将巨大的 Keras 模型加载到 Flask 应用程序中

Question

我正在构建一个小型 Flask 应用程序，它在幕后使用卷积神经网络对用户上传的图像进行预测。如果我像这样加载它，它就会起作用：

@app.route("/uploader", methods=["GET","POST"])
def get_image():
    if request.method == 'POST':
        f = request.files['file']
        sfname = 'static/'+str(secure_filename(f.filename))
        f.save(sfname)
        clf = catdog.classifier()
        return render_template('result.html', pred = clf.predict(sfname), imgpath = sfname)

但是，这需要在用户添加图像后加载分类器（clf）。这需要一段时间，因为它需要从 pickle 文件设置 200 层以上神经网络的所有权重。

我想要做的是在应用程序生成时加载所有权重。为此，我尝试了以下操作（删除 HTML 模板/导入/应用程序启动的不相关代码）：

# put model into memory on spawn
clf = catdog.classifier()
# Initialize the app
app = flask.Flask(__name__)

@app.route("/uploader", methods=["GET","POST"])
def get_image():
    if request.method == 'POST':
        f = request.files['file']
        sfname = 'static/'+str(secure_filename(f.filename))
        f.save(sfname)
        return render_template('result.html', pred = clf.predict(sfname), imgpath = sfname)

当我这样做时，我得到了这个回溯（跳过顶部的所有烧瓶特定跟踪）：

 File "/Users/zachariahmiller/Documents/Metis/test_area/flask_catdog/flask_backend.py", line 26, in get_image
    return render_template('result.html', pred = clf.predict(sfname), imgpath = sfname)
  File "/Users/zachariahmiller/Documents/Metis/test_area/flask_catdog/catdog.py", line 56, in predict
    prediction = self.model.predict(img_to_predict, batch_size=1, verbose=1)
  File "/Users/zachariahmiller/anaconda/lib/python2.7/site-packages/keras/engine/training.py", line 1569, in predict
    self._make_predict_function()
  File "/Users/zachariahmiller/anaconda/lib/python2.7/site-packages/keras/engine/training.py", line 1037, in _make_predict_function
    **kwargs)
  File "/Users/zachariahmiller/anaconda/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 2095, in function
    return Function(inputs, outputs, updates=updates)
  File "/Users/zachariahmiller/anaconda/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 2049, in __init__
    with tf.control_dependencies(self.outputs):
  File "/Users/zachariahmiller/anaconda/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3583, in control_dependencies
    return get_default_graph().control_dependencies(control_inputs)
  File "/Users/zachariahmiller/anaconda/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3314, in control_dependencies
    c = self.as_graph_element(c)
  File "/Users/zachariahmiller/anaconda/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2405, in as_graph_element
    return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
  File "/Users/zachariahmiller/anaconda/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2484, in _as_graph_element_locked
    raise ValueError("Tensor %s is not an element of this graph." % obj)
ValueError: Tensor Tensor("dense_2/Softmax:0", shape=(?, 2), dtype=float32) is not an element of this graph.

我不确定为什么在特定调用之外加载分类器作为应用程序的全局对象会导致失败。它应该在内存中，并且我见过人们使用 SKLearn 分类器执行此操作的其他示例。关于为什么会导致此错误的任何想法？

Answer 1

尝试放入debug=False烧瓶中。

在多次张量流保存/加载尝试失败后为我工作。

（感谢shafy @github） https://github.com/fchollet/keras/issues/2397#issuecomment-338659190

对我来说，它看起来像这样，在我的烧瓶应用程序的底部：

if __name__ == '__main__':
    app.run(debug=False)