Value error: input samples have different number of arrays with target samples. about keras-transfer-learning-for-oxford102

[Arsey]

ValueError: Input arrays should have the same number of samples as target arrays. Found 6149 input samples and 8660 target samples. - It's possible that your data structure has changed since save_bottleneck_features() was completed

[TriLoo]

Maybe I know the reason causing this error.
In bottlenecks.py, the way to get training labels is :
train_labels += [k] * len(os.listdir('{}/{}'.format(config.train_dir, i)))
So, if there are other not image files in train dir, this sentense would treat them as images leading to wrong target samples...
In fact, I just used these dataset in SIFT + SVM frame, so there are some .sift files in train data dir. Now, I have deleted them and try again...

[Arsey]

@TriLoo I've just fixed the issue

[vasudhabansal1994]

@Arsey Can you please tell me how did you fix the issue.

[stobasa]

this is unfair, tell us how you fixed it so we could lesrn

[Arsey]

@stobasa basically the bottlenecks extraction step is not necessary and do not exist in the code anymore. Please read the code to get the idea. But simply the steps are:

1. get pretrained model without the last fully-connected layer + its weights
2. add a fully-connected layer for classification with a number of neurons that is equal to the number of classes you have
3. freeze N layers of the original pretrained model
4. start training with small learning rate

all these steps are already implemented

[stobasa]

@Arsey can you please post the code here..i have been stucked on this for a whole day..this would help me greatly

[Arsey]

@stobasa code for what?