我在 Tensorflow 中有以下預處理管道：
data_transformation = tf.keras.Sequential([layers.experimental.preprocessing.RandomContrast(factor=(0.7,0.9)),layers.GaussianNoise(stddev=tf.random.uniform(shape=(),minval=0, maxval=1)), layers.experimental.preprocessing.RandomRotation(factor=0.1, fill_mode='reflect', interpolation='bilinear', seed=None, name=None, fill_value=0.0), layers.experimental.preprocessing.RandomZoom(height_factor=(0.1,0.2), width_factor=(0.1,0.2), fill_mode='reflect', interpolation='bilinear', seed=None, name=None, fill_value=0.0),])
我想更改 layers.experimental.preprocessing.RandomContrast.py 檔案以更改其作業方式。但是，我在我的系統中找不到這樣的檔案。每當我找到一個檔案時，它都是一個鏈接到不同目錄的init .py 檔案。我知道，如果我在 python 終端中宣告以下內容，它會回傳正常：
import tensorflow as tf
tf.image.random_contrast
但是如果我在我的 tensorflow 目錄中查找影像，以下內容會回傳給我
/usr/local/lib/python3.8/dist-packages/tensorflow/_api/v2/image
/usr/local/lib/python3.8/dist-packages/tensorflow/_api/v2/compat/v1/image
/usr/local/lib/python3.8/dist-packages/tensorflow/_api/v2/compat/v2/image
/usr/local/lib/python3.8/dist-packages/tensorflow/include/tensorflow/core/kernels/image
/usr/local/lib/python3.8/dist-packages/tensorflow/keras/preprocessing/image
/usr/local/lib/python3.8/dist-packages/tensorflow/python/keras/api/_v1/keras/preprocessing/image
/usr/local/lib/python3.8/dist-packages/tensorflow/python/keras/api/keras/preprocessing/image
/usr/local/lib/python3.8/dist-packages/tensorflow/python/keras/api/_v2/keras/preprocessing/image
所有這些目錄都再次指向init .py 檔案。它似乎在無限回圈中尋找由init .py 檔案重定向的目錄。我應該如何在 python 中找到特定匯入的特定 .py 檔案？
uj5u.com熱心網友回復：
您可以在網上搜索：
tf layers.experimental.preprocessing.RandomContrast
然后點擊第一個鏈接：RandomContrast，最后點擊github 上的查看源代碼：image_preprocessing.py
轉載請註明出處，本文鏈接：https://www.uj5u.com/gongcheng/466784.html