!9601 fix gnmtv2 doc issues

From: @zhaojichen
Reviewed-by: 
Signed-off-by:

model_zoo/official/nlp/gnmt_v2/README.md

@@ -39,7 +39,7 @@ Attention mechanism: uses the standardized Bahdanau attention mechanism. First,
 
 Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below.
 
-- WMT Englis-German for training.
+- WMT English-German for training.
 - WMT newstest2014 for evaluation.
 
 # [Environment Requirements](#contents)
@@ -178,7 +178,7 @@ Almost all required options and parameters can be easily assigned, including the
   'hidden_size': 1024        # the output's last dimension of dynamicRNN
   'initializer_range': 0.1  # initializer range
   'max_decode_length': 50  # max length of decoder
-  'lr': 2e-1                 # initial learning rate
+  'lr': 2e-3                 # initial learning rate
   'lr_scheduler': 'WarmupMultiStepLR'  # learning rate scheduler
   'existed_ckpt': ""        # the absolute full path to save the checkpoint file
   ```
@@ -242,7 +242,7 @@ The `VOCAB_ADDR` is the vocabulary address, `BPE_CODE_ADDR` is the bpe code addr
 | Resource                   | Ascend 910                                                     |
 | uploaded Date              | 11/06/2020 (month/day/year)                                    |
 | MindSpore Version          | 1.0.0                                                          |
-| Dataset                    | WMT Englis-German for training                                              |
+| Dataset                    | WMT English-German for training                                |
 | Training Parameters        | epoch=6, batch_size=128                                        |
 | Optimizer                  | Adam                                                           |
 | Loss Function              | Softmax Cross Entropy                                          |

model_zoo/official/nlp/gnmt_v2/config/config.json

@@ -4,7 +4,7 @@
     "epochs": 6,
     "batch_size": 128,
     "dataset_schema": "/home/workspace/dataset_menu/train.tok.clean.bpe.32000.en.json",
-    "pre_train_dataset": "/home/workspace/dataset_menu/train.tok.clean.bpe.32000.en.tfrecord-001-of-001",
+    "pre_train_dataset": "/home/workspace/dataset_menu/train.tok.clean.bpe.32000.en.mindrecord",
     "fine_tune_dataset": null,
     "valid_dataset": null,
     "dataset_sink_mode": true

model_zoo/official/nlp/gnmt_v2/config/config.py

@@ -93,7 +93,7 @@ class GNMTConfig:
         init_loss_scale (int): Initialized loss scale.
         loss_scale_factor (int): Loss scale factor.
         scale_window (int): Window size of loss scale.
-        lr_scheduler (str): Whether use lr_scheduler, only support "ISR" now.
+        lr_scheduler (str): Learning rate scheduler. Please see the Note as follow.
         optimizer (str): Optimizer for training, e.g. Adam, Lamb, momentum. Default: Adam.
         lr (float): Initial learning rate.
         min_lr (float): Minimum learning rate.

model_zoo/official/nlp/gnmt_v2/config/config_test.json

@@ -6,7 +6,7 @@
     "dataset_schema": "/home/workspace/dataset_menu/newstest2014.en.json",
     "pre_train_dataset": null,
     "fine_tune_dataset": null,
-    "test_dataset":  "/home/workspace/dataset_menu/newstest2014.en.tfrecord-001-of-001",
+    "test_dataset":  "/home/workspace/dataset_menu/newstest2014.en.mindrecord",
     "valid_dataset": null,
     "dataset_sink_mode": true
   },

model_zoo/official/nlp/gnmt_v2/scripts/run_distributed_train_ascend.sh

@@ -15,13 +15,13 @@
 # ============================================================================
 
 echo "=============================================================================================================="
-echo "Please run the scipt as: "
+echo "Please run the script as: "
 echo "sh run_distributed_train_ascend.sh RANK_TABLE_ADDR DATASET_SCHEMA_TRAIN PRE_TRAIN_DATASET"
 echo "for example:"
 echo "sh run_distributed_train_ascend.sh \
   /home/workspace/rank_table_8p.json \
   /home/workspace/dataset_menu/train.tok.clean.bpe.32000.en.json \
-  /home/workspace/dataset_menu/train.tok.clean.bpe.32000.en.tfrecord-001-of-001"
+  /home/workspace/dataset_menu/train.tok.clean.bpe.32000.en.mindrecord"
 echo "It is better to use absolute path."
 echo "=============================================================================================================="
 

model_zoo/official/nlp/gnmt_v2/scripts/run_standalone_eval_ascend.sh

@@ -15,13 +15,13 @@
 # ============================================================================
 
 echo "=============================================================================================================="
-echo "Please run the scipt as: "
+echo "Please run the script as: "
 echo "sh run_standalone_eval_ascend.sh DATASET_SCHEMA_TEST TEST_DATASET EXISTED_CKPT_PATH \
   VOCAB_ADDR BPE_CODE_ADDR TEST_TARGET"
 echo "for example:"
 echo "sh run_standalone_eval_ascend.sh \
   /home/workspace/dataset_menu/newstest2014.en.json \
-  /home/workspace/dataset_menu/newstest2014.en.tfrecord-001-of-001 \
+  /home/workspace/dataset_menu/newstest2014.en.mindrecord \
   /home/workspace/gnmt_v2/gnmt-6_3452.ckpt \
   /home/workspace/wmt16_de_en/vocab.bpe.32000 \
   /home/workspace/wmt16_de_en/bpe.32000 \
@@ -53,7 +53,7 @@ cp ../*.py ./eval
 cp -r ../src ./eval
 cp -r ../config ./eval
 cd ./eval || exit
-echo "start eval for device $DEVICE_ID"
+echo "start for evaluation"
 env > env.log
 python eval.py \
   --config=${current_exec_path}/eval/config/config_test.json \

model_zoo/official/nlp/gnmt_v2/scripts/run_standalone_train_ascend.sh

@@ -15,12 +15,12 @@
 # ============================================================================
 
 echo "=============================================================================================================="
-echo "Please run the scipt as: "
+echo "Please run the script as: "
 echo "sh run_standalone_train_ascend.sh DATASET_SCHEMA_TRAIN PRE_TRAIN_DATASET"
 echo "for example:"
 echo "sh run_standalone_train_ascend.sh \
   /home/workspace/dataset_menu/train.tok.clean.bpe.32000.en.json \
-  /home/workspace/dataset_menu/train.tok.clean.bpe.32000.en.tfrecord-001-of-001"
+  /home/workspace/dataset_menu/train.tok.clean.bpe.32000.en.mindrecord"
 echo "It is better to use absolute path."
 echo "=============================================================================================================="
 
@@ -42,10 +42,10 @@ cp ../*.py ./train
 cp -r ../src ./train
 cp -r ../config ./train
 cd ./train || exit
-echo "start training for device $DEVICE_ID"
+echo "start for training"
 env > env.log
 python train.py \
 	--config=${current_exec_path}/train/config/config.json \
 	--dataset_schema_train=$DATASET_SCHEMA_TRAIN \
-	--pre_train_dataset=$PRE_TRAIN_DATASET > log_gnmt_network${i}.log 2>&1 &
+	--pre_train_dataset=$PRE_TRAIN_DATASET > log_gnmt_network.log 2>&1 &
 cd ..

model_zoo/official/nlp/gnmt_v2/src/dataset/bi_data_loader.py

@@ -136,7 +136,7 @@ class BiLingualDataLoader(DataLoader):
                     columns = ["src", "src_padding", "prev_opt", "target", "tgt_padding"]
                     with open(self.schema_address, "w", encoding="utf-8") as  f:
                         f.write("{\n")
-                        f.write('  "datasetType":"TF",\n')
+                        f.write('  "datasetType":"MS",\n')
                         f.write('  "numRows":%s,\n' % provlist[0])
                         f.write('  "columns":{\n')
                         t = 1
@@ -211,7 +211,7 @@ class TextDataLoader(DataLoader):
                 columns = ["src", "src_padding"]
                 with open(self.schema_address, "w", encoding="utf-8") as  f:
                     f.write("{\n")
-                    f.write('  "datasetType":"TF",\n')
+                    f.write('  "datasetType":"MS",\n')
                     f.write('  "numRows":%s,\n' % provlist[0])
                     f.write('  "columns":{\n')
                     t = 1

model_zoo/official/nlp/gnmt_v2/src/utils/initializer.py

@@ -23,7 +23,7 @@ def _compute_fans(shape):
     Computes the number of input and output units for a weight shape.
 
     Args:
-        shape (tuple): Integer shape tuple or TF tensor shape.
+        shape (tuple): Integer shape tuple or MS tensor shape.
 
     Returns:
         tuple, integer scalars (fan_in, fan_out).