framework 48/2

importer_test.py

ValueError: Unsupported type <class 'tensorflow.python.framework.ops.Tensor'>.

x86也失败
file_system_test.py

tensorflow.python.framework.errors_impl.NotFoundError: test_file_system.so: cannot open shared object file: No such file or directory

x86也失败

training 56/2

evaluation_test.py

RuntimeError: Merging tf.summary.* ops is not compatible with eager execution. Use tf.contrib.summary instead.

x86也失败
checkpoint_utils_test.py

Traceback (most recent call last):
  File "checkpoint_utils_test.py", line 273, in testInitFromPartitionVar
    v1 = _create_partition_checkpoints(session, checkpoint_dir)
  File "checkpoint_utils_test.py", line 80, in _create_partition_checkpoints
    saver = saver_lib.Saver()
  File "/opt/python/python-3.7.9/lib/python3.7/site-packages/tensorflow/python/training/saver.py", line 813, in __init__
    "When eager execution is enabled, `var_list` must specify a list "
RuntimeError: When eager execution is enabled, `var_list` must specify a list or dict of variables to save

x86也失败

platform 10/2

test.py

tensorflow.python.util.tf_export.SymbolAlreadyExposedError: Symbol unittest.mock is already exposed as ().

x86也失败
stacktrace_handler_test.py

AssertionError: b'PyEval_EvalFrame' not found in b'Running tests under Python 3.7.9

x86 正常

eager 44/1

remote_cloud_tpu_test.py

    raise ValueError('Please provide a TPU Name to connect to.')
ValueError: Please provide a TPU Name to connect to.

x86也失败

keras 242/9

未修复

layers/normalization_test.py x86正常
distribute/keras_utils_test.py x86正常
mixed_precision/experimental/layer_correctness_test.py x86正常
integration_test/forwardprop_test.py x86正常

精度不对

distribute/collective_all_reduce_strategy_test.py

core 信息
    tensorflow::CurrentStackTrace()
    raise

x86也失败

applications/applications_load_weight_test.py

Traceback (most recent call last):
  File "applications/applications_load_weight_test.py", line 104, in test_application_pretrained_weights_loading
    app_module = ARG_TO_MODEL[FLAGS.module][0]
KeyError: None

x86也失败
layers/layers_test.py

Traceback (most recent call last):
  File "layers/layers_test.py", line 32, in test_keras_private_symbol
    self.assertEqual('normalization', normalization_parent)
AssertionError: 
- normalization
+ normalization_v1
?              +++

x86也失败
engine/training_test.py

  File "engine/training_test.py", line 3604, in test_no_tracing_between_epoch
    self.assertEqual(sum(new_func_graph in log for log in logs.output), 9)
AssertionError: 0 != 9

x86也失败
integration_test/tpu_strategy_test.py

    raise ValueError('Please provide a TPU Name to connect to.')
ValueError: Please provide a TPU Name to connect to.

x86也失败

已修复

keras/mixed_precision/experimental/keras_test.py

 import os
os.environ['TEST_SRCDIR']='/home/loongson/workspace/'

activations_test.py
preprocessing/image_test.py

缺少scipy包

data 162/1

experimental/kernel_tests/optimization/filter_with_random_uniform_fusion_test.py

tensorflow.python.framework.errors_impl.InternalError: Tried to register a dataset optimizer that doesn't exist: filter_with_random_uniform_fusion
     [[{{node OptimizeDatasetV2}}]]
     [[OneShotIterator]]

autograph 61/1

operators/exceptions_test.py

E1028 14:03:14.035942 1099111942288 test_util.py:1695] assertion failed: [test message]
     [[node Assert/Assert (defined at ./operators/exceptions_test.py:41) ]]

Errors may have originated from an input operation.
Input Source operations connected to node Assert/Assert:
 Const (defined at ./operators/exceptions_test.py:40)

kernel_tests 324/8

ackermann_test.py

tensorflow.python.framework.errors_impl.NotFoundError: ackermann_op.so: cannot open shared object file: No such file or directory

denormal_test.py

精度问题

reader_ops_test.py

FileNotFoundError: [Errno 2] No such file or directory: 'tensorflow/core/lib/lmdb/testdata/data.mdb'

decode_image_op_test.py

tensorflow.python.framework.errors_impl.NotFoundError: tensorflow/core/lib/png/testdata/lena_gray.png; No such file or directory [Op:ReadFile]

duplicate_op_test.py

tensorflow.python.framework.errors_impl.NotFoundError: duplicate_op.so: cannot open shared object file: No such file or directory

tensor_priority_test.py

AssertionError: Exception of type <class 'ValueError'>: Attempt to convert a value (<__main__.TensorPriorityTest.testUnsupportedRhsWithoutDelegation.<locals>.WithoutReverseAdd object at 0xffed85b3d0>) with an unsupported type (<class '__main__.TensorPriorityTest.testUnsupportedRhsWithoutDelegation.<locals>.WithoutReverseAdd'>) to a Tensor.

invalid_op_test.py

tensorflow.python.framework.errors_impl.NotFoundError: invalid_op.so: cannot open shared object file: No such file or directory

conv_ops_test.py

  File "/opt/python/python-3.7.9/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 1978, in __init__
    self._traceback = tf_stack.extract_stack()

已经修复

eig_op_test.py
self_adjoint_eig_op_test.py

import os
os.environ['TEST_SRCDIR']='/home/loongson/workspace/'

ops 113/5

nccl_ops_test.py

  File "nccl_ops_test.py", line 177, in testBroadcastToCpuError
    str(e), "No registered '_NcclBroadcastRecv' OpKernel for CPU devices")
AssertionError: Regex didn't match: "No registered '_NcclBroadcastRecv' OpKernel for CPU devices" not found in 'Could not find device for node: {{node NcclBroadcast}} = NcclBroadcast[T=DT_HALF, shape=[3,4]]\nAll kernels registered for op NcclBroadcast:\n  <no registered kernels>\n [Op:NcclBroadcast]'

parallel_for/array_test.py x86ok

     (OpKernel was found, but attributes didn't match) Requested Attributes: N=3, T=DT_FLOAT, Tidx=DT_INT64, _XlaHasReferenceVars=false, _kernel="MklLayoutDependentOp", _device="/job:localhost/replica:0/task:0/device:CPU:0"
    .  Registered:  device='CPU'; label='MklLayoutDependentOp'; T in [DT_BFLOAT16]; Tidx in [DT_INT32]
  device='CPU'; label='MklLayoutDependentOp'; T in [DT_FLOAT]; Tidx in [DT_INT32]

nn_fused_batchnorm_test.py x86ok

  File "/opt/python/python-3.7.9/lib/python3.7/site-packages/tensorflow/python/framework/test_util.py", line 1312, in decorated
    return f(self, *args, **kwargs)
  File "nn_fused_batchnorm_test.py", line 524, in testBatchNormGradTrainingShape4
    self._runtests(x_shape, is_training=True, gradient_test=True)
  File "nn_fused_batchnorm_test.py", line 401, in _runtests
    exponential_avg_factor=exponential_avg_factor)
  File "nn_fused_batchnorm_test.py", line 270, in _test_gradient
    self.assertLess(err_x, x_err_tolerance)
AssertionError: 78.420975 not less than 0.002

image_ops_test.py

    jpeg0 = io_ops.read_file(os.path.join(base, "jpeg_merge_test1.jpg"))
  File "/opt/python/python-3.7.9/lib/python3.7/site-packages/tensorflow/python/ops/gen_io_ops.py", line 576, in read_file
    "ReadFile", filename=filename, name=name)
  File "/opt/python/python-3.7.9/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py", line 777, in _apply_op_helper
    attrs=attr_protos, op_def=op_def)
  File "/opt/python/python-3.7.9/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 3520, in _create_op_internal
    op_def=op_def)
  File "/opt/python/python-3.7.9/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 1978, in __init__
    self._traceback = tf_stack.extract_stack()

control_flow_v2_disable_test.py

Traceback (most recent call last):
  File "control_flow_v2_disable_test.py", line 35, in testIsDisabled
    self.assertFalse(control_flow_util.ENABLE_CONTROL_FLOW_V2)
AssertionError: True is not false

tensorflow-eigenCpp-oneDNN-test

tensorflow-eigenCpp-oneDNN-test

framework 48/2

training 56/2

platform 10/2

eager 44/1

keras 242/9

未修复

已修复

data 162/1

autograph 61/1

kernel_tests 324/8

已经修复

ops 113/5