search

SathwikTejaswi / deep-ranking

Learning Fine-grained Image Similarity with Deep Ranking is a novel application of neural networks, where the authors use a new multi scale architecture combined with a triplet loss to create a neural network that is able to perform image search. This repository is a simplified implementation of the same
MIT License
80 stars 17 forks source link

can you provide dataset? #2

Closed noelcodes closed 5 years ago

noelcodes commented 5 years ago

can you provide dataset? I want them in order to generate train_embeddings.npy and test_embeddings.npy.

noelcodes commented 5 years ago

OK found it: https://tiny-imagenet.herokuapp.com/

But I ran python train_embedding.py, thrown me error no matter where I place the dataset.... ha ha..

` python train_embedding.py

libraries imported loading training data... Traceback (most recent call last): File "train_embedding.py", line 87, in Tiny = Tiny('tiny-imagenet-200/val') File "train_embedding.py", line 52, in init for i,j in enumerate(os.listdir(os.path.join(self.root_dir))): FileNotFoundError: [WinError 3] The system cannot find the path specified: 'tiny-imagenet-200/val'`

SathwikTejaswi commented 5 years ago

Hi, This is the link to the dataset : http://cs231n.stanford.edu/tiny-imagenet-200.zip

SathwikTejaswi commented 5 years ago

For the FileNotFoundError, you have to replace 'tiny-imagenet-200/val' with the path to the dataset on your system!