[Eager] Add hierarchical_sigmoid yaml (#44638)

paddle/phi/api/yaml/generator/api_base.py

@@ -135,7 +135,7 @@ class BaseAPI(object):
             'double': 'double',
             'bool': 'bool',
             'str': 'const std::string&',
-            'str[] ': 'const std::vector<std::string>&',
+            'str[]': 'const std::vector<std::string>&',
             'Place': 'const Place&',
             'DataLayout': 'DataLayout',
             'DataType': 'DataType',

paddle/phi/api/yaml/legacy_api.yaml

@@ -1038,6 +1038,18 @@
     func : hard_swish
   backward : hard_swish_grad
 
+# hierarchical_sigmoid
+- api : hierarchical_sigmoid
+  args : (Tensor x, Tensor w, Tensor label, Tensor path, Tensor code, Tensor bias, int num_classes, bool remote_prefetch, int trainer_id, int64_t[] height_sections, str[] epmap, str[] table_names, bool is_sparse)
+  output : Tensor(out), Tensor(pre_out), Tensor(w_out)
+  infer_meta :
+    func : HierarchicalSigmoidInferMeta
+  optional: path, code, bias
+  kernel :
+    func : hierarchical_sigmoid
+    data_type : x
+  backward : hierarchical_sigmoid_grad
+
 # histogram
 - api : histogram
   args : (Tensor x, int64_t bins, int min, int max)

paddle/phi/api/yaml/legacy_backward.yaml

@@ -935,6 +935,17 @@
     func : hard_swish_grad
   inplace : (out_grad -> x_grad)
 
+- backward_api : hierarchical_sigmoid_grad
+  forward : hierarchical_sigmoid (Tensor x, Tensor w, Tensor label, Tensor path, Tensor code, Tensor bias, int num_classes, bool remote_prefetch, int trainer_id, int64_t[] height_sections, str[] epmap, str[] table_names, bool is_sparse) -> Tensor(out), Tensor(pre_out), Tensor(w_out)
+  args : (Tensor x, Tensor w, Tensor label, Tensor path, Tensor code, Tensor bias, Tensor pre_out, Tensor out_grad, int num_classes, bool remote_prefetch, int trainer_id, int64_t[] height_sections, str[] epmap, str[] table_names, bool is_sparse)
+  output : Tensor(x_grad), Tensor(w_grad), Tensor(bias_grad)
+  infer_meta :
+    func : GeneralTernaryGradInferMeta
+    param : [x ,w, bias]
+  optional: path, code, bias
+  kernel :
+    func : hierarchical_sigmoid_grad
+
 - backward_api : huber_loss_grad
   forward : huber_loss (Tensor input, Tensor label, float delta) -> Tensor(out), Tensor(residual)
   args : (Tensor residual, Tensor out_grad, float delta)
@@ -2396,7 +2407,7 @@
   backward : unsqueeze_double_grad
 
 - backward_api : warpctc_grad
-  forward : warpctc (Tensor logits, Tensor label, Tensor logits_length, Tensor labels_length, int blank, bool norm_by_times) -> Tensor(loss), Tensor(warpctcgrad) 
+  forward : warpctc (Tensor logits, Tensor label, Tensor logits_length, Tensor labels_length, int blank, bool norm_by_times) -> Tensor(loss), Tensor(warpctcgrad)
   args : (Tensor logits, Tensor logits_length, Tensor warpctcgrad, Tensor loss_grad, int blank, bool norm_by_times)
   output : Tensor(logits_grad)
   infer_meta :

python/paddle/fluid/tests/unittests/test_hsigmoid_op.py

@@ -172,10 +172,30 @@ def hsigmoidWithCustomTree(x, w, path_table, path_code, label, bias,
     return pre_output, out
 
 
+def python_api(input,
+               weight,
+               label,
+               path_table=None,
+               path_code=None,
+               bias=None,
+               num_classes=-1,
+               is_sparse=False,
+               remote_prefetch=False):
+    assert is_sparse == remote_prefetch, "is_sparse is equal to remote_prefetch in dygraph."
+    return paddle.nn.functional.hsigmoid_loss(input, label, num_classes, weight,
+                                              bias, path_table, path_code,
+                                              is_sparse)
+
+
+python_out_sig = ["Out"]
+
+
 class TestHSigmoidOp(OpTest):
 
     def setUp(self):
         self.op_type = "hierarchical_sigmoid"
+        self.python_api = python_api
+        self.python_out_sig = python_out_sig
         num_classes = 101
         feature_size = 5
         batch_size = 20
@@ -193,11 +213,12 @@ class TestHSigmoidOp(OpTest):
         self.user_grads = hsigmoid_grad(x, w, label, bias, num_classes)
 
     def test_check_output(self):
-        self.check_output()
+        self.check_output(check_eager=True)
 
     def test_check_grad(self):
         self.check_grad(['X', 'W', 'Bias'], ['Out'],
-                        user_defined_grads=self.user_grads)
+                        user_defined_grads=self.user_grads,
+                        check_eager=True)
 
 
 @skip_check_grad_ci(
@@ -208,6 +229,8 @@ class TestHSigmoidOpSparse(OpTest):
 
     def setUp(self):
         self.op_type = "hierarchical_sigmoid"
+        self.python_api = python_api
+        self.python_out_sig = python_out_sig
         num_classes = 6  #using 1,2,3,4,5,6 to build a huffman tree and select 1,2,5,6 as sample
         feature_size = 8
         batch_size = 4
@@ -237,7 +260,7 @@ class TestHSigmoidOpSparse(OpTest):
         self.outputs = {'PreOut': pre_output, 'Out': out}
 
     def test_check_output(self):
-        self.check_output()
+        self.check_output(check_eager=True)
 
 
 class TestHSigmoidOpWithSparseGrad(unittest.TestCase):
@@ -318,6 +341,8 @@ class TestHSigmoidOpWithCostumTree(OpTest):
 
     def setUp(self):
         self.op_type = "hierarchical_sigmoid"
+        self.python_api = python_api
+        self.python_out_sig = python_out_sig
         num_classes = 6  #using 1,2,3,4,5,6 to build a huffman tree and select 1,2,5,6 as sample
         feature_size = 8
         batch_size = 4
@@ -347,10 +372,12 @@ class TestHSigmoidOpWithCostumTree(OpTest):
         self.outputs = {'PreOut': pre_output, 'Out': out}
 
     def test_check_output(self):
-        self.check_output()
+        self.check_output(check_eager=True)
 
     def test_check_grad(self):
-        self.check_grad(['Bias', 'X', 'W'], ['Out'], no_grad_set=set('Label'))
+        self.check_grad(['Bias', 'X', 'W'], ['Out'],
+                        no_grad_set=set('Label'),
+                        check_eager=True)
 
 
 @skip_check_grad_ci(
@@ -361,6 +388,8 @@ class TestHSigmoidOpWithCostumTreeWithoutBias(OpTest):
 
     def setUp(self):
         self.op_type = "hierarchical_sigmoid"
+        self.python_api = python_api
+        self.python_out_sig = python_out_sig
         num_classes = 6  #using 1,2,3,4,5,6 to build a huffman tree and select 1,2,5,6 as sample
         feature_size = 8
         batch_size = 4
@@ -394,10 +423,12 @@ class TestHSigmoidOpWithCostumTreeWithoutBias(OpTest):
         self.outputs = {'PreOut': pre_output, 'Out': out}
 
     def test_check_output(self):
-        self.check_output()
+        self.check_output(check_eager=True)
 
     def test_check_grad(self):
-        self.check_grad(['X', 'W'], ['Out'], no_grad_set=set('Label'))
+        self.check_grad(['X', 'W'], ['Out'],
+                        no_grad_set=set('Label'),
+                        check_eager=True)
 
 
 class TestHSigmoidLossAPI(unittest.TestCase):

python/paddle/nn/functional/loss.py

@@ -920,7 +920,11 @@ def hsigmoid_loss(input,
             #  [2.11009121]
             #  [1.92374969]]
     """
-
+    if in_dygraph_mode():
+        out, _, _ = _C_ops.final_state_hierarchical_sigmoid(
+            input, weight, label, path_table, path_code, bias, num_classes,
+            is_sparse, 0, [], [], [], is_sparse)
+        return out
     if _non_static_mode():
         out, _, _ = _C_ops.hierarchical_sigmoid(input, weight, label,
                                                 path_table, path_code, bias,