Hi all. when I run code Auto-tuning a Convolutional Network for NVIDIA GPU.
I meet the problem below. How can I solve it?
[Task 1/16] Current/Best: 0.00/ 0.00 GFLOPS | Progress: (0/2000) | 0.00 sException in thread Thread-1:
Traceback (most recent call last):
File "/home/miniconda3/envs/tvm-build/lib/python3.7/threading.py", line 926, in _bootstrap_inner
self.run()
File "/home/miniconda3/envs/tvm-build/lib/python3.7/threading.py", line 870, in run
self._target(*self._args, **self._kwargs)
File "/root/tvm/python/tvm/rpc/server.py", line 272, in _listen_loop
_serving(conn, addr, opts, load_library)
File "/root/tvm/python/tvm/rpc/server.py", line 150, in _serving
f'RPCSessionTimeoutError: Your {opts["timeout"]}s session has expired, '
File "tvm/_ffi/_cython/./packed_func.pxi", line 331, in tvm._ffi._cy3.core.PackedFuncBase.__call__
File "tvm/_ffi/_cython/./packed_func.pxi", line 262, in tvm._ffi._cy3.core.FuncCall
File "tvm/_ffi/_cython/./packed_func.pxi", line 251, in tvm._ffi._cy3.core.FuncCall3
File "tvm/_ffi/_cython/./base.pxi", line 181, in tvm._ffi._cy3.core.CHECK_CALL
tvm._ffi.base.TVMError: Traceback (most recent call last):
3: TVMFuncCall
2: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::runtime::TypedPackedFunc<void (int, tvm::runtime::String)>::AssignTypedLambda<tvm::runtime::{lambda(int, tvm::runtime::String)#3}>(tvm::runtime::{lambda(int, tvm::runtime::String)#3}, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> >)::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
1: tvm::runtime::SimpleSockHandler::Write(void const*, unsigned long)
0: tvm::support::Socket::Error(char const*)
File "/root/tvm/src/runtime/rpc/../../support/socket.h", line 362
TVMError: Socket SendAll Error:Broken pipe
My source is here
import os
import numpy as np
import tvm
from tvm import relay, autotvm
import tvm.relay.testing
from tvm.autotvm.tuner import XGBTuner, GATuner, RandomTuner, GridSearchTuner
import tvm.contrib.graph_executor as runtime
def get_network(name, batch_size):
input_shape = (batch_size, 3, 224, 224)
output_shape = (batch_size, 1000)
if "resnet" in name:
n_layer = int(name.split("-")[1])
mod, params = relay.testing.resnet.get_workload(
num_layers=n_layer, batch_size=batch_size, dtype=dtype
)
elif "vgg" in name:
n_layer = int(name.split("-")[1])
mod, params = relay.testing.vgg.get_workload(
num_layers=n_layer, batch_size=batch_size, dtype=dtype
)
elif name == "mobilenet":
mod, params = relay.testing.mobilenet.get_workload(batch_size=batch_size, dtype=dtype)
elif name == "squeezenet_v1.1":
mod, params = relay.testing.squeezenet.get_workload(
batch_size=batch_size, version="1.1", dtype=dtype
)
elif name == "inception_v3":
input_shape = (batch_size, 3, 299, 299)
mod, params = relay.testing.inception_v3.get_workload(batch_size=batch_size, dtype=dtype)
elif name == "mxnet":
from mxnet.gluon.model_zoo.vision import get_model
block = get_model("resnet18_v1", pretrained=True)
mod, params = relay.frontend.from_mxnet(block, shape={"data": input_shape}, dtype=dtype)
net = mod["main"]
net = relay.Function(
net.params, relay.nn.softmax(net.body), None, net.type_params, net.attrs
)
mod = tvm.IRModule.from_expr(net)
else:
raise ValueError("Unsupported network: " + name)
return mod, params, input_shape, output_shape
target = tvm.target.cuda()
network = "resnet-18"
log_file = "%s.log" % network
dtype = "float32"
tuning_option = {
"log_filename": log_file,
"tuner": "xgb",
"n_trial": 2000,
"early_stopping": 600,
"measure_option": autotvm.measure_option(
builder=autotvm.LocalBuilder(timeout=10),
runner=autotvm.LocalRunner(number=20, repeat=3, timeout=4, min_repeat_ms=150),
),
}
def tune_tasks(
tasks,
measure_option,
tuner="xgb",
n_trial=1000,
early_stopping=None,
log_filename="tuning.log",
use_transfer_learning=True,
):
tmp_log_file = log_filename + ".tmp"
if os.path.exists(tmp_log_file):
os.remove(tmp_log_file)
for i, tsk in enumerate(reversed(tasks)):
prefix = "[Task %2d/%2d] " % (i + 1, len(tasks))
if tuner == "xgb":
tuner_obj = XGBTuner(tsk, loss_type="reg")
elif tuner == "xgb_knob":
tuner_obj = XGBTuner(tsk, loss_type="reg", feature_type="knob")
elif tuner == "xgb_itervar":
tuner_obj = XGBTuner(tsk, loss_type="reg", feature_type="itervar")
elif tuner == "xgb_curve":
tuner_obj = XGBTuner(tsk, loss_type="reg", feature_type="curve")
elif tuner == "xgb_rank":
tuner_obj = XGBTuner(tsk, loss_type="rank")
elif tuner == "xgb_rank_knob":
tuner_obj = XGBTuner(tsk, loss_type="rank", feature_type="knob")
elif tuner == "xgb_rank_itervar":
tuner_obj = XGBTuner(tsk, loss_type="rank", feature_type="itervar")
elif tuner == "xgb_rank_curve":
tuner_obj = XGBTuner(tsk, loss_type="rank", feature_type="curve")
elif tuner == "xgb_rank_binary":
tuner_obj = XGBTuner(tsk, loss_type="rank-binary")
elif tuner == "xgb_rank_binary_knob":
tuner_obj = XGBTuner(tsk, loss_type="rank-binary", feature_type="knob")
elif tuner == "xgb_rank_binary_itervar":
tuner_obj = XGBTuner(tsk, loss_type="rank-binary", feature_type="itervar")
elif tuner == "xgb_rank_binary_curve":
tuner_obj = XGBTuner(tsk, loss_type="rank-binary", feature_type="curve")
elif tuner == "ga":
tuner_obj = GATuner(tsk, pop_size=100)
elif tuner == "random":
tuner_obj = RandomTuner(tsk)
elif tuner == "gridsearch":
tuner_obj = GridSearchTuner(tsk)
else:
raise ValueError("Invalid tuner: " + tuner)
if use_transfer_learning:
if os.path.isfile(tmp_log_file):
tuner_obj.load_history(autotvm.record.load_from_file(tmp_log_file))
tsk_trial = min(n_trial, len(tsk.config_space))
tuner_obj.tune(
n_trial=tsk_trial,
early_stopping=early_stopping,
measure_option=measure_option,
callbacks=[
autotvm.callback.progress_bar(tsk_trial, prefix=prefix),
autotvm.callback.log_to_file(tmp_log_file),
],
)
autotvm.record.pick_best(tmp_log_file, log_filename)
os.remove(tmp_log_file)
def tune_and_evaluate(tuning_opt):
print("Extract tasks...")
mod, params, input_shape, out_shape = get_network(network, batch_size=1)
tasks = autotvm.task.extract_from_program(
mod["main"], target=target, params=params, ops=(relay.op.get("nn.conv2d"),)
)
print("Tuning...")
tune_tasks(tasks, **tuning_opt)
with autotvm.apply_history_best(log_file):
print("Compile...")
with tvm.transform.PassContext(opt_level=3):
lib = relay.build_module.build(mod, target=target, params=params)
dev = tvm.device(str(target), 2)
module = runtime.GraphModule(lib["default"](dev))
data_tvm = tvm.nd.array((np.random.uniform(size=input_shape)).astype(dtype))
module.set_input("data", data_tvm)
print("Evaluate inference time cost...")
print(module.benchmark(dev, number=1, repeat=600))
tune_and_evaluate(tuning_option)