Adnios opened a new issue #20371: URL: https://github.com/apache/incubator-mxnet/issues/20371
## Description - When the input's `shape=()`, the backward log_sigmoid activation is incorrect - There is an error when run the log_sigmoid in gpu. ### Error Message And To Reproduce ``` git clone --recursive https://github.com/apache/incubator-mxnet rm -rf build mkdir -p build && cd build cmake -GNinja \ -DUSE_CUDA=OFF \ -DUSE_MKL_IF_AVAILABLE=ON \ -DCMAKE_CUDA_COMPILER_LAUNCHER=ccache \ -DCMAKE_C_COMPILER_LAUNCHER=ccache \ -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \ -DCMAKE_BUILD_TYPE=Release \ .. ninja ``` Use the following code to test. Reference: https://github.com/apache/incubator-mxnet/blob/master/tests/python/unittest/test_numpy_op.py ``` import numpy as _np import mxnet as mx from mxnet import np, npx from mxnet.gluon import HybridBlock from mxnet.base import MXNetError from mxnet.test_utils import same, assert_almost_equal, rand_shape_nd, rand_ndarray from mxnet.test_utils import check_numeric_gradient, use_np, collapse_sum_like, effective_dtype @use_np def test_activation(): def np_log_sigmoid(a): return _np.log(_np.divide(1.0, _np.add(1.0, _np.exp(-a)))) def np_log_sigmoid_grad(a): return _np.divide(1.0, _np.add(1.0, _np.exp(a))) class TestLogSigmoid(HybridBlock): def __init__(self): super(TestLogSigmoid, self).__init__() def hybrid_forward(self, F, a): return F.npx.activation(a, act_type='log_sigmoid') shape = () # shape = (1,) test_log_sigmoid = TestLogSigmoid() x = mx.np.random.uniform(low=-1.0, high=1.0, size=shape) x.attach_grad() np_out = np_log_sigmoid(x.asnumpy()) with mx.autograd.record(): mx_out = test_log_sigmoid(x) assert mx_out.shape == np_out.shape assert_almost_equal(mx_out.asnumpy(), np_out, rtol=1e-3, atol=1e-5) mx_out.backward() np_backward = np_log_sigmoid_grad(x.asnumpy()) print(np_backward) print(x.grad.asnumpy()) assert_almost_equal(x.grad.asnumpy(), np_backward, rtol=1e-3, atol=1e-5) mx_out = npx.activation(x, act_type='log_sigmoid') np_out = np_log_sigmoid(x.asnumpy()) assert_almost_equal(mx_out.asnumpy(), np_out, rtol=1e-3, atol=1e-5) @use_np def test_activation_gpu(): def np_log_sigmoid(a): return _np.log(_np.divide(1.0, _np.add(1.0, _np.exp(-a)))) def np_log_sigmoid_grad(a): return _np.divide(1.0, _np.add(1.0, _np.exp(a))) class TestLogSigmoid(HybridBlock): def __init__(self): super(TestLogSigmoid, self).__init__() def hybrid_forward(self, F, a): return F.npx.activation(a, act_type='log_sigmoid') # shape = () shape = (1,) test_log_sigmoid = TestLogSigmoid() x = mx.np.random.uniform(low=-1.0, high=1.0, size=shape, ctx=mx.gpu()) x.attach_grad() np_out = np_log_sigmoid(x.asnumpy()) with mx.autograd.record(): mx_out = test_log_sigmoid(x) assert mx_out.shape == np_out.shape assert_almost_equal(mx_out.asnumpy(), np_out, rtol=1e-3, atol=1e-5) mx_out.backward() np_backward = np_log_sigmoid_grad(x.asnumpy()) print(np_backward) print(x.grad.asnumpy()) assert_almost_equal(x.grad.asnumpy(), np_backward, rtol=1e-3, atol=1e-5) mx_out = npx.activation(x, act_type='log_sigmoid') np_out = np_log_sigmoid(x.asnumpy()) assert_almost_equal(mx_out.asnumpy(), np_out, rtol=1e-3, atol=1e-5) ``` When run `test_activation()`, the error message is: ``` Traceback (most recent call last): File "log_sigmoid_backward_bug.py", line 191, in <module> test_activation() File "/home/lthpc/anaconda3/lib/python3.6/site-packages/mxnet/util.py", line 299, in _with_np_shape return func(*args, **kwargs) File "/home/lthpc/anaconda3/lib/python3.6/site-packages/mxnet/util.py", line 480, in _with_np_array return func(*args, **kwargs) File "log_sigmoid_backward_bug.py", line 62, in test_activation assert_almost_equal(x.grad.asnumpy(), np_backward, rtol=1e-3, atol=1e-5) File "/home/lthpc/anaconda3/lib/python3.6/site-packages/mxnet/test_utils.py", line 740, in assert_almost_equal raise AssertionError(msg) AssertionError: Items are not equal: Error 371.466237 exceeds tolerance rtol=1.000000e-03, atol=1.000000e-05. ACTUAL: array(0.65600127, dtype=float32) DESIRED: 0.47561258889520563 ``` But it can success when the `shape=(1,)` running on CPU. When run `test_activation_gpu()`, the error message is: ``` [19:24:54] ../src/base.cc:80: cuDNN lib mismatch: linked-against version 8005 != compiled-against version 8004. Set MXNET_CUDNN_LIB_CHECKING=0 to quiet this warning. [19:24:57] ../src/storage/storage.cc:199: Using Pooled (Naive) StorageManager for GPU Traceback (most recent call last): File "log_sigmoid_backward_bug.py", line 153, in <module> test_activation_gpu() File "/home/lthpc/anaconda3/lib/python3.6/site-packages/mxnet/util.py", line 299, in _with_np_shape return func(*args, **kwargs) File "/home/lthpc/anaconda3/lib/python3.6/site-packages/mxnet/util.py", line 480, in _with_np_array return func(*args, **kwargs) File "log_sigmoid_backward_bug.py", line 65, in test_activation_gpu assert_almost_equal(mx_out.asnumpy(), np_out, rtol=1e-3, atol=1e-5) File "/home/lthpc/anaconda3/lib/python3.6/site-packages/mxnet/ndarray/ndarray.py", line 2626, in asnumpy ctypes.c_size_t(data.size))) File "/home/lthpc/anaconda3/lib/python3.6/site-packages/mxnet/base.py", line 246, in check_call raise get_last_ffi_error() mxnet.base.MXNetError: Traceback (most recent call last): File "../src/operator/nn/./cudnn/cudnn_activation-inl.h", line 61 MXNetError: Not implmented ``` -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@mxnet.apache.org For additional commands, e-mail: issues-h...@mxnet.apache.org
