0

我创建了一个数据集，每个字母有 1 个生成的训练图像，每个字母大约有 10 个真实的测试图像。

它们都是 10x14px，黑白（在预处理阶段很好地二值化）。

生成的模型将所有符号识别为“1”（甚至是测试集中的实际图像），所以基本上它根本不起作用。

谁能指出我正确的方向？

这是 CreateML 输出 -

Extracting image features from full data set.
Analyzing and extracting image features.
+------------------+--------------+------------------+
| Images Processed | Elapsed Time | Percent Complete |
+------------------+--------------+------------------+
| 1                | 1.74s        | 2.5%             |
| 2                | 1.96s        | 5.25%            |
| 3                | 2.17s        | 8%               |
| 4                | 2.39s        | 10.75%           |
| 5                | 2.60s        | 13.5%            |
| 10               | 3.68s        | 27%              |
| 25               | 6.90s        | 67.5%            |
| 37               | 9.48s        | 100%             |
| 36               | 9.26s        | 97.25%           |
+------------------+--------------+------------------+
Skipping automatic creation of validation set; training set has fewer than 50 points.
Beginning model training on processed features. 
Calibrating solver; this may take some time.
+-----------+--------------+-------------------+
| Iteration | Elapsed Time | Training Accuracy |
+-----------+--------------+-------------------+
| 0         | 0.038845     | 0.027027          |
| 1         | 0.139269     | 0.837838          |
| 2         | 0.268821     | 0.945946          |
| 3         | 0.317312     | 0.945946          |
| 4         | 0.367944     | 0.972973          |
| 5         | 0.422657     | 0.972973          |
| 10        | 0.713325     | 1.000000          |
| 24        | 1.495230     | 1.000000          |
+-----------+--------------+-------------------+
SUCCESS: Optimal solution found.
Extracting image features from evaluation data.
Analyzing and extracting image features.
+------------------+--------------+------------------+
| Images Processed | Elapsed Time | Percent Complete |
+------------------+--------------+------------------+
| 1                | 211.661ms    | 0.25%            |
| 2                | 425.538ms    | 0.75%            |
| 3                | 641.33ms     | 1.25%            |
| 4                | 861.215ms    | 1.75%            |
| 5                | 1.07s        | 2.25%            |
| 10               | 2.16s        | 4.75%            |
| 25               | 5.39s        | 12%              |
| 50               | 10.75s       | 24%              |
| 75               | 16.12s       | 36%              |
| 100              | 21.51s       | 48%              |
| 125              | 26.88s       | 60%              |
| 150              | 32.24s       | 72%              |
| 175              | 37.61s       | 84%              |
| 200              | 42.97s       | 96%              |
| 208              | 44.69s       | 100%             |
| 207              | 44.47s       | 99.5%            |
+------------------+--------------+------------------+
Trained model successfully saved at /mypath/ocr.mlmodel.

4

1 回答 1

1

  1. OCR 很难。

  2. 您没有足够的训练示例。

  3. Create ML 使用非常强大的“特征提取器”。这也意味着模型很容易记住所有的训练数据，因为图像非常小，而且你只有几个。对于 Create ML，您无能为力来防止这种情况发生。

  4. 尝试使用 scikit-learn 等软件包对数据进行简单的逻辑回归训练。它将比深度神经网络工作得更好。

于 2018-10-13T10:48:08.703 回答