darkflow将.weights转换为.pb文件

1.更新conda

conda update conda

2.安装tensorfow

conda install tensorflow

3.安装opencv

conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/

conda install --channel https://conda.anaconda.org/menpo opencv

4.安装darkflow,假设你已经下载好源码，切换到源码目录

pip install -e .

5.执行以下命令验证安装是否成功

flow --h

如果看到如下信息则表示安装成功

Example usage: flow --imgdir sample_img/ --model cfg/yolo.cfg --load bin/yolo.weights

Arguments:
  --help, --h, -h  show this super helpful message and exit
  --imgdir         path to testing directory with images
  --binary         path to .weights directory
  --config         path to .cfg directory
  --dataset        path to dataset directory
  --labels         path to labels file
  --backup         path to backup folder
  --summary        path to TensorBoard summaries directory
  --annotation     path to annotation directory
  --threshold      detection threshold
  --model          configuration of choice
  --trainer        training algorithm
  --momentum       applicable for rmsprop and momentum optimizers
  --verbalise      say out loud while building graph
  --train          train the whole net
  --load           how to initialize the net? Either from .weights or a checkpoint, or even from scratch
  --savepb         save net and weight to a .pb file
  --gpu            how much gpu (from 0.0 to 1.0)
  --gpuName        GPU device name
  --lr             learning rate
  --keep           Number of most recent training results to save
  --batch          batch size
  --epoch          number of epoch
  --save           save checkpoint every ? training examples
  --demo           demo on webcam
  --queue          process demo in batch
  --json           Outputs bounding box information in json format.
  --saveVideo      Records video from input video or camera
  --pbLoad         path to .pb protobuf file (metaLoad must also be specified)
  --metaLoad       path to .meta file generated during --savepb that corresponds to .pb file

6.执行转换

flow --model cfg/yolo.cfg --load /your path/yolov2.weights  --savepb

当你看到如下信息，表示转换成功，可以在/your path/darkflow/built_graph 下找到转换好的文件。

Successfully identified 203934260 bytes
Finished in 0.02666330337524414s
Model has a coco model name, loading coco labels.

Building net ...
Source | Train? | Layer description                | Output size
-------+--------+----------------------------------+---------------
       |        | input                            | (?, 608, 608, 3)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 608, 608, 32)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 304, 304, 32)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 304, 304, 64)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 152, 152, 64)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 152, 152, 128)
 Load  |  Yep!  | conv 1x1p0_1  +bnorm  leaky      | (?, 152, 152, 64)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 152, 152, 128)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 76, 76, 128)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 76, 76, 256)
 Load  |  Yep!  | conv 1x1p0_1  +bnorm  leaky      | (?, 76, 76, 128)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 76, 76, 256)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 38, 38, 256)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 38, 38, 512)
 Load  |  Yep!  | conv 1x1p0_1  +bnorm  leaky      | (?, 38, 38, 256)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 38, 38, 512)
 Load  |  Yep!  | conv 1x1p0_1  +bnorm  leaky      | (?, 38, 38, 256)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 38, 38, 512)
 Load  |  Yep!  | maxp 2x2p0_2                     | (?, 19, 19, 512)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 19, 19, 1024)
 Load  |  Yep!  | conv 1x1p0_1  +bnorm  leaky      | (?, 19, 19, 512)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 19, 19, 1024)
 Load  |  Yep!  | conv 1x1p0_1  +bnorm  leaky      | (?, 19, 19, 512)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 19, 19, 1024)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 19, 19, 1024)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 19, 19, 1024)
 Load  |  Yep!  | concat [16]                      | (?, 38, 38, 512)
 Load  |  Yep!  | conv 1x1p0_1  +bnorm  leaky      | (?, 38, 38, 64)
 Load  |  Yep!  | local flatten 2x2                | (?, 19, 19, 256)
 Load  |  Yep!  | concat [27, 24]                  | (?, 19, 19, 1280)
 Load  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 19, 19, 1024)
 Load  |  Yep!  | conv 1x1p0_1    linear           | (?, 19, 19, 425)
-------+--------+----------------------------------+---------------
Running entirely on CPU
2019-03-10 22:43:51.794420: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2019-03-10 22:43:51.797996: I tensorflow/core/common_runtime/process_util.cc:69] Creating new thread pool with default inter op setting: 4. Tune using inter_op_parallelism_threads for best performance.
Finished in 22.694877862930298s

Rebuild a constant version ...
Done