我正在尝试使用我自己的一组图像来训练一个简单的逻辑回归模型,但是当我尝试训练模型时,我收到了这个错误:
Traceback (most recent call last):
File "main.py", line 26, in
model.entrenar_modelo(sess, training_images, training_labels)
File "/home/jr/Desktop/Dropbox/Machine_Learning/TF/Míos/Hip/model_log_reg.py", line 24, in entrenar_modelo
train_step.run({x: batch_xs, y_: batch_ys})
File "/home/jr/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1267, in run
_run_using_default_session(self, feed_dict, self.graph, session)
File "/home/jr/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2763, in _run_using_default_session
session.run(operation, feed_dict)
File "/home/jr/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 334, in run
np_val = np.array(subfeed_val, dtype=subfeed_t.dtype.as_numpy_dtype)
ValueError: setting an array element with a sequence.
我正在为train_step.run({x:batch_xs,y_:batch_ys})提供的数据是这样的:
> batch_xs:表示100×100(10,000个长张量)图像的张量对象列表
> batch_ys:标签列表为浮点数(1.0或0.0)
我究竟做错了什么?
Thx提前!
编辑1:问题是我必须在将它们传递给train_step.run(…)之前评估batch_xs中的张量.我认为run方法可以解决这个问题,但我想我错了?
无论如何,所以一旦我在调用函数之前这样做了:
for i, x in enumerate(batch_xs):
batch_xs[i] = x.eval()
#print batch_xs[i].shape
#assert all(x.shape == (100, 100, 3) for x in batch_xs)
# Now I can call the function
编辑2:即使在完成以下答案中的建议后,我也遇到了几个问题.我终于通过抛弃张量并使用numpy数组来修复所有内容.
希望这有助于其他人