Ошибка типа: Невозможно передать (1024, 6272) -> (1024, 25088) - PullRequest
Новая
       5

Ошибка типа: Невозможно передать (1024, 6272) -> (1024, 25088)

0 голосов
/ 20 января 2020

Я пытаюсь извлечь объекты из набора данных с использованием и кодировщика, но я получаю следующую ошибку: 

Traceback (most recent call last):
  File "extract_features.py", line 104, in <module>
    features = features.reshape((features.shape[0], 512 * 7 * 7))
ValueError: cannot reshape array of size 200704 into shape (32,25088)

кодировщик выглядит следующим образом: 

class ConvNetEncoder(tf.keras.Model):
    def __init__(self):
        super(ConvNetEncoder, self).__init__()

        self.conv1 = tf.keras.layers.Conv2D(16, (3, 3), activation='relu', padding='same')
        self.maxp1 = tf.keras.layers.MaxPooling2D((2, 2), padding='same')
        self.conv2 = tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same')
        self.maxp2 = tf.keras.layers.MaxPooling2D((2, 2), padding='same')
        self.conv3 = tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same')

        self.encoded = tf.keras.layers.MaxPooling2D((2, 2), padding='same')

    def call(self, x):
        x = self.conv1(x)
        x = self.maxp1(x)
        x = self.conv2(x)
        x = self.maxp2(x)
        x = self.conv3(x)
        x = self.encoded(x)
        return x

Следующее является частью кода функции извлечения 

# loop over the images in batches
for i in np.arange(0, len(imagePaths), bs):
    # extract the batch of images and labels, then initialize the
    # list of actual images that will be passed through the network
    # for feature extraction
    batchPaths = imagePaths[i:i + bs]
    batchLabels = labels[i:i + bs]
    batchImages = []

    # loop over the images and labels in the current batch
    for (j, imagePath) in enumerate(batchPaths):
        # load the input image using the Keras helper utility
        # while ensuring the image is resized to 224x224 pixels
        image = load_img(imagePath, target_size=(224, 224))
        image = img_to_array(image)

        # preprocess the image by (1) expanding the dimensions and
        # (2) subtracting the mean RGB pixel intensity from the
        # ImageNet dataset
        image = np.expand_dims(image, axis=0)
        image = imagenet_utils.preprocess_input(image)

        # add the image to the batch
        batchImages.append(image)

    # pass the images through the network and use the outputs as
    # our actual features
    batchImages = np.vstack(batchImages)
    features = model.predict(batchImages, batch_size=bs)

    # reshape the features so that each image is represented by
    # a flattened feature vector of the `MaxPooling2D` outputs
    features = features.reshape((features.shape[0], 512 * 7 * 7))

    # add the features and labels to our HDF5 dataset
    dataset.add(features, batchLabels)
    pbar.update(i)

Я использую tenorflow 2.0, python 3.7.6 на windows.

После изменения размеров на features = features.reshape((features.shape[0], 128 * 7 * 7)), я получил следующее ошибка 

Traceback (most recent call last):####                          | ETA:  0:00:24
  File "extract_features.py", line 108, in <module>
    dataset.add(features, batchLabels)
  File "D:\Clones\feature_extraction_try\pyimagesearch\io\hdf5datasetwriter.py", line 37, in add
    self.flush()
  File "D:\Clones\feature_extraction_try\pyimagesearch\io\hdf5datasetwriter.py", line 42, in flush
    self.data[self.idx:i] = self.buffer["data"]
  File "h5py\_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
  File "h5py\_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
  File "C:\Users\sancy\Anaconda3\envs\tensorflow2\lib\site-packages\h5py\_hl\dataset.py", line 707, in __setitem__
    for fspace in selection.broadcast(mshape):
  File "C:\Users\sancy\Anaconda3\envs\tensorflow2\lib\site-packages\h5py\_hl\selections.py", line 299, in broadcast
    raise TypeError("Can't broadcast %s -> %s" % (target_shape, self.mshape))
TypeError: Can't broadcast (1024, 6272) -> (1024, 25088)

В трассировке упоминается следующее в моем hdf5datasetWriter.py 

def add(self, rows, labels):
        # add the rows and labels to the buffer
        self.buffer["data"].extend(rows)
        self.buffer["labels"].extend(labels)

        # check to see if the buffer needs to be flushed to disk
        if len(self.buffer["data"]) >= self.bufSize:
            self.flush()

def flush(self):
        # write the buffers to disk then reset the buffer
        i = self.idx + len(self.buffer["data"])
        self.data[self.idx:i] = self.buffer["data"]
        self.labels[self.idx:i] = self.buffer["labels"]
        self.idx = i
        self.buffer = {"data": [], "labels": []}

Ждем вашей помощи.

1 Ответ

2 голосов
/ 20 января 2020

Похоже, ваш размер не соответствует 32 * 25088 = 802816, что в 4 раза больше, чем в 200704 году.

Так что сработало бы, если бы вы сделали: features = features.reshape((features.shape[0], 128 * 7 * 7))

...