p12346870
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

gpu add test for amp

This commit is contained in:
VectorSL 2020-04-28 11:24:03 +08:00
parent 420ef2a352
commit 1d7fe758a0
2 changed files with 28 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
mindspore/ccsrc/kernel/gpu/arrays/slice_gpu_kernel.h
View File

@ -129,10 +129,10 @@ class SliceGpuFwdKernel : public GpuKernel {
}
begin_ = GetAttr<std::vector<int>>(kernel_node, "begin");
for (size_t i = 0; i < input_shape.size(); i++) {
if ((begin_[i] > 0 && (begin_[i] >= SizeToInt(input_shape[i]))) ||
if ((begin_[i] > 0 && (begin_[i] > SizeToInt(input_shape[i]))) ||
(begin_[i] < 0 && (std::abs(begin_[i]) > SizeToInt(input_shape[i])))) {
MS_LOG(ERROR) << "Error input, out of bounds " << input_shape[i] << " in axis " << i << ".";
return false;
MS_LOG(INFO) << "Input out of bounds " << input_shape[i] << " in axis " << i << ".";
begin_[i] = 0;
}
}
return true;

28
tests/st/networks/test_gpu_resnet.py
View File

@ -32,9 +32,7 @@ from mindspore.nn.optim import Momentum
from mindspore.ops import operations as P
from mindspore.nn import TrainOneStepCell, WithLossCell
from mindspore.nn import Dense
from mindspore.common.initializer import initializer
context.set_context(mode=context.GRAPH_MODE, device_target="GPU")
from mindspore import amp
def random_normal_init(shape, mean=0.0, stddev=0.01, seed=None):
@ -326,6 +324,7 @@ def resnet50(num_classes):
@pytest.mark.platform_x86_gpu_training
@pytest.mark.env_onecard
def test_trainTensor(num_classes=10, epoch=8, batch_size=1):
context.set_context(mode=context.GRAPH_MODE, device_target="GPU")
net = resnet50(num_classes)
lr = 0.1
momentum = 0.9
@ -341,3 +340,26 @@ def test_trainTensor(num_classes=10, epoch=8, batch_size=1):
loss = train_network(data, label)
losses.append(loss)
assert(losses[-1].asnumpy() < 1)
@pytest.mark.level0
@pytest.mark.platform_x86_gpu_training
@pytest.mark.env_onecard
def test_trainTensor_amp(num_classes=10, epoch=18, batch_size=16):
context.set_context(mode=context.GRAPH_MODE, device_target="GPU", enable_mem_reuse=False,
enable_dynamic_memory=False)
net = resnet50(num_classes)
lr = 0.1
momentum = 0.9
optimizer = Momentum(filter(lambda x: x.requires_grad, net.get_parameters()), lr, momentum)
criterion = nn.SoftmaxCrossEntropyWithLogits(is_grad=False, sparse=True)
train_network = amp.build_train_network(net, optimizer, criterion, level="O2")
train_network.set_train()
losses = []
for i in range(0, epoch):
data = Tensor(np.ones([batch_size, 3, 224, 224]).astype(np.float32) * 0.01)
label = Tensor(np.ones([batch_size]).astype(np.int32))
loss = train_network(data, label)
losses.append(loss)
assert(losses[-1][0].asnumpy() < 1)
assert(losses[-1][1].asnumpy() == False)
assert(losses[-1][2].asnumpy() > 1)