neural_image_captioning

neural_image_captioning copied to clipboard

Dear Professor, thank you for your great work. I've read one of your paper: image captiong and classification for damgerous detection, in which there is a special dataset for anomaly...

wangran1999

@oarriaga Hello there! I run train.py, the result is reported as follows, how can I solve it? thank you very much! 

Blue-Eagle-10

no such layer flatten

6

File "", line 1, in data_manager.preprocess() File "C:/Users/chaturbhuj/Downloads/Compressed/neural_image_captioning-master/src/data_manager.py", line 75, in preprocess self.get_image_features(self.image_directory) File "C:/Users/chaturbhuj/Downloads/Compressed/neural_image_captioning-master/src/data_manager.py", line 232, in get_image_features output=base_model.get_layer('flatten').output) File "C:\Users\chaturbhuj\Anaconda3\lib\site-packages\keras\engine\topology.py", line 1868, in get_layer raise ValueError('No such layer:...

chaturbhuj02

Load Model

3

Hi, I have problem for loading the pre-trained model : TypeError: ('Keyword argument not understood:', 'return_state') Do you know how to fix this?

iland5

To extract top level features from InceptionV3; set include_top=False

NamanJain8

Hi, it seems that your models have 2 input branches, one for the words and one for the image descriptor. Instead, in the paper the input is the same. That...

alex88o

[Contribution] Convert cnn output from 'flatten' to 'avg_pool'

4

[Current version of Inception_v3](https://github.com/fchollet/keras/blob/master/keras/applications/inception_v3.py#L344-L347) doesn't have [a layer named 'flatten'](https://github.com/oarriaga/neural_image_captioning/blob/master/src/data_manager.py#L230-L232) so the code crashes when `extract_image_features` is set to `True`. [In this older version](https://github.com/fchollet/keras/blob/f23f2ff2c96537274beb99aca8417f054f817501/keras/applications/inception_v3.py#L258-L262), it's clear that the 'flatten' layer...

PavlosMelissinos

I've been trying to train the network but I've been getting captions that repeat the same word again and again, like so: ``` Predicted: a a a a a a...

PavlosMelissinos

Hey there, could you post the pre-trained model on mscoco?

PavlosMelissinos

Evaluate unlearned images.

1

Hello. I want to Evaluate unlearned images(my own image). What should I do?

Heidisnaps