在 Keras 中训练对象检测模型时出现不兼容张量形状的问题
Posted
技术标签:
【中文标题】在 Keras 中训练对象检测模型时出现不兼容张量形状的问题【英文标题】:Problem with incompatible tensor shapes when training object detection model in Keras 【发布时间】:2019-05-02 16:05:20 【问题描述】:我正在尝试将基本分类模型 (https://machinelearningmastery.com/handwritten-digit-recognition-using-convolutional-neural-networks-python-keras/) 扩展到单个对象的简单对象检测模型。
分类模型只是对图像中的手写数字进行分类,其中数字填充了图像的大部分。为了为目标检测制作有意义的数据集,我使用 MNIST 数据集作为基础,并通过以下步骤将其转换为新数据集
-
将图像画布尺寸从 28x28 增加到 100x100
将手写数字移动到 100x100 图像内的随机位置
创建地面实况边界框
图 1:步骤 1 和 2 的图示。
图 2:一些生成的真实边界框。
模型的输出向量受 YOLO 定义的启发,但针对单个对象:
y = [p, x, y, w, h, c0, ..., c9]
其中 p = 对象的概率,(x, y, w, h) = 作为图像大小分数的边界框中心、宽度和高度,c0-c9 = 类别概率(每个数字一个)。
因此,为了将分类模型更改为对象检测模型,我只是将最后一个 softmax 层替换为具有 15 个节点的全连接层(y
中的每个值一个),并编写了一个自定义损失函数,可以比较对基本事实的预测。
但是,当我尝试训练模型时,我得到了一个神秘的错误tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [15] vs. [200]
,其中[15]
是我最后一层中的节点数,[200]
是我为训练指定的批量大小(我通过以下方式验证了这一点更改值并再次运行)。它们不能合理地必须相同,所以我想我在模型中的张量维度上遗漏了一些重要的东西,但我不知道是什么。
注意:我对批次的理解是模型在训练期间一次处理多少个样本(图像)。因此,批量大小应该是训练数据大小的偶数部分是合理的。但是没有什么可以将它与模型中的输出节点数联系起来。
感谢任何帮助。
这里是完整的代码:
import numpy as np
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import Flatten
from keras.layers.convolutional import Conv2D
from keras.layers.convolutional import MaxPooling2D
from keras import backend as K
def increase_image_size(im_set, new_size):
num_images = im_set.shape[0]
orig_size = im_set[0].shape[0]
im_stack = np.zeros((num_images, new_size, new_size), dtype='uint8')
# Put MNIST digits at random positions in new images
for i in range(num_images):
x0 = int(np.random.random() * (new_size - orig_size - 1))
y0 = int(np.random.random() * (new_size - orig_size - 1))
x1 = x0 + orig_size
y1 = y0 + orig_size
im_stack[i, y0:y1, x0:x1] = im_set[i]
return im_stack
# Get bounding box annotations from images and object labels
def get_image_annotations(X_train, y_train):
num_images = len(X_train)
annotations = np.zeros((num_images, 15), dtype='float')
for i in range(num_images):
annotations[i] = get_image_annotation(X_train[i], y_train[i])
return annotations
def get_image_annotation(X, y):
sz_y, sz_x = X.shape
y_indices, x_indices = np.where(X > 0)
y_min = max(np.min(y_indices) - 1, 0)
y_max = min(np.max(y_indices) + 1, sz_y)
x_min = max(np.min(x_indices) - 1, 0)
x_max = min(np.max(x_indices) + 1, sz_x)
bb_x = (x_min + x_max) / 2.0 / sz_x
bb_y = (y_min + y_max) / 2.0 / sz_y
bb_w = (x_max - x_min) / sz_x
bb_h = (y_max - y_min) / sz_y
classes = np.zeros(10, dtype='float')
classes[y] = 1
output = np.concatenate(([1, bb_x, bb_y, bb_w, bb_h], classes))
return output
def custom_cost_function(y_true, y_pred):
p_p = y_pred[0]
x_p = y_pred[1]
y_p = y_pred[2]
w_p = y_pred[3]
h_p = y_pred[4]
p_t = y_true[0]
x_t = y_true[1]
y_t = y_true[2]
w_t = y_true[3]
h_t = y_true[4]
c_pred = y_pred[5:]
c_true = y_true[5:]
c1 = K.sum((c_pred - c_true) * (c_pred - c_true))
c2 = (x_p - x_t) * (x_p - x_t) + (y_p - y_t) * (y_p - y_t) \
+ (K.sqrt(w_p) - K.sqrt(w_t)) * (K.sqrt(w_p) - K.sqrt(w_t)) \
+ (K.sqrt(h_p) - K.sqrt(h_t)) * (K.sqrt(h_p) - K.sqrt(h_t))
lambda_class = 1.0
lambda_coord = 1.0
return lambda_class * c1 + lambda_coord * c2
def baseline_model():
# create model
model = Sequential()
model.add(Conv2D(32, (5, 5), input_shape=(1, 100, 100), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(15, activation='linear'))
# Compile model
model.compile(loss=custom_cost_function, optimizer='adam', metrics=['accuracy'])
return model
def mnist_object_detection():
K.set_image_dim_ordering('th')
# fix random seed for reproducibility
np.random.seed(7)
# Load data
print("Loading data")
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# Adjust input images
print("Adjust input images (increasing image sizes and moving digits)")
X_train = increase_image_size(X_train, 100)
X_test = increase_image_size(X_test, 100)
print("Creating annotations")
y_train_prim = get_image_annotations(X_train, y_train)
y_test_prim = get_image_annotations(X_test, y_test)
print("...done")
# reshape to be [samples][pixels][width][height]
X_train = X_train.reshape(X_train.shape[0], 1, 100, 100).astype('float32')
X_test = X_test.reshape(X_test.shape[0], 1, 100, 100).astype('float32')
# normalize inputs from 0-255 to 0-1
X_train = X_train / 255
X_test = X_test / 255
# build the model
print("Building model")
model = baseline_model()
# Fit the model
print("Training model")
model.fit(X_train, y_train_prim, validation_data=(X_test, y_test_prim), epochs=10, batch_size=200, verbose=1)
if __name__ == '__main__':
mnist_object_detection()
当我运行它时,我得到了错误:
/Users/gedda/anaconda3/envs/keras-obj-det/bin/pythonn /Users/gedda/devel/tensorflow/digit-recognition/object_detection_reduced.py
Using TensorFlow backend.
Loading data
Adjust input images (increasing image sizes and moving digits)
Creating annotations
...done
Building model
2018-11-30 13:26:34.030159: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX
2018-11-30 13:26:34.030463: I tensorflow/core/common_runtime/process_util.cc:69] Creating new thread pool with default inter op setting: 8. Tune using inter_op_parallelism_threads for best performance.
Training model
Train on 60000 samples, validate on 10000 samples
Epoch 1/3
Traceback (most recent call last):
File "/Users/gedda/devel/tensorflow/digit-recognition/object_detection_reduced.py", line 140, in <module>
mnist_object_detection()
File "/Users/gedda/devel/tensorflow/digit-recognition/object_detection_reduced.py", line 136, in mnist_object_detection
model.fit(X_train, y_train_prim, validation_data=(X_test, y_test_prim), epochs=3, batch_size=200, verbose=1)
File "/Users/gedda/anaconda3/envs/keras-obj-det/lib/python3.6/site-packages/keras/engine/training.py", line 1039, in fit
validation_steps=validation_steps)
File "/Users/gedda/anaconda3/envs/keras-obj-det/lib/python3.6/site-packages/keras/engine/training_arrays.py", line 199, in fit_loop
outs = f(ins_batch)
File "/Users/gedda/anaconda3/envs/keras-obj-det/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2715, in __call__
return self._call(inputs)
File "/Users/gedda/anaconda3/envs/keras-obj-det/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2675, in _call
fetched = self._callable_fn(*array_vals)
File "/Users/gedda/anaconda3/envs/keras-obj-det/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1439, in __call__
run_metadata_ptr)
File "/Users/gedda/anaconda3/envs/keras-obj-det/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 528, in __exit__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [15] vs. [200]
[[node training/Adam/gradients/loss/dense_2_loss/mul_7_grad/BroadcastGradientArgs = BroadcastGradientArgs[T=DT_INT32, _class=["loc:@training/Adam/gradients/loss/dense_2_loss/mul_7_grad/Reshape"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](training/Adam/gradients/loss/dense_2_loss/mul_7_grad/Shape, training/Adam/gradients/loss/dense_2_loss/mul_7_grad/Shape_1)]]
Process finished with exit code 1
【问题讨论】:
【参考方案1】:所有张量的第一个维度是批量大小。
您的损失可能应该在第二个维度上起作用:
def custom_cost_function(y_true, y_pred):
p_p = y_pred[:,0]
x_p = y_pred[:,1]
y_p = y_pred[:,2]
w_p = y_pred[:,3]
h_p = y_pred[:,4]
p_t = y_true[:,0]
x_t = y_true[:,1]
y_t = y_true[:,2]
w_t = y_true[:,3]
h_t = y_true[:,4]
c_pred = y_pred[:,5:]
c_true = y_true[:,5:]
........
【讨论】:
谢谢!现在它起作用了。我永远不会猜到这是问题所在。以上是关于在 Keras 中训练对象检测模型时出现不兼容张量形状的问题的主要内容,如果未能解决你的问题,请参考以下文章
如何在 Keras / Tensorflow 中将(无,)批量维度重新引入张量?
当在 tensorflow 1.14 中使用混合精度训练时,张量对象在 keras vgg16 中没有属性“is_initialized”