def test_model_script_detection(self):
model = detr_resnet50(pretrained=False).eval()
scripted_model = torch.jit.script(model)
x = nested_tensor_from_tensor_list(
[torch.rand(3, 200, 200), torch.rand(3, 200, 250)]
)
out = model(x)
out_script = scripted_model(x)
self.assertTrue(out["pred_logits"].equal(out_script["pred_logits"]))
self.assertTrue(out["pred_boxes"].equal(out_script["pred_boxes"]))
def test_model_onnx_detection(self):
model = detr_resnet50(pretrained=False).eval()
dummy_image = torch.ones(1, 3, 800, 800) * 0.3
model(dummy_image)
# Test exported model on images of different size, or dummy input
self.run_model(
model,
[(torch.rand(1, 3, 750, 800),)],
input_names=["inputs"],
output_names=["pred_logits", "pred_boxes"],
tolerate_small_mismatch=True,
)
def test_model_detection_different_inputs(self):
model = detr_resnet50(pretrained=False).eval()
# support NestedTensor
x = nested_tensor_from_tensor_list(
[torch.rand(3, 200, 200), torch.rand(3, 200, 250)]
)
out = model(x)
self.assertIn("pred_logits", out)
# and 4d Tensor
x = torch.rand(1, 3, 200, 200)
out = model(x)
self.assertIn("pred_logits", out)
# and List[Tensor[C, H, W]]
x = torch.rand(3, 200, 200)
out = model([x])
self.assertIn("pred_logits", out)
def test_warpped_model_script_detection(self):
class WrappedDETR(nn.Module):
def __init__(self, model):
super().__init__()
self.model = model
def forward(self, inputs: List[Tensor]):
sample = nested_tensor_from_tensor_list(inputs)
return self.model(sample)
model = detr_resnet50(pretrained=False)
wrapped_model = WrappedDETR(model)
wrapped_model.eval()
scripted_model = torch.jit.script(wrapped_model)
x = [torch.rand(3, 200, 200), torch.rand(3, 200, 250)]
out = wrapped_model(x)
out_script = scripted_model(x)
self.assertTrue(out["pred_logits"].equal(out_script["pred_logits"]))
self.assertTrue(out["pred_boxes"].equal(out_script["pred_boxes"]))
