Spaces:
Runtime error
Runtime error
File size: 2,866 Bytes
0ef6060 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
from __future__ import annotations
import os
import numpy as np
import torch
import torch.nn as nn
from mmdet.apis import inference_detector, init_detector_from_hf_hub
MODEL_DICT = {"faster_rcnn": {"repo_id": "blesot/Faster-R-CNN-Object-detection"}, "mask_rcnn": {"repo_id": "blesot/Mask-RCNN"}}
class Model:
def __init__(self, model_name: str, device: str | torch.device):
self.device = torch.device(device)
self._load_all_models_once()
self.model_name = model_name
self.model = self._load_model(model_name)
def _load_all_models_once(self) -> None:
for name in MODEL_DICT.keys():
self._load_model(name)
def _load_model(self, name: str) -> nn.Module:
dic = MODEL_DICT[name]
return init_detector_from_hf_hub(dic['repo_id'], device=self.device)
def set_model(self, name: str) -> None:
if name == self.model_name:
return
self.model_name = name
self.model = self._load_model(name)
def detect_and_visualize(
self, image: np.ndarray, score_threshold: float
) -> tuple[list[np.ndarray] | tuple[list[np.ndarray],
list[list[np.ndarray]]]
| dict[str, np.ndarray], np.ndarray]:
out = self.detect(image)
vis = self.visualize_detection_results(image, out, score_threshold)
return out, vis
def detect(
self, image: np.ndarray
) -> list[np.ndarray] | tuple[
list[np.ndarray], list[list[np.ndarray]]] | dict[str, np.ndarray]:
image = image[:, :, ::-1] # RGB -> BGR
out = inference_detector(self.model, image)
return out
def visualize_detection_results(
self,
image: np.ndarray,
detection_results: list[np.ndarray]
| tuple[list[np.ndarray], list[list[np.ndarray]]]
| dict[str, np.ndarray],
score_threshold: float = 0.3) -> np.ndarray:
image = image[:, :, ::-1] # RGB -> BGR
vis = self.model.show_result(image,
detection_results,
score_thr=score_threshold,
bbox_color=None,
text_color=(200, 200, 200),
mask_color=None)
return vis[:, :, ::-1] # BGR -> RGB
class AppModel(Model):
def run(
self, model_name: str, image: np.ndarray, score_threshold: float
) -> tuple[list[np.ndarray] | tuple[list[np.ndarray],
list[list[np.ndarray]]]
| dict[str, np.ndarray], np.ndarray]:
self.set_model(model_name)
return self.detect_and_visualize(image, score_threshold)
def model_list(self) -> list[str]:
return list(MODEL_DICT.keys())
|