Question

我正在尝试使用Darkflow设置YOLO模型训练，但是从训练开始时出现了错误。错误是KeyError：'logistic'。我不知道这个错误。我怎么解决这个问题？这是我尝试的结果。

(base) ---> python flow --model ./cfg/car-yolo.cfg --labels ./labels.txt -            
    -trainer adam --dataset ./test/training/images/ --annotation 
    ./test/training/annotations/ --train --summary ./logs --batch 5 --epoch 100 --save 50 --keep 5 --lr 1e-04 --savepb
C:\Users\jylee\Anaconda3\lib\site-packages\h5py\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters

Parsing ./cfg/car-yolo.cfg
Loading None ...
Finished in 0.0009963512420654297s

Building net ...

| Source| Train? | Layer description                | Output size      |
| ------| -------| -------------------------------- |------------------|
|       |        | input                            | (?, 608, 608, 3) |
| Init  |  Yep!  | conv 3x3p1_1  +bnorm  leaky      | (?, 608, 608, 32)|
| Load  |  Yep!  | maxp 2x2p0_2                     | (?, 304, 304, 32)|
| Init  |  Yep!  | conv 3x3p1_1  +bnorm  logistic   | (?, 304, 304, 64)|

Traceback (most recent call last):
  File "flow", line 6, in <module>
    cliHandler(sys.argv)
  File "C:\\license_plate_detection\darkflow\darkflow\cli.py", line 26, in cliHandler
    tfnet = TFNet(FLAGS)

  File "C:\\license_plate_detection\darkflow\darkflow\net\build.py", line 75, in __init__
    self.build_forward()

  File "C:\\license_plate_detection\darkflow\darkflow\net\build.py", line 115, in build_forward
    state = op_create(*args)

  File "C:\\license_plate_detection\darkflow\darkflow\net\ops\__init__.py", line 27, in op_create
    return op_types[layer_type](*args)

KeyError: 'logistic'

带darkflow的YOLO模型：keyError：“物流”？

0 个答案: