oke-aditya / image_similarity Goto Github PK

I'm working on cat facial recognition. so my first idea was to calculate the distance between two embedded cat faces.
Is it possible to retrain/fine tune the embedding models for such task ?

Thank you.

embedding = torch.cat((embedding, enc_output), 0)
why cat embedding and enc_output?
and my log has some problem.

log:
torch.Size([1, 64, 64, 64]) embedding value
100%|██████████| 2/2 [00:00<00:00, 2.10it/s]
torch.Size([8, 64, 32, 32]) output for enc_output
why not use enc_output only?

Hi @oke-aditya,
Thanks for your great work and thanks for making it available for the community. The blog post is just fantastic. Indeed, I opened this issue to ask for the animal dataset you used. I reproduced the code and I need the dataset to run it, please if it is possible to share it with us. Thanks again!

I was trying to test an image using the train-image-inference.ipynb file. But in the last block of code, I am getting an error.

ValueError Traceback (most recent call last)
in ()
10 embedding = np.load(EMBEDDING_PATH, allow_pickle=True)
11
---> 12 indices_list = compute_similar_images(TEST_IMAGE_PATH, NUM_IMAGES, embedding, device)
13 plot_similar_images(indices_list)

7 frames
/usr/local/lib/python3.7/dist-packages/sklearn/metrics/pairwise.py in check_pairwise_arrays(X, Y, precomputed, dtype, accept_sparse, force_all_finite, copy)
153 raise ValueError("Incompatible dimension for X and Y matrices: "
154 "X.shape[1] == %d while Y.shape[1] == %d" % (
--> 155 X.shape[1], Y.shape[1]))
156
157 return X, Y

ValueError: Incompatible dimension for X and Y matrices: X.shape[1] == 65536 while Y.shape[1] == 262144

Please help me how to solve this issue

Tutorials are in .ipynb format, explaining each step of the process, really detailed, not production like.

Examples are be in the .py format, more production oriented. Ready to be run with arguments from the command line and easy to integrate with wandb sweeps and alike.

It should be an open dataset, please provide the link.

Hi you, Can I get encoder model trained?
In this link you give have not encoder model checkpoint.

Thank you and best regards.