标签: darkflow

我想使用我自己的数据集训练一个新模型。我将使用 Darkflow/Tensorflow 来实现。

针对我的疑惑：

(1) 我们应该将训练图像调整为特定尺寸吗？

(2) 我认为较小的图像可能会节省时间，但是较小的图像会损害准确性吗？

（3）对于要预测的图像，我们是否也应该调整它们的大小，或者是否有必要？

我有几个文件与不同的文件:

• main.py
• watch.py
• read.py
• detect.py < - 使用darkflow依赖于图模式的基于张量流的库
• translate.py < - 使用tf eager执行

在darkflow的TFNet初始化期间,我收到此错误:

Traceback (most recent call last):
  File "/home/justin/Projects/comp3931/main.py", line 6, in <module>
    watcher = Watcher('res/vid/planet_earth_s01e01/video.mp4', 'res/vid/planet_earth_s01e01/english.srt')
  File "/home/justin/Projects/comp3931/watch.py", line 9, in __init__
    self.detector = Detector()
  File "/home/justin/Projects/comp3931/detect.py", line 6, in __init__
    self.tfnet = TFNet(self.options)
  File "/usr/local/lib64/python3.6/site-packages/darkflow/net/build.py", line 75, in __init__
    self.build_forward()
  File "/usr/local/lib64/python3.6/site-packages/darkflow/net/build.py", line 105, in build_forward
    self.inp = tf.placeholder(tf.float32, inp_size, 'input')
  File "/usr/local/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 1677, in placeholder
    raise RuntimeError("tf.placeholder() is not compatible with " …

谁能帮我区分暗网和暗流。一个比另一个的优势。我对 YOLO（你只看一次）的理解是一种用于快速物体检测的算法。

我已使用该命令在 Windows 10 上成功安装了 darkflow-1.0.0 ( https://github.com/thtrieu/darkflow ) pip install .。

Successfully built darkflow
Installing collected packages: darkflow
  Found existing installation: darkflow 1.0.0
    Uninstalling darkflow-1.0.0:
      Successfully uninstalled darkflow-1.0.0
Successfully installed darkflow-1.0.0

在此之后，我正在尝试运行python flow --h，这给了我以下错误：

Traceback (most recent call last):
  File "flow", line 4, in <module>
    from darkflow.cli import cliHandler
  File "C:\Users\filda\Desktop\FIT_VUT\BP\YOLO\YOLO_keras\darkflow\darkflow\cli.py", line 3, in <module>
    from .net.build import TFNet
  File "C:\Users\filda\Desktop\FIT_VUT\BP\YOLO\YOLO_keras\darkflow\darkflow\net\build.py", line 7, in <module>
    from .framework import create_framework
  File "C:\Users\filda\Desktop\FIT_VUT\BP\YOLO\YOLO_keras\darkflow\darkflow\net\framework.py", line 1, in <module>
    from . …

我已经在 Windows 机器上安装了 opencv，并且需要在 C 盘中单独拥有 opencv 文件夹（不在任何其他文件夹内），但找不到安装它的文件夹。请帮我。