[英]Keras Sequential Model: fit_generator with batch input
I have been trying to train a Sequential Keras model using a sparse matrix. 我一直在尝试使用稀疏矩阵训练序列Keras模型。 Although I have specified the batch size in the code, it is being trained at batch_size = 1 (ie one row at a time).
尽管我已在代码中指定了批处理大小,但正在使用batch_size = 1(即一次一行)进行训练。
Here's the code: 这是代码:
def batch_generator(X_toGen, y_toGen = None, batch_size = 32):
counter = 0
sample_index = np.arange(X_toGen.shape[0])
np.random.shuffle(sample_index)
while True:
batch_index = sample_index[batch_size*counter:min(batch_size*(counter+1), X_toGen.shape[0])]
counter += 1
X_batch = X_toGen[batch_index,:]
if y_toGen is not None:
y_batch = y_toGen[batch_index]
yield X_batch.toarray(), y_batch
else:
yield X_batch.toarray()
Can anyone please help me in generating a batch input for the Sequential model? 谁能帮助我为顺序模型生成批输入? Also, how different would the accuracy be when the model is being trained at batch_size = 32, rather than batch_size = 1?
另外,当模型以batch_size = 32而不是batch_size = 1进行训练时,精度有多大?
Thanks 谢谢
What you are getting is not 1 batch size output from this generator. 您得到的不是此生成器输出的1批大小。 Let me give you an example here:
让我在这里给你一个例子:
If you have total 1000 samples and you are dividing this in batches 10. Then using fit_generator you will get only 10 batches which means you have 10 batches each of 10 samples. 如果总共有1000个样本,并且将其分成10个批次,则使用fit_generator只能得到10个批次,这意味着10个样本中的每个都有10个批次。
So, the crux is fit_generator shows number of batches instead of total number of samples. 因此,关键是fit_generator显示的是批次数量而不是样本总数。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.