This model is fine-tuned version of microsoft/conditional-detr-resnet-50.
You can find details of model in this github repo -> fashion-visual-search
And you can find fashion image feature extractor model -> yainage90/fashion-image-feature-extractor
This model was trained using a combination of two datasets: modanet and fashionpedia
The labels are ['bag', 'bottom', 'dress', 'hat', 'shoes', 'outer', 'top']
In the 96th epoch out of total of 100 epochs, the best score was achieved with mAP 0.7542. Therefore, it is believed that there is a little room for performance improvement.
from PIL import Image
import torch
from transformers import AutoImageProcessor, AutoModelForObjectDetection
device = 'cpu'
if torch.cuda.is_available():
device = torch.device('cuda')
elif torch.backends.mps.is_available():
device = torch.device('mps')
ckpt = 'yainage90/fashion-object-detection'
image_processor = AutoImageProcessor.from_pretrained(ckpt)
model = AutoModelForObjectDetection.from_pretrained(ckpt).to(device)
image = Image.open('<path/to/image>').convert('RGB')
with torch.no_grad():
inputs = image_processor(images=[image], return_tensors="pt")
outputs = model(**inputs.to(device))
target_sizes = torch.tensor([[image.size[1], image.size[0]]])
results = image_processor.post_process_object_detection(outputs, threshold=0.4, target_sizes=target_sizes)[0]
items = []
for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
score = score.item()
label = label.item()
box = [i.item() for i in box]
print(f"{model.config.id2label[label]}: {round(score, 3)} at {box}")
items.append((score, label, box))
