[New Sample] Add NLP samples, incluing rocketqa, ure, utc models. (#260)

* Add rocketqa models.

* Update graph_hash.

* Remove redundant samples.

* Optimize check_redundant_incrementally.py.

* Add uer samples.

* Add utc samples.

* Fix path.

Author: Xreki

.github/workflows/Validate-GPU.yml

@@ -61,7 +61,7 @@ jobs:
             -v "/home/data/cfs/.ccache:/root/.ccache" \
             -v "/dev/shm:/dev/shm" \
             -v ${{ github.workspace }}/../../..:${{ github.workspace }}/../../.. \
-            -v ${{ github.workspace }}:/graphnet \
+            -v ${{ github.workspace }}:${{ github.workspace }} \
             -e python \
             -e core_index \
             -e BRANCH \
@@ -73,7 +73,7 @@ jobs:
             -e CACHE_DIR \
             -e GITHUB_API_TOKEN \
             -e CFS_DIR \
-            -w /graphnet --network host ${docker_image}
+            -w ${{ github.workspace }} --network host ${docker_image}
 
       - name: Run check
         env:

graph_net/paddle/check_redundant_incrementally.py

@@ -46,11 +46,26 @@ def main(args):
     assert os.path.isdir(
         args.graph_net_samples_path
     ), f"args.graph_net_samples_path ({args.graph_net_samples_path}) is not a directory!"
+
+    current_model_graph_hash_pathes = set()
+    if args.model_path:
+        assert os.path.isdir(
+            args.model_path
+        ), f"args.model_path {args.model_path} is not a directory!"
+        current_model_graph_hash_pathes = set(
+            graph_hash_path
+            for model_path in get_recursively_model_pathes(args.model_path)
+            for graph_hash_path in [f"{model_path}/graph_hash.txt"]
+        )
+
     find_redundant = False
     graph_hash2graph_net_model_path = {}
     for model_path in get_recursively_model_pathes(args.graph_net_samples_path):
         graph_hash_path = f"{model_path}/graph_hash.txt"
-        if os.path.isfile(graph_hash_path):
+        if (
+            os.path.isfile(graph_hash_path)
+            and graph_hash_path not in current_model_graph_hash_pathes
+        ):
             graph_hash = open(graph_hash_path).read()
             if graph_hash not in graph_hash2graph_net_model_path.keys():
                 graph_hash2graph_net_model_path[graph_hash] = [graph_hash_path]
@@ -60,29 +75,24 @@ def main(args):
     print(
         f"Totally {len(graph_hash2graph_net_model_path)} unique samples under {args.graph_net_samples_path}."
     )
-    for graph_hash, graph_paths in graph_hash2graph_net_model_path.items():
-        if len(graph_paths) > 1:
-            print(f"Redundant models detected for grap_hash {graph_hash}:")
-            for model_path in graph_paths:
-                print(f"    {model_path}")
-    assert (
-        not find_redundant
-    ), f"Redundant models detected under {args.graph_net_samples_path}."
 
     if args.model_path:
-        assert os.path.isdir(
-            args.model_path
-        ), f"args.model_path {args.model_path} is not a directory!"
-        current_model_graph_hash_pathes = set(
-            graph_hash_path
-            for model_path in get_recursively_model_pathes(args.model_path)
-            for graph_hash_path in [f"{model_path}/graph_hash.txt"]
-        )
+        # Check whether the specified model is redundant.
         for current_model_graph_hash_path in current_model_graph_hash_pathes:
             graph_hash = open(current_model_graph_hash_path).read()
             assert (
                 graph_hash not in graph_hash2graph_net_model_path
-            ), f"Redundant models detected. old-model-path:{current_model_graph_hash_path}, new-model-path:{graph_hash2graph_net_model_path[graph_hash]}."
+            ), f"Redundant models detected.\n\tgraph_hash:{graph_hash}, newly-added-model-path:{current_model_graph_hash_path}, existing-model-path:{graph_hash2graph_net_model_path[graph_hash]}."
+    else:
+        # Check whether there are redundant samples under samples directory.
+        for graph_hash, graph_paths in graph_hash2graph_net_model_path.items():
+            if len(graph_paths) > 1:
+                print(f"Redundant models detected for grap_hash {graph_hash}:")
+                for model_path in graph_paths:
+                    print(f"    {model_path}")
+        assert (
+            not find_redundant
+        ), f"Redundant models detected under {args.graph_net_samples_path}."
 
 
 if __name__ == "__main__":

graph_net/paddle/samples_util.py

@@ -3,4 +3,5 @@
 
 
 def get_default_samples_directory():
-    return f"{os.path.dirname(graph_net.__file__)}/../paddle_samples"
+    graph_net_root = os.path.dirname(os.path.dirname(graph_net.__file__))
+    return f"{graph_net_root}/paddle_samples"

paddle_samples/PaddleNLP/rocketqa-base-cross-encoder/graph_hash.txt

@@ -0,0 +1 @@
+62cc3d05adaf6e4219e2b653fec24cce7290406e2f80064a1e914ebc82570775

paddle_samples/PaddleNLP/ernie-search-base-dual-encoder-marco-en/graph_net.json renamed to paddle_samples/PaddleNLP/rocketqa-base-cross-encoder/graph_net.json

@@ -1,6 +1,6 @@
 {
     "framework": "paddle",
-    "model_name": "ernie-search-base-dual-encoder-marco-en",
+    "model_name": "rocketqa-base-cross-encoder",
     "num_devices_required": 1,
     "num_nodes_required": 1
 }

paddle_samples/PaddleNLP/rocketqa-base-cross-encoder/input_meta.py

@@ -0,0 +1,34 @@
+class Program_weight_tensor_data_0:
+    name = "data_0"
+    shape = [1, 21]
+    dtype = "int64"
+    data = [
+        1,
+        6368,
+        30,
+        3441,
+        5254,
+        2775,
+        7208,
+        42,
+        1675,
+        6433,
+        7946,
+        4640,
+        31618,
+        7476,
+        34874,
+        1662,
+        4968,
+        36810,
+        9478,
+        42,
+        2,
+    ]
+
+
+class Program_weight_tensor_data_1:
+    name = "data_1"
+    shape = [1, 21]
+    dtype = "int64"
+    data = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]