我试图将运行resnet50获得的瓶颈特性加载到顶层模型中。我在resnet上运行predict_generator,并将产生的瓶颈特性保存到npy文件中。由于以下错误,我无法适应我创建的模型:
Traceback (most recent call last):
File "Labeled_Image_Recognition.py", line 119, in <module>
callbacks=[checkpointer])
File "/home/dillon/anaconda3/envs/tensorflow/lib/python3.6/site-packages/keras/models.py", line 963, in fit
validation_steps=validation_steps)
File "/home/dillon/anaconda3/envs/tensorflow/lib/python3.6/site-packages/keras/engine/training.py", line 1630, in fit
batch_size=batch_size)
File "/home/dillon/anaconda3/envs/tensorflow/lib/python3.6/site-packages/keras/engine/training.py", line 1490, in _standardize_user_data
_check_array_lengths(x, y, sample_weights)
File "/home/dillon/anaconda3/envs/tensorflow/lib/python3.6/site-packages/keras/engine/training.py", line 220, in _check_array_lengths
'and ' + str(list(set_y)[0]) + ' target samples.')
ValueError: Input arrays should have the same number of samples as target arrays. Found 940286 input samples and 14951 target samples.
我不太清楚这是什么意思。我有940286总图像在我的列车目录,有14951个总的子目录,这些图像是分开的。我的两个假设是:
任何引导到正确的方向将不胜感激!在
代码如下:
^{pr2}$
在有监督学习的情况下,输入样本数(
X
)必须与输出(标签)样本数(Y
)相匹配。在例如:如果我们想让(学习)一个NN来识别手写数字,并向模型提供10000个图像(
X
),那么我们还应该传递10000个标签(Y
)。在在你的情况下,这些数字不匹配。在
相关问题 更多 >
编程相关推荐