This is a wrapper for the YOLOX https://arxiv.org/abs/2107.08430 object detection model. The class handles preprocessing of the input, postprocessing of the model output, and calculation of bounding boxes and their probabilities.
Type
Default
Details
model
Module
The YOLOX model.
normalize_mean
Tensor
tensor([[[[0.]],
[[0.]],
[[0.]]]])
The mean values for normalization.
normalize_std
Tensor
tensor([[[[1.]],
[[1.]],
[[1.]]]])
The standard deviation values for normalization.
strides
typing.Optional[typing.List[int]]
[8, 16, 32]
The strides for the model.
scale_inp
bool
False
Whether to scale the input by dividing by 255.
channels_last
bool
False
Whether the input tensor has channels first.
run_box_and_prob_calculation
bool
True
Whether to calculate the bounding boxes and their probabilities.
model_type ='yolox_tiny'model = build_model(model_type, 19, pretrained=True)test_inp = torch.randn(1, 3, 256, 256)with torch.no_grad(): cls_scores, bbox_preds, objectness = model(test_inp)print(f"cls_scores: {[cls_score.shape for cls_score in cls_scores]}")print(f"bbox_preds: {[bbox_pred.shape for bbox_pred in bbox_preds]}")print(f"objectness: {[objectness.shape for objectness in objectness]}")
The file ./pretrained_checkpoints/yolox_tiny.pth already exists and overwrite is set to False.
cls_scores: [torch.Size([1, 19, 32, 32]), torch.Size([1, 19, 16, 16]), torch.Size([1, 19, 8, 8])]
bbox_preds: [torch.Size([1, 4, 32, 32]), torch.Size([1, 4, 16, 16]), torch.Size([1, 4, 8, 8])]
objectness: [torch.Size([1, 1, 32, 32]), torch.Size([1, 1, 16, 16]), torch.Size([1, 1, 8, 8])]
norm_stats = [*NORM_STATS[model_type].values()]# Convert the normalization stats to tensorsmean_tensor = torch.tensor(norm_stats[0]).view(1, 3, 1, 1)std_tensor = torch.tensor(norm_stats[1]).view(1, 3, 1, 1)# Set the model to evaluation modemodel.eval();# Wrap the model with preprocessing and post-processing stepswrapped_model = YOLOXInferenceWrapper(model, mean_tensor, std_tensor, scale_inp=False, channels_last=False)with torch.no_grad(): model_output = wrapped_model(test_inp)model_output.shape