好的,多谢。那我是否可以理解使用caffe对模型“量化”就已经调用了MLU270的硬件呢?
您好,按照以下修改:layer { input:"input" input_dim:1 input_dim:3 input_dim:256 input_dim:192}又报了新的错误:[libprotobuf ERROR google/protobuf/text_format.cc:298] Error parsing text-format caffe.NetParameter: 2:8: Message type "caffe.LayerParameter" has no field named "input".F0803 17:15:44.062944 2885 upgrade_proto.cpp:514] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: /caffe/build/tools/sr_enhan.prototxt展开
您好,按照以下修改:
layer {
input:"input"}
又报了新的错误:
[libprotobuf ERROR google/protobuf/text_format.cc:298] Error parsing text-format caffe.NetParameter: 2:8: Message type "caffe.LayerParameter" has no field named "input".
F0803 17:15:44.062944 2885 upgrade_proto.cpp:514] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: /caffe/build/tools/sr_enhan.prototxt
我们这面采用以下推理的网络文件格式:layer { name: "input" type: "Input" top: "input" input_param { shape { dim: 1 dim: 3 dim: 256 dim: 192 } }}在执行./generate_quantized_pt -ini_file convert.ini时候却报错:F0802 16:44:38.928105 2811 image_data_layer.cpp:64] Check failed: (new_height == 0 && new_width == 0) || (new_height > 0 && new_width > 0) Current implementation requires new_height and new_width to be set at the same time.这里要怎么添加new_width和new_height呢?展开
我们这面采用以下推理的网络文件格式:
layer {
name: "input"}
在执行./generate_quantized_pt -ini_file convert.ini时候却报错:
F0802 16:44:38.928105 2811 image_data_layer.cpp:64] Check failed: (new_height == 0 && new_width == 0) || (new_height > 0 && new_width > 0) Current implementation requires new_height and new_width to be set at the same time.
这里要怎么添加new_width和new_height呢?
请登录后评论