我創(chuàng)建了一個(gè)字符串的 Tensorflow 數(shù)據(jù)集（其中每個(gè)字符串都是 dicom 圖像的路徑），我想將預(yù)處理函數(shù)映射到數(shù)據(jù)集。預(yù)處理函數(shù)應(yīng)該使用pydicom包從 dicom 文件加載像素?cái)?shù)組。但是當(dāng)我嘗試映射一個(gè)函數(shù)時(shí)，雖然我得到一個(gè)屬性錯(cuò)誤。如何使用如下函數(shù)從張量中讀取字符串值？我正在使用 Tensorflow 2.0.0 和 pydicom 1.3.0。AttributeError: in converted code: <ipython-input-12-eff65198c202>:12 load_and_preprocess_image * dicom_data = pydicom.dcmread(img_path) /opt/conda/lib/python3.6/site-packages/pydicom/filereader.py:849 dcmread * dataset = read_partial(fp, stop_when, defer_size=defer_size, /opt/conda/lib/python3.6/site-packages/pydicom/filereader.py:651 read_partial * preamble = read_preamble(fileobj, force) /opt/conda/lib/python3.6/site-packages/pydicom/filereader.py:589 read_preamble * preamble = fp.read(128) AttributeError: 'Tensor' object has no attribute 'read'這是我創(chuàng)建數(shù)據(jù)集并將預(yù)處理函數(shù)映射到它的代碼。def load_and_preprocess_image(img_path): """ Load image, resize, and normalize the image""" dicom_data = pydicom.dcmread(img_path)) image = tf.convert_to_tensor(dicom_data.pixel_array, dtype=tf.float32) return image# Create dataset (list of strings that lead to dicom paths)image_train_ds = tf.data.Dataset.from_tensor_slices(dicom_files_list)# Map a preprocessing function to list of dicom pathsimage_train_ds = image_train_ds.map(load_and_preprocess_image)
2 回答
慕尼黑8549860
TA貢獻(xiàn)1818條經(jīng)驗(yàn) 獲得超11個(gè)贊
有一個(gè) Tensorflow-io 包現(xiàn)在允許這樣做。它相當(dāng)簡(jiǎn)單。
安裝包：
pip install -q tensorflow-io
import tensorflow_io as tfio
def load_and_preprocess_image(img_path):
_bytes = tf.io.read_file(img_path)
dicom_data = tfio.image.decode_dicom_image(_bytes, dtype=tf.float32)
return dicom_data
dicom_files_list = ['path/to/dicom']
# Create dataset (list of strings that lead to dicom paths)
image_train_ds = tf.data.Dataset.from_tensor_slices(dicom_files_list)
image_train_ds = image_train_ds.map(load_and_preprocess_image)
弒天下
TA貢獻(xiàn)1818條經(jīng)驗(yàn) 獲得超8個(gè)贊
在 中pydicom.dcmread(img_path)，img_path是 tf.string 張量。我不認(rèn)為pydicom支持讀取張量對(duì)象。
我找到了一種解決方法，它是在 tensorflow 中提供 DICOM 操作的 gradient_decode_dicom 。以下代碼改編自此 colab，并在 tf2.0 上進(jìn)行了測(cè)試。
def load_and_preprocess_image(img_path):
_bytes = tf.io.read_file(img_path)
dicom_data = decode_dicom_image(_bytes, dtype=tf.float32)
return dicom_data
dicom_files_list = ['path/to/dicom']
# Create dataset (list of strings that lead to dicom paths)
image_train_ds = tf.data.Dataset.from_tensor_slices(dicom_files_list)
image_train_ds = image_train_ds.map(load_and_preprocess_image)
添加回答
舉報(bào)
0/150
提交
取消