martlgap / octuplet-loss Goto Github PK
View Code? Open in Web Editor NEWRepo for our Paper: Octuplet Loss: Make Your Face Recognition Model Robust to Image Resolution
License: MIT License
Repo for our Paper: Octuplet Loss: Make Your Face Recognition Model Robust to Image Resolution
License: MIT License
Hello, are you able to share code to generate embeddings database from our own dataset? So that we can use for inference?
Thanks!
hi Martlgap,
Your work was amazing. Are you willing to provide the dataset file ("/mnt/ssd2/test_embs.pkl") ? Meanwhile, the file seems contains both basic training data and downsimpled data, am I correct?
Thx
Dear @Martlgap ,
first of all thank you for this magnificent work you have done. I wanted to ask you the steps I should take to achieve this face recognition with pytorch. I saw that in the github he released a python file that uses pytorch, I think it is the neural network. To implement everything and make it work what steps should I do starting from the 'pt_octuplet_loss.py' file.
Sorry for disturbing.
Thank you in advance for your reply.
Dear @Martlgap ,
first of all thank you for this magnificent work you have done. I wanted to ask you two questions.
1.How many batches are there in one epoch。(I don't know how you generate minibatch. But I randomly selected different identity pictures as a minibatch, so I need to know this.)
2.Whether the resolution of low resolution pictures in one batch is random, or the resolution of low resolution pictures in one batch is the same, but different batches are different ?
Thank you in advance for your reply.
Thanks for your work
But I'm still puzzled about the data preprocessing for the pretrained face model. Apart from the finetuning process, is the data downsampling used to pretrain the face model?
Hello! Thank you for your work. Could you please provide the finetuned weights?
can you upload this file?
I based the code below on the example main.py from the hugging face model page.
Identical images produce a very small distance of 4.919836871231098e-09 as expected.
The different images used here produce a distance of 0.3032730731332305.
The aligned images appear to have been processed correctly at 112x112.
The original images can be found here.
https://resizing.flixster.com/-XZAfHZM39UwaGJIFWKAE8fS0ak=/v3/t/assets/30905_v9_bc.jpg
https://upload.wikimedia.org/wikipedia/commons/thumb/3/30/David_Schwimmer_2011.jpg/800px-David_Schwimmer_2011.jpg
Apologies if this is a mistake on my part.
import numpy as np
import onnxruntime as rt
import mediapipe as mp
import cv2
import time
from skimage.transform import SimilarityTransform
from scipy.spatial.distance import cosine
# ---------------------------------------------------------------------------------------------------------------------
# INITIALIZATIONS
# Target landmark coordinates for alignment (used in training)
LANDMARKS_TARGET = np.array(
[
[38.2946, 51.6963],
[73.5318, 51.5014],
[56.0252, 71.7366],
[41.5493, 92.3655],
[70.7299, 92.2041],
],
dtype=np.float32,
)
def compare(img_path1, img_path2):
img1_embedding = infer(img_path1)
img2_embedding = infer(img_path2)
cos_dist = cosine(img1_embedding, img2_embedding)
if cos_dist <= 0.5:
print(f'{img_path1} and {img_path2} are the same')
else:
print(f'{img_path1} and {img_path2} are different')
print(f'cosine distance = {cos_dist}')
def infer(img_path):
img = cv2.imread(img_path)
# Process the image with the face detector
FACE_DETECTOR = mp.solutions.face_mesh.FaceMesh(
refine_landmarks=True, min_detection_confidence=0.5, min_tracking_confidence=0.5, max_num_faces=1
)
result = FACE_DETECTOR.process(img)
if result.multi_face_landmarks:
# Select 5 Landmarks (Eye Centers, Nose Tip, Left Mouth Corner, Right Mouth Corner)
five_landmarks = np.asarray(result.multi_face_landmarks[0].landmark)[[470, 475, 1, 57, 287]]
# Extract the x and y coordinates of the landmarks of interest
landmarks = np.asarray(
[[landmark.x * img.shape[1], landmark.y * img.shape[0]] for landmark in five_landmarks]
)
else:
print(f"No faces detected in {img_path}")
exit()
# ---------------------------------------------------------------------------------------------------------------------
# FACE ALIGNMENT
# Align Image with the 5 Landmarks
tform = SimilarityTransform()
tform.estimate(landmarks, LANDMARKS_TARGET)
tmatrix = tform.params[0:2, :]
img_aligned = cv2.warpAffine(img, tmatrix, (112, 112), borderValue=0.0)
# safe to disk
cv2.imwrite(f"{img_path}_aligned.jpg", img_aligned)
# ---------------------------------------------------------------------------------------------------------------------
# FACE RECOGNITION
# Inference face embeddings with onnxruntime
input_image = (np.asarray([img_aligned]).astype(np.float32)).clip(0.0, 255.0).transpose(0, 3, 1, 2)
FACE_RECOGNIZER = rt.InferenceSession("FaceTransformerOctupletLoss.onnx", providers=rt.get_available_providers())
embedding = FACE_RECOGNIZER.run(None, {"input_image": input_image})[0][0]
return embedding
if __name__ == "__main__":
ds = "David_Schwimmer.jpg"
ja = "jennifer_aniston.jpg"
compare(ja, ds)
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.