FHardtanhTest,
LayerReLUTest,
FReLUTest,
LayerELUTest,
FPELUTest,
]:
for i in range(10):
model = act_type()
model.eval()
input_np = np.random.uniform(0, 1, (1, 3, 224, 224))
input_var = torch.FloatTensor(input_np)
torch.onnx.export(model,
input_var,
"_tmpnet.onnx",
verbose=True,
input_names=['test_in'],
output_names=['test_out'])
onnx_model = onnx.load('_tmpnet.onnx')
k_model = onnx_to_keras(onnx_model, ['test_in'])
os.unlink('_tmpnet.onnx')
error = check_torch_keras_error(model, k_model, input_np)
print('Error:', error)
if max_error < error:
max_error = error
print('Max error: {0}'.format(max_error))
model = LayerTest(kernel_size=kernel_size,
padding=padding,
stride=stride)
model.eval()
input_np = np.random.uniform(0, 1, (1, 3, 224, 224))
input_var = Variable(torch.FloatTensor(input_np))
torch.onnx.export(model,
input_var,
"_tmpnet.onnx",
verbose=True,
input_names=['test_in'],
output_names=['test_out'])
onnx_model = onnx.load('_tmpnet.onnx')
k_model = onnx_to_keras(onnx_model, ['test_in'],
change_ordering=change_ordering)
error = check_torch_keras_error(
model,
k_model,
input_np,
change_ordering=change_ordering)
print('Error:', error)
if max_error < error:
max_error = error
print('Max error: {0}'.format(max_error))
for stride in [1, 2, 3]:
for bias in [True, False]:
# for dilation in [1, 2, 3]:
for dilation in [3,]:
for groups in [1, 3]:
# ValueError: strides > 1 not supported in conjunction with dilation_rate > 1
if stride > 1 and dilation > 1:
continue
model = LayerTest(
3, groups,
kernel_size=kernel_size, padding=padding,
stride=stride, bias=bias, dilation=dilation, groups=groups)
model.eval()
input_np = np.random.uniform(0, 1, (1, 3, 224, 224))
input_var = Variable(torch.FloatTensor(input_np))
torch.onnx.export(model, input_var, "_tmpnet.onnx", verbose=True, input_names=['test_in'], output_names=['test_out'])
onnx_model = onnx.load('_tmpnet.onnx')
k_model = onnx_to_keras(onnx_model, ['test_in'])
error = check_torch_keras_error(model, k_model, input_np, epsilon=1e-2)
print('Error:', error)
if max_error < error:
max_error = error
print('Max error: {0}'.format(max_error))
