在研究了这篇研究论文后，我正试图从头开始实现一个全卷积神经网络。由于FCN可以处理任何大小的输入，我很难实现它的DataLoader。我试图使用batch((函数对输入进行批处理，但由于可变长度张量，它给出了一个错误。有没有可行的方法来批量处理任意形状的张量？
我的代码：
import tensorflow as tf
import matplotlib.pyplot as plt
from PIL import Image
import numpy as np
import os
from albumentations import ElasticTransform,VerticalFlip,RandomSizedCrop,Compose,RandomRotate90
# Train and Val contains the respective paths for [TrainImage,Labels] and [ValImage,Labels] respectively.
num_classes = 21
Train = tf.data.Dataset.from_tensor_slices(Train)
Val = tf.data.Dataset.from_tensor_slices(Val)
def Create_Mask(Img):
Seg_Labels = np.zeros((Img.shape[0],Img.shape[1],num_classes),dtype=np.float32)
for class_ in range(num_classes):
Seg_Labels[:,:,class_] = (Img == class_)
return tf.cast(Seg_Labels,dtype=tf.float32)
def Create_PreProcess_Mask_Img(Instance):
Img = np.asarray(Image.open(Instance[0].numpy()))
Mask = np.asarray(Image.open(Instance[1].numpy()))
# Since Mask is in 'P' mode it will automatically convert to labels using Color Palette
Normalization = tf.keras.layers.experimental.preprocessing.Rescaling(1./255)
if tf.random.uniform(()) > 0.5: # Applying data Augmentation
Num = tf.random.uniform((),minval=0,maxval=3,dtype=tf.int32)
if Num == 0:
aug = ElasticTransform(p=1)
Augmented = aug(image = Img,mask = Mask)
elif Num == 1:
Height,Width = Img.shape[0],Img.shape[1]
aug = RandomSizedCrop(min_max_height=(50,101),height=Height,width=Width,p = 1)
Augmented = aug(image = Img,mask = Mask)
elif Num == 2:
aug = Compose([VerticalFlip(p=0.5),RandomRotate90(p=0.5)])
Augmented = aug(image = Img,mask = Mask)
Img = Augmented["image"]
Mask = Augmented["mask"]
return Normalization(Img),Create_Mask(Mask)
def Preprocess(Instance):
Img,Mask = tf.py_function(Create_PreProcess_Mask_Img,[Instance],[tf.float32,tf.float32])
return tf.ensure_shape(Img,[None,None,3]),tf.ensure_shape(Mask,[None,None,num_classes])
#tf.ensure_shape returns the matrix if shape matches else error
def DataLoader(dataset,BATCH_SIZE = 32,BUFFER_SIZE = 256):
data = dataset.map(Preprocess,num_parallel_calls = tf.data.AUTOTUNE)
data = data.cache().shuffle(BUFFER_SIZE).batch(BATCH_SIZE).repeat(1)
data = data.prefetch(buffer_size = tf.data.AUTOTUNE)
return data
Train = DataLoader(Train)
Val = DataLoader(Val)
for X,Y in Train.take(1):
print(X.shape)
print(Y.shape)
堆栈跟踪：
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/context.py in execution_mode(mode)
2112 ctx.executor = executor_new
-> 2113 yield
2114 finally:
9 frames
InvalidArgumentError: Cannot batch tensors with different shapes in component 0. First element had shape [500,375,3] and element 1 had shape [500,383,3]. [Op:IteratorGetNext]
During handling of the above exception, another exception occurred:
InvalidArgumentError Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/eager/executor.py in wait(self)
67 def wait(self):
68 """Waits for ops dispatched in this executor to finish."""
---> 69 pywrap_tfe.TFE_ExecutorWaitForAllPendingNodes(self._handle)
70
71 def clear_error(self):
InvalidArgumentError: Cannot batch tensors with different shapes in component 0. First element had shape [500,375,3] and element 1 had shape [500,383,3].
你不能有一个不同图像大小的批次，但如果你想解决这个问题，你可以：
- 调整所有图像的大小以获得一个通用形状(如果图像的比例接近，则影响最小(查看此链接
- 将批次的大小减小到一个图像(这种方法会使训练非常不稳定(
你可以看看这篇文章