sklearn pipeline中用于分类的图像数组-值错误:使用序列设置数组元素

from pandas import DataFrame
from scipy.misc import imread, imresize
rows = []
for product in products:
    try:
        relevant = product.categoryrelevant.all()[0].relevant
    except IndexError:
        relevant = False
    if relevant:
        relevant = "A"
    else:
        relevant = "B"
    # this exists for all pictures
    image_array = imread("{}/{}".format(MEDIA_ROOT, product.picture_file.url))
    image_array = imresize(image_array, (160, 160))
    image_array = image_array.reshape(-1)
    print(image_array)
    # [254 254 252 ..., 255 255 253]
    print(image_array.shape)
    # (76800,)
    rows.append({"id": product.pk, "image": image_array, "class": relevant})
    index.append(product)
df = DataFrame(rows, index=index)

http://scikit-learn.org/stable/auto_examples/hetero_feature_union.html

它接受“图像”列中的值。或者,也可以这样做 train_X = df.iloc[train_indices]["image"].values ,但我想稍后添加其他列。

def randomforest_image_pipeline():
    """Returns a RandomForest pipeline."""
    return Pipeline([
        ("union", FeatureUnion(
            transformer_list=[
                ("image", Pipeline([
                    ("selector", ItemSelector(key="image")),
                ]))
            ],
            transformer_weights={
                "image": 1.0
            },
        )),
        ("classifier", RandomForestClassifier()),
    ])

from sklearn.model_selection import KFold
kfold(tested_pipeline=randomforest_image_pipeline(), df=df)
def kfold(tested_pipeline=None, df=None, splits=6):
    k_fold = KFold(n_splits=splits)
    for train_indices, test_indices in k_fold.split(df):
        # training set
        train_X = df.iloc[train_indices]
        train_y = df.iloc[train_indices]['class'].values
        # test set
        test_X = df.iloc[test_indices]
        test_y = df.iloc[test_indices]['class'].values
        for val in train_X["image"]:
            print(len(val), val.dtype, val.shape)
            # 76800 uint8 (76800,) for all
        tested_pipeline.fit(train_X, train_y) # crashes in this call
        pipeline_predictions = tested_pipeline.predict(test_X)
        ...

.fit 我得到以下错误:

Traceback (most recent call last):
  File "<path>/project/classifier/classify.py", line 362, in <module>
    best = best_pipeline(dataframe=data, f1_scores=f1_dict, get_fp=True)
  File "<path>/project/classifier/classify.py", line 351, in best_pipeline
    confusion_list=confusion_list, get_fp=get_fp)
  File "<path>/project/classifier/classify.py", line 65, in kfold
    tested_pipeline.fit(train_X, train_y)
  File "/usr/local/lib/python3.5/dist-packages/sklearn/pipeline.py", line 270, in fit
    self._final_estimator.fit(Xt, y, **fit_params)
  File "/usr/local/lib/python3.5/dist-packages/sklearn/ensemble/forest.py", line 247, in fit
    X = check_array(X, accept_sparse="csc", dtype=DTYPE)
  File "/usr/local/lib/python3.5/dist-packages/sklearn/utils/validation.py", line 382, in check_array
    array = np.array(array, dtype=dtype, order=order, copy=copy)
ValueError: setting an array element with a sequence.

我发现其他人也有同样的问题,对他们来说,问题是他们的行长度不同。我的情况似乎不是这样,因为所有行都是一维的,长度为76800:

    for val in train_X["image"]:
        print(len(val), val.dtype, val.shape)
        # 76800 uint8 (76800,) for all

array

[array([ 255.,  255.,  255., ...,  255.,  255.,  255.])
 array([ 255.,  255.,  255., ...,  255.,  255.,  255.])
 array([ 255.,  255.,  255., ...,  255.,  255.,  255.]) ...,
 array([ 255.,  255.,  255., ...,  255.,  255.,  255.])
 array([ 255.,  255.,  255.

我能做些什么来解决这个问题?