def _test_model(self, config_path, inference_func, batch=1):
model = model_zoo.get(config_path, trained=True)
image = get_sample_coco_image()
inputs = tuple(image.clone() for _ in range(batch))
wrapper = TracingAdapter(model, inputs, inference_func)
wrapper.eval()
with torch.no_grad():
# trace with smaller images, and the trace must still work
trace_inputs = tuple(
nn.functional.interpolate(
image, scale_factor=random.uniform(0.5, 0.7))
for _ in range(batch))
traced_model = torch.jit.trace(wrapper, trace_inputs)
outputs = inference_func(model, *inputs)
traced_outputs = wrapper.outputs_schema(traced_model(*inputs))
if batch > 1:
for output, traced_output in zip(outputs, traced_outputs):
assert_instances_allclose(output,
traced_output,
size_as_tensor=True)
else:
assert_instances_allclose(outputs,
traced_outputs,
size_as_tensor=True)
def _test_model(self, config_path, inference_func):
model = model_zoo.get(config_path, trained=True)
image = get_sample_coco_image()
class Wrapper(nn.ModuleList): # a wrapper to make the model traceable
def forward(self, image):
outputs = inference_func(self[0], image)
flattened_outputs, schema = flatten_to_tuple(outputs)
if not hasattr(self, "schema"):
self.schema = schema
return flattened_outputs
def rebuild(self, flattened_outputs):
return self.schema(flattened_outputs)
wrapper = Wrapper([model])
wrapper.eval()
with torch.no_grad(), patch_builtin_len():
small_image = nn.functional.interpolate(image, scale_factor=0.5)
# trace with a different image, and the trace must still work
traced_model = torch.jit.trace(wrapper, (small_image,))
output = inference_func(model, image)
traced_output = wrapper.rebuild(traced_model(image))
assert_instances_allclose(output, traced_output, size_as_tensor=True)
def _test_model(self, config_path, inference_func):
model = model_zoo.get(config_path, trained=True)
image = get_sample_coco_image()
wrapper = TracingAdapter(model, image, inference_func)
wrapper.eval()
with torch.no_grad():
small_image = nn.functional.interpolate(image, scale_factor=0.5)
# trace with a different image, and the trace must still work
traced_model = torch.jit.trace(wrapper, (small_image,))
output = inference_func(model, image)
traced_output = wrapper.outputs_schema(traced_model(image))
assert_instances_allclose(output, traced_output, size_as_tensor=True)
def _test_model(self, config_path, WrapperCls):
# TODO wrapper should be handled by export API in the future
model = model_zoo.get(config_path, trained=True)
image = get_sample_coco_image()
model = WrapperCls([model])
model.eval()
with torch.no_grad(), patch_builtin_len():
small_image = nn.functional.interpolate(image, scale_factor=0.5)
# trace with a different image, and the trace must still work
traced_model = torch.jit.trace(model, (small_image, ))
output = WrapperCls.convert_output(model(image))
traced_output = WrapperCls.convert_output(traced_model(image))
assert_instances_allclose(output, traced_output)
def _test_retinanet_model(self, config_path):
model = model_zoo.get(config_path, trained=True)
model.eval()
fields = {
"pred_boxes": Boxes,
"scores": Tensor,
"pred_classes": Tensor,
}
script_model = export_torchscript_with_instances(model, fields)
img = get_sample_coco_image()
inputs = [{"image": img}]
with torch.no_grad():
instance = model(inputs)[0]["instances"]
scripted_instance = convert_scripted_instances(script_model(inputs)[0])
scripted_instance = detector_postprocess(scripted_instance, img.shape[1], img.shape[2])
assert_instances_allclose(instance, scripted_instance)
def _test_rcnn_model(self, config_path):
model = model_zoo.get(config_path, trained=True)
model.eval()
fields = {
"proposal_boxes": Boxes,
"objectness_logits": Tensor,
"pred_boxes": Boxes,
"scores": Tensor,
"pred_classes": Tensor,
"pred_masks": Tensor,
}
script_model = export_torchscript_with_instances(model, fields)
inputs = [{"image": get_sample_coco_image()}]
with torch.no_grad():
instance = model.inference(inputs, do_postprocess=False)[0]
scripted_instance = script_model.inference(inputs, do_postprocess=False)[0]
assert_instances_allclose(instance, scripted_instance)
def _test_model(self, config_path, device="cpu"):
# requires extra dependencies
from detectron2.export import Caffe2Model, add_export_config, Caffe2Tracer
cfg = model_zoo.get_config(config_path)
add_export_config(cfg)
cfg.MODEL.DEVICE = device
model = model_zoo.get(config_path, trained=True, device=device)
inputs = [{"image": get_sample_coco_image()}]
c2_model = Caffe2Tracer(cfg, model,
copy.deepcopy(inputs)).export_caffe2()
with tempfile.TemporaryDirectory(prefix="detectron2_unittest") as d:
c2_model.save_protobuf(d)
c2_model.save_graph(os.path.join(d, "test.svg"),
inputs=copy.deepcopy(inputs))
c2_model = Caffe2Model.load_protobuf(d)
c2_model(inputs)[0]["instances"]
def _test_model(self, config_path, device="cpu"):
cfg = model_zoo.get_config(config_path)
cfg.MODEL.DEVICE = device
model = model_zoo.get(config_path, trained=True, device=device)
inputs = [{"image": get_sample_coco_image()}]
tracer = Caffe2Tracer(cfg, model, copy.deepcopy(inputs))
with tempfile.TemporaryDirectory(prefix="detectron2_unittest") as d:
if not os.environ.get("CI"):
# This requires onnx, which is not yet available on public CI
c2_model = tracer.export_caffe2()
c2_model.save_protobuf(d)
c2_model.save_graph(os.path.join(d, "test.svg"),
inputs=copy.deepcopy(inputs))
c2_model = Caffe2Model.load_protobuf(d)
c2_model(inputs)[0]["instances"]
ts_model = tracer.export_torchscript()
ts_model.save(os.path.join(d, "model.ts"))
def _test_rcnn_model(self, config_path):
model = model_zoo.get(config_path, trained=True)
model.eval()
fields = {
"proposal_boxes": Boxes,
"objectness_logits": Tensor,
"pred_boxes": Boxes,
"scores": Tensor,
"pred_classes": Tensor,
"pred_masks": Tensor,
}
script_model = scripting_with_instances(model, fields)
# Test that batch inference with different shapes are supported
image = get_sample_coco_image()
small_image = nn.functional.interpolate(image, scale_factor=0.5)
inputs = [{"image": image}, {"image": small_image}]
with torch.no_grad():
instance = model.inference(inputs, do_postprocess=False)[0]
scripted_instance = script_model.inference(inputs, do_postprocess=False)[0]
assert_instances_allclose(instance, scripted_instance)
def _test_model(self, config_path, inference_func, batch=1):
model = model_zoo.get(config_path, trained=True)
image = get_sample_coco_image()
inputs = tuple(image.clone() for _ in range(batch))
wrapper = TracingAdapter(model, inputs, inference_func)
wrapper.eval()
with torch.no_grad():
# trace with smaller images, and the trace must still work
trace_inputs = tuple(
nn.functional.interpolate(image, scale_factor=random.uniform(0.5, 0.7))
for _ in range(batch)
)
traced_model = torch.jit.trace(wrapper, trace_inputs)
testing_devices = self._get_device_casting_test_cases(model)
# save and load back the model in order to show traceback of TorchScript
with tempfile.TemporaryDirectory(prefix="detectron2_test") as d:
basename = "model"
jitfile = f"{d}/{basename}.jit"
torch.jit.save(traced_model, jitfile)
traced_model = torch.jit.load(jitfile)
if any(device and "cuda" in device for device in testing_devices):
self._check_torchscript_no_hardcoded_device(jitfile, d, "cuda")
for device in testing_devices:
print(f"Testing casting to {device} for inference (traced on {model.device}) ...")
with torch.no_grad():
outputs = inference_func(copy.deepcopy(model).to(device), *inputs)
traced_outputs = wrapper.outputs_schema(traced_model.to(device)(*inputs))
if batch > 1:
for output, traced_output in zip(outputs, traced_outputs):
assert_instances_allclose(output, traced_output, size_as_tensor=True)
else:
assert_instances_allclose(outputs, traced_outputs, size_as_tensor=True)
