0");
  input_param->add_shape()->CopyFrom(input_shapes[1]);

  LayerParameter* cont_slice_param = net_param->add_layer();
  cont_slice_param->CopyFrom(slice_param);
  cont_slice_param->set_name("cont_slice");
  cont_slice_param->add_bottom("cont");
  cont_slice_param->mutable_slice_param()->set_axis(0);

  // Add layer to transform all timesteps of x to the hidden state dimension.
  //     W_xc_x = W_xc * x + b_c
  {
    LayerParameter* x_transform_param = net_param->add_layer();
    x_transform_param->CopyFrom(biased_hidden_param);
    x_transform_param->set_name("x_transform");
    x_transform_param->add_param()->set_name("W_xc");
    x_transform_param->add_param()->set_name("b_c");
    x_transform_param->add_bottom("x");
    x_transform_param->add_top("W_xc_x");
    x_transform_param->add_propagate_down(true);
  }

  if (this->static_input_) {
    // Add layer to transform x_static to the gate dimension.
    //     W_xc_x_static = W_xc_static * x_static
    LayerParameter* x_static_transform_param = net_param->add_layer();
    x_static_transform_param->CopyFrom(hidden_param);
    x_static_transform_param->mutable_inner_product_param()->set_axis(1);
    x_static_transform_param->set_name("W_xc_x_static");
    x_static_transform_param->add_param()->set_name("W_xc_static");
    x_static_transform_param->add_bottom("x_static");
    x_static_transform_param->add_top("W_xc_x_static_preshape");
    x_static_transform_param->add_propagate_down(true);

    LayerParameter* reshape_param = net_param->add_layer();
    reshape_param->set_type("Reshape");
    BlobShape* new_shape =
         reshape_param->mutable_reshape_param()->mutable_shape();
    new_shape->add_dim(1);  // One timestep.
    // Should infer this->N as the dimension so we can reshape on batch size.
    new_shape->add_dim(-1);
    new_shape->add_dim(
        x_static_transform_param->inner_product_param().num_output());
    reshape_param->set_name("W_xc_x_static_reshape");
    reshape_param->add_bottom("W_xc_x_static_preshape");
    reshape_param->add_top("W_xc_x_static");
  }

  LayerParameter* x_slice_param = net_param->add_layer();
  x_slice_param->CopyFrom(slice_param);
//.........这里部分代码省略.........

void Convolution3DLayer<Dtype>::SetUp(const vector<Blob<Dtype>*>& bottom,
      vector<Blob<Dtype>*>* top) {
  CHECK_EQ(bottom.size(), 1) << "Conv Layer takes a single blob as input.";
  CHECK_EQ(top->size(), 1) << "Conv Layer takes a single blob as output.";

  kernel_size_ = this->layer_param_.convolution_param().kernel_size();
  kernel_depth_ = this->layer_param_.convolution_param().kernel_depth();
  stride_ = this->layer_param_.convolution_param().stride();
  temporal_stride_ = this->layer_param_.convolution_param().temporal_stride();
  pad_ = this->layer_param_.convolution_param().pad();
  temporal_pad_ = this->layer_param_.convolution_param().temporal_pad();
  num_ = bottom[0]->num();
  channels_ = bottom[0]->channels();
  length_ = bottom[0]->length();
  height_ = bottom[0]->height();
  width_ = bottom[0]->width();
  num_output_ = this->layer_param_.convolution_param().num_output();
  filter_group_ = this->layer_param_.convolution_param().filter_group();
  CHECK_GT(num_output_, 0);

  // number of output filters must be divided by filter_group
  CHECK_EQ(num_output_ % filter_group_, 0);

  // The vol2col result buffer would only hold one image at a time to avoid
  // overly large memory usage.

  int height_out = (height_ + 2 * pad_ - kernel_size_) / stride_ + 1;
  int width_out = (width_ + 2 * pad_ - kernel_size_) / stride_ + 1;
  int length_out = (length_ + 2 * temporal_pad_ - kernel_depth_) / temporal_stride_ + 1;

  // buffer for one image
  col_buffer_.Reshape(
      1, channels_ * kernel_depth_ * kernel_size_ * kernel_size_, length_out, height_out, width_out);


  bias_term_ = this->layer_param_.convolution_param().bias_term();

  // Figure out the dimensions for individual gemms.
  M_ = num_output_ / filter_group_; // doing convolution filter_group_ times per volume
  K_ = channels_ * kernel_depth_ * kernel_size_ * kernel_size_;
  N_ = length_out * height_out * width_out;

  // output size
  (*top)[0]->Reshape(bottom[0]->num(), num_output_, length_out, height_out, width_out);

  // Check if we need to set up the weights
  if (this->blobs_.size() > 0) {
    LOG(INFO) << "Skipping parameter initialization";
  } else {
    if (bias_term_) {
      this->blobs_.resize(2);
    } else {
      this->blobs_.resize(1);
    }
    // Initialize the weights
    this->blobs_[0].reset(new Blob<Dtype>(
        num_output_, channels_, kernel_depth_, kernel_size_, kernel_size_));
    // fill the weights
    shared_ptr<Filler<Dtype> > weight_filler(GetFiller<Dtype>(
        this->layer_param_.convolution_param().weight_filler()));
    weight_filler->Fill(this->blobs_[0].get());
    // If necessary, initialize and fill the bias term
    if (bias_term_) {
      this->blobs_[1].reset(new Blob<Dtype>(1, 1, 1, 1, num_output_));
      shared_ptr<Filler<Dtype> > bias_filler(GetFiller<Dtype>(
          this->layer_param_.convolution_param().bias_filler()));
      bias_filler->Fill(this->blobs_[1].get());
    }


  }

  // Set up the bias filler
  if (bias_term_) {
    bias_multiplier_.reset(new SyncedMemory(N_ * sizeof(Dtype)));
    Dtype* bias_multiplier_data =
        reinterpret_cast<Dtype*>(bias_multiplier_->mutable_cpu_data());
    for (int i = 0; i < N_; ++i) {
        bias_multiplier_data[i] = 1.;
    }
  }
}

void Blob<Dtype>::ShareData(const Blob& other) {
  CHECK_EQ(count_, other.count());
  data_ = other.data();
}

void GradientChecker<Dtype>::CheckGradientSingle(Layer<Dtype>* layer,
    vector<Blob<Dtype>*>* bottom, vector<Blob<Dtype>*>* top,
    int check_bottom, int top_id, int top_data_id, bool element_wise) {
  if (element_wise) {
    CHECK_EQ(0, layer->blobs().size());
    CHECK_LE(0, top_id);
    CHECK_LE(0, top_data_id);
    const int top_count = (*top)[top_id]->count();
    for (int blob_id = 0; blob_id < bottom->size(); ++blob_id) {
      CHECK_EQ(top_count, (*bottom)[blob_id]->count());
    }
  }
  // First, figure out what blobs we need to check against.
  vector<Blob<Dtype>*> blobs_to_check;
  for (int i = 0; i < layer->blobs().size(); ++i) {
    blobs_to_check.push_back(layer->blobs()[i].get());
  }
  if (check_bottom < 0) {
    for (int i = 0; i < bottom->size(); ++i) {
      blobs_to_check.push_back((*bottom)[i]);
    }
  } else {
    CHECK(check_bottom < bottom->size());
    blobs_to_check.push_back((*bottom)[check_bottom]);
  }
  // Compute the gradient analytically using Backward
  Caffe::set_random_seed(seed_);
  // Get any loss from the layer
  Dtype computed_objective = layer->Forward(*bottom, top);
  // Get additional loss from the objective
  computed_objective += GetObjAndGradient(top, top_id, top_data_id);
  layer->Backward(*top, true, bottom);
  // Store computed gradients for all checked blobs
  vector<shared_ptr<Blob<Dtype> > >
      computed_gradient_blobs(blobs_to_check.size());
  for (int blob_id = 0; blob_id < blobs_to_check.size(); ++blob_id) {
    Blob<Dtype>* current_blob = blobs_to_check[blob_id];
    computed_gradient_blobs[blob_id].reset(new Blob<Dtype>());
    computed_gradient_blobs[blob_id]->ReshapeLike(*current_blob);
    const int count = blobs_to_check[blob_id]->count();
    const Dtype* diff = blobs_to_check[blob_id]->cpu_diff();
    Dtype* computed_gradients =
        computed_gradient_blobs[blob_id]->mutable_cpu_data();
    caffe_copy(count, diff, computed_gradients);
  }
  // Compute derivative of top w.r.t. each bottom and parameter input using
  // finite differencing.
  // LOG(ERROR) << "Checking " << blobs_to_check.size() << " blobs.";
  for (int blob_id = 0; blob_id < blobs_to_check.size(); ++blob_id) {
    Blob<Dtype>* current_blob = blobs_to_check[blob_id];
    const Dtype* computed_gradients =
        computed_gradient_blobs[blob_id]->cpu_data();
    // LOG(ERROR) << "Blob " << blob_id << ": checking "
    //     << current_blob->count() << " parameters.";
    for (int feat_id = 0; feat_id < current_blob->count(); ++feat_id) {
      // For an element-wise layer, we only need to do finite differencing to
      // compute the derivative of (*top)[top_id][top_data_id] w.r.t.
      // (*bottom)[blob_id][i] only for i == top_data_id.  For any other
      // i != top_data_id, we know the derivative is 0 by definition, and simply
      // check that that's true.
      Dtype estimated_gradient = 0;
      if (!element_wise || (feat_id == top_data_id)) {
        // Do finite differencing.
        // Compute loss with stepsize_ added to input.
        current_blob->mutable_cpu_data()[feat_id] += stepsize_;
        Caffe::set_random_seed(seed_);
        Dtype positive_objective = layer->Forward(*bottom, top);
        positive_objective += GetObjAndGradient(top, top_id, top_data_id);
        // Compute loss with stepsize_ subtracted from input.
        current_blob->mutable_cpu_data()[feat_id] -= stepsize_ * 2;
        Caffe::set_random_seed(seed_);
        Dtype negative_objective = layer->Forward(*bottom, top);
        negative_objective += GetObjAndGradient(top, top_id, top_data_id);
        // Recover original input value.
        current_blob->mutable_cpu_data()[feat_id] += stepsize_;
        estimated_gradient = (positive_objective - negative_objective) /
            stepsize_ / 2.;
      }
      Dtype computed_gradient = computed_gradients[feat_id];
      Dtype feature = current_blob->cpu_data()[feat_id];
      // LOG(ERROR) << "debug: " << current_blob->cpu_data()[feat_id] << " "
      //     << current_blob->cpu_diff()[feat_id];
      if (kink_ - kink_range_ > fabs(feature)
          || fabs(feature) > kink_ + kink_range_) {
        // We check relative accuracy, but for too small values, we threshold
        // the scale factor by 1.
        Dtype scale = max(
            max(fabs(computed_gradient), fabs(estimated_gradient)), 1.);
        EXPECT_NEAR(computed_gradient, estimated_gradient, threshold_ * scale)
          << "debug: (top_id, top_data_id, blob_id, feat_id)="
          << top_id << "," << top_data_id << "," << blob_id << "," << feat_id;
      }
      // LOG(ERROR) << "Feature: " << current_blob->cpu_data()[feat_id];
      // LOG(ERROR) << "computed gradient: " << computed_gradient
      //    << " estimated_gradient: " << estimated_gradient;
    }
  }
}

void BaseConvolutionLayer<Dtype>::Reshape(const vector<Blob<Dtype>*>& bottom,
      const vector<Blob<Dtype>*>& top) {
  const int first_spatial_axis = channel_axis_ + 1;
  CHECK_EQ(bottom[0]->num_axes(), first_spatial_axis + num_spatial_axes_)
      << "bottom num_axes may not change.";
  num_ = bottom[0]->count(0, channel_axis_);
  CHECK_EQ(bottom[0]->shape(channel_axis_), channels_)
      << "Input size incompatible with convolution kernel.";
  // TODO: generalize to handle inputs of different shapes.
  for (int bottom_id = 1; bottom_id < bottom.size(); ++bottom_id) {
    CHECK(bottom[0]->shape() == bottom[bottom_id]->shape())
        << "All inputs must have the same shape.";
  }
  // Shape the tops.
  bottom_shape_ = &bottom[0]->shape();
  compute_output_shape();
  vector<int> top_shape(bottom[0]->shape().begin(),
      bottom[0]->shape().begin() + channel_axis_);
  top_shape.push_back(num_output_);
  for (int i = 0; i < num_spatial_axes_; ++i) {
    top_shape.push_back(output_shape_[i]);
  }
  for (int top_id = 0; top_id < top.size(); ++top_id) {
    top[top_id]->Reshape(top_shape);
  }
  if (reverse_dimensions()) {
    conv_out_spatial_dim_ = bottom[0]->count(first_spatial_axis);
  } else {
    conv_out_spatial_dim_ = top[0]->count(first_spatial_axis);
  }
  col_offset_ = kernel_dim_ * conv_out_spatial_dim_;
  output_offset_ = conv_out_channels_ * conv_out_spatial_dim_ / group_;
  // Setup input dimensions (conv_input_shape_).
  vector<int> bottom_dim_blob_shape(1, num_spatial_axes_ + 1);
  conv_input_shape_.Reshape(bottom_dim_blob_shape);
  int* conv_input_shape_data = conv_input_shape_.mutable_cpu_data();
  for (int i = 0; i < num_spatial_axes_ + 1; ++i) {
    if (reverse_dimensions()) {
      conv_input_shape_data[i] = top[0]->shape(channel_axis_ + i);
    } else {
      conv_input_shape_data[i] = bottom[0]->shape(channel_axis_ + i);
    }
  }
  // The im2col result buffer will only hold one image at a time to avoid
  // overly large memory usage. In the special case of 1x1 convolution
  // it goes lazily unused to save memory.
  col_buffer_shape_.clear();
  col_buffer_shape_.push_back(kernel_dim_ * group_);
  for (int i = 0; i < num_spatial_axes_; ++i) {
    if (reverse_dimensions()) {
      col_buffer_shape_.push_back(input_shape(i + 1));
    } else {
      col_buffer_shape_.push_back(output_shape_[i]);
    }
  }
  col_buffer_.Reshape(col_buffer_shape_);
  bottom_dim_ = bottom[0]->count(channel_axis_);
  top_dim_ = top[0]->count(channel_axis_);
  num_kernels_im2col_ = conv_in_channels_ * conv_out_spatial_dim_;
  num_kernels_col2im_ = reverse_dimensions() ? top_dim_ : bottom_dim_;
  // Set up the all ones "bias multiplier" for adding biases by BLAS
  out_spatial_dim_ = top[0]->count(first_spatial_axis);
  if (bias_term_) {
    vector<int> bias_multiplier_shape(1, out_spatial_dim_);
    bias_multiplier_.Reshape(bias_multiplier_shape);
    caffe_set(bias_multiplier_.count(), Dtype(1),
        bias_multiplier_.mutable_cpu_data());
  }
}

SoftHEVC::~SoftHEVC() {
    ALOGD("In SoftHEVC::~SoftHEVC");
    CHECK_EQ(deInitDecoder(), (status_t)OK);
}