Description
Hi,
I’m trying to run 2 TensorRT engines, each with a different model, on the same GPU but I’m getting the error
Cask Error in checkCaskExecError<false>: 7 (Cask Convolution execution).
What is the reason for this error?
Below is my code:
import tensorrt as trt
TRT_LOGGER = trt.Logger(trt.Logger.WARNING)
import pycuda.driver as cuda
class FeatureCalcTrt(object):
def __init__(self, device_id, params_file):
self.__device_id = device_id
self._params_file = params_file
self.dev = None
self.ctx = None
self.engine = None
self.inputs = None
self.outputs = None
self.bindings = None
self.stream = None
self.engine_context = None
def _init_network_impl(self):
LOG.info("Initializing Network %s", self._device_id)
os.environ["CUDA_VISIBLE_DEVICES"] = str(self._device_id)
self.dev = cuda.Device(self._device_id)
self.ctx = self.dev.make_context()
with open(self._params_file, 'rb') as f, trt.Runtime(TRT_LOGGER) as runtime:
self.engine = runtime.deserialize_cuda_engine(f.read())
self.inputs, self.outputs, self.bindings, self.stream = self._allocate_trt_buffers(self.engine)
assert len(self.inputs) == 1, "inputs = %s" % self.inputs
assert len(self.outputs) == 1, "outputs = %s" % self.outputs
self.engine_context = self.engine.create_execution_context()
@staticmethod
def _allocate_trt_buffers(engine):
inputs = []
outputs = []
bindings = []
stream = cuda.Stream()
for binding in engine:
size = trt.volume(engine.get_binding_shape(binding)) * engine.max_batch_size
dtype = trt.nptype(engine.get_binding_dtype(binding))
# Allocate host and device buffers
host_mem = cuda.pagelocked_empty(size, dtype)
device_mem = cuda.mem_alloc(host_mem.nbytes)
# Append the device buffer to device bindings.
bindings.append(int(device_mem))
# Append to the appropriate list.
if engine.binding_is_input(binding):
inputs.append((host_mem, device_mem))
else:
LOG.info("Allocating output %s %s", engine.get_binding_shape(binding), binding)
outputs.append((host_mem, device_mem))
return inputs, outputs, bindings, stream
@staticmethod
def _do_trt_inference(context, bindings, inputs, outputs, stream, batch_size=1):
# Transfer input data to the GPU.
for inp in inputs:
LOG.debug("input %s", inp[0])
cuda.memcpy_htod_async(inp[1], inp[0], stream)
# Run inference.
context.execute_async(batch_size=batch_size, bindings=bindings, stream_handle=stream.handle)
# Transfer predictions back from the GPU.
for out in outputs:
cuda.memcpy_dtoh_async(out[0], out[1], stream)
# Synchronize the stream
stream.synchronize()
# Return only the host outputs.
LOG.debug("output %s", outputs[0][0])
return [out[0] for out in outputs]
@staticmethod
def _process_trt_batch(patches, context, inputs, outputs, bindings, stream):
pagelocked_buffer = inputs[0][0]
flat_patches = np.array(patches).ravel()
data_size = len(flat_patches)
np.copyto(pagelocked_buffer[:data_size], flat_patches)
[cur_features] = FeatureCalcTrt._do_trt_inference(context, bindings=bindings, inputs=inputs, outputs=outputs, stream=stream,
batch_size=len(patches))
return cur_features.copy()
def calc_features_one_batch(self, patches):
return self._process_trt_batch(patches, self.engine_context, self.inputs, self.outputs, self.bindings, self.stream)
if __name__ == '__main__':
cuda.init()
f1 = FeatureCalcTrt(0, 'params1.trt')
f2 = FeatureCalcTrt(0, 'params2,trt')
patches = // code that reads patches
res1 = f1.calc_features_one_batch(patches)
res2 = f2.calc_features_one_batch(patches)
Environment
TensorRT Version: 7.0.0
GPU Type: RTX 2080 ti
Nvidia Driver Version: 410.78
CUDA Version: 10.0
CUDNN Version: 7.4.2
Operating System + Version: Ubuntu 18.04
Python Version (if applicable): 2.7
