v1.6.4 Wrong predicted class names

[nickjyj]

Search before asking

• I have searched the RF-DETR issues and found no similar bug report.

Bug

from rfdetr import RFDETRSegSmall

model = RFDETRSegSmall()

detections = model.predict("https://media.roboflow.com/dog.jpg", threshold=0.5)
print(detections.data["class_name"])

It output: ['sheep' 'tie' 'motorcycle']. However, it supposed to output "dog".

Environment

RF-DETR 1.6.4

Minimal Reproducible Example

from rfdetr import RFDETRSegSmall

model = RFDETRSegSmall()

detections = model.predict("https://media.roboflow.com/dog.jpg", threshold=0.5)
print(detections.data["class_name"])

Additional

No response

Are you willing to submit a PR?

• Yes, I'd like to help by submitting a PR!

[Alarmod]

Checked... Invalid labels in detections.data["class_name"]

from rfdetr import RFDETRSegSmall
from rfdetr.assets.coco_classes import COCO_CLASSES

model = RFDETRSegSmall()

detections = model.predict("https://media.roboflow.com/dog.jpg", threshold=0.5)
print(detections.data["class_name"])

data = [
    f"{COCO_CLASSES[class_id]} {conf:.2f}"
    for class_id, conf
    in zip(detections.class_id, detections.confidence)
]
print(data)

Result:

['sheep' 'tie' 'motorcycle']
['dog 0.90', 'backpack 0.78', 'car 0.58']

[Alarmod]

print(model.class_names)
print(COCO_CLASSES)

['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush']

{1: 'person', 2: 'bicycle', 3: 'car', 4: 'motorcycle', 5: 'airplane', 6: 'bus', 7: 'train', 8: 'truck', 9: 'boat', 10: 'traffic light', 11: 'fire hydrant', 13: 'stop sign', 14: 'parking meter', 15: 'bench', 16: 'bird', 17: 'cat', 18: 'dog', 19: 'horse', 20: 'sheep', 21: 'cow', 22: 'elephant', 23: 'bear', 24: 'zebra', 25: 'giraffe', 27: 'backpack', 28: 'umbrella', 31: 'handbag', 32: 'tie', 33: 'suitcase', 34: 'frisbee', 35: 'skis', 36: 'snowboard', 37: 'sports ball', 38: 'kite', 39: 'baseball bat', 40: 'baseball glove', 41: 'skateboard', 42: 'surfboard', 43: 'tennis racket', 44: 'bottle', 46: 'wine glass', 47: 'cup', 48: 'fork', 49: 'knife', 50: 'spoon', 51: 'bowl', 52: 'banana', 53: 'apple', 54: 'sandwich', 55: 'orange', 56: 'broccoli', 57: 'carrot', 58: 'hot dog', 59: 'pizza', 60: 'donut', 61: 'cake', 62: 'chair', 63: 'couch', 64: 'potted plant', 65: 'bed', 67: 'dining table', 70: 'toilet', 72: 'tv', 73: 'laptop', 74: 'mouse', 75: 'remote', 76: 'keyboard', 77: 'cell phone', 78: 'microwave', 79: 'oven', 80: 'toaster', 81: 'sink', 82: 'refrigerator', 84: 'book', 85: 'clock', 86: 'vase', 87: 'scissors', 88: 'teddy bear', 89: 'hair drier', 90: 'toothbrush'}

COCO_CLASSES don't have 12, for example, and don't have 0 class

[Alarmod]

@Borda Patch #1005 don't change result. Again
['sheep' 'tie' 'motorcycle']
Predict return classid 18.

[Alarmod]

num_logit_slots > n: True
model_class_names == list(COCO_CLASS_NAMES): True
_dataset_file in ("coco", None): False
_dataset_file: roboflow
_is_coco_pretrained: False

_dataset_file -- roboflow, not expected coco