!3795 remove old MINDSPORE_HCCL_CONFIG_PATH in model zoo 2

Merge pull request !3795 from panbingao/master

model_zoo/official/cv/maskrcnn/README.md

@@ -94,7 +94,7 @@ sh run_distribute_train.sh [RANK_TABLE_FILE] [PRETRAINED_MODEL]
 sh run_standalone_train.sh [PRETRAINED_MODEL]
 ```
  
-> hccl.json which is specified by MINDSPORE_HCCL_CONFIG_PATH is needed when you are running a distribute task. You can generate it by using the [hccl_tools](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/utils/hccl_tools).
+> hccl.json which is specified by RANK_TABLE_FILE is needed when you are running a distribute task. You can generate it by using the [hccl_tools](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/utils/hccl_tools).
 > As for PRETRAINED_MODEL，if not set, the model will be trained from the very beginning.Ready-made pretrained_models are not available now. Stay tuned.
 
 #### Result

model_zoo/official/cv/mobilenetv3/src/launch.py

@@ -139,7 +139,6 @@ def main():
         env['DEVICE_ID'] = str(device_id)
         if args.nproc_per_node > 1:
             env['RANK_TABLE_FILE'] = table_fn
-            env['RANK_TABLE_FILE'] = table_fn
         if os.path.exists(device_dir):
             shutil.rmtree(device_dir)
         os.mkdir(device_dir)

model_zoo/official/cv/resnet_thor/scripts/run_distribute_train.sh

@@ -22,7 +22,7 @@ fi
 
 if [ ! -f $1 ]
 then
-    echo "error: DRANK_TABLE_FILE=$1 is not a file"
+    echo "error: RANK_TABLE_FILE=$1 is not a file"
 exit 1
 fi
 

model_zoo/official/nlp/bert/README.md

@@ -21,7 +21,7 @@ This example implements pre-training, fine-tuning and evaluation of [BERT-base](
 - Run `run_distribute_pretrain.sh` for distributed pre-training of BERT-base and BERT-NEZHA model.
 
     ``` bash   
-    sh scripts/run_distribute_pretrain.sh DATA_DIR MINDSPORE_HCCL_CONFIG_PATH
+    sh scripts/run_distribute_pretrain.sh DATA_DIR RANK_TABLE_FILE
     ```  
 
 ### Fine-Tuning and Evaluation

model_zoo/official/nlp/bert/scripts/ascend_distributed_launcher/run_distribute_pretrain.py

@@ -62,7 +62,6 @@ def distribute_pretrain():
     cfg = dict(cf.items("config"))
 
     print("hccl_config_dir:", args.hccl_config_dir)
-    os.environ['MINDSPORE_HCCL_CONFIG_PATH'] = args.hccl_config_dir
     os.environ['RANK_TABLE_FILE'] = args.hccl_config_dir
 
     cores = multiprocessing.cpu_count()

model_zoo/official/nlp/bert/scripts/run_distribute_pretrain.sh

@@ -16,7 +16,7 @@
 
 echo "=============================================================================================================="
 echo "Please run the scipt as: "
-echo "bash run_distribute_pretrain.sh DATA_DIR MINDSPORE_HCCL_CONFIG_PATH"
+echo "bash run_distribute_pretrain.sh DATA_DIR RANK_TABLE_FILE"
 echo "for example: bash run_distribute_pretrain.sh /path/dataset /path/hccl.json"
 echo "It is better to use absolute path."
 echo "For hyper parameter, please note that you should customize the scripts:

model_zoo/official/nlp/tinybert/README.md

@@ -21,7 +21,7 @@
 - Run `run_distribute_gd.sh` for distributed general distill of BERT-base model.
 
     ``` bash
-    bash scripts/run_distribute_gd.sh DEVICE_NUM EPOCH_SIZE MINDSPORE_HCCL_CONFIG_PATH
+    bash scripts/run_distribute_gd.sh DEVICE_NUM EPOCH_SIZE RANK_TABLE_FILE
     ```  
 
 ### Task Distill

model_zoo/official/nlp/tinybert/scripts/run_distribute_gd.sh

@@ -16,7 +16,7 @@
 
 echo "=============================================================================================================="
 echo "Please run the scipt as: "
-echo "bash scripts/run_distribute_gd.sh DEVICE_NUM EPOCH_SIZE MINDSPORE_HCCL_CONFIG_PATH"
+echo "bash scripts/run_distribute_gd.sh DEVICE_NUM EPOCH_SIZE RANK_TABLE_FILE"
 echo "for example: bash scripts/run_distribute_gd.sh 8 40 /path/hccl.json"
 echo "It is better to use absolute path."
 echo "running....... please see details by LOG{}/log.txt"
@@ -25,7 +25,6 @@ echo "==========================================================================
 EPOCH_SIZE=$2
 
 PROJECT_DIR=$(cd "$(dirname "$0")" || exit; pwd)
-export MINDSPORE_HCCL_CONFIG_PATH=$3
 export RANK_TABLE_FILE=$3
 export RANK_SIZE=$1
 cores=`cat /proc/cpuinfo|grep "processor" |wc -l`

model_zoo/utils/ascend_distributed_launcher/run_distribute_pretrain.py

@@ -62,7 +62,6 @@ def distribute_pretrain():
     cfg = dict(cf.items("config"))
 
     print("hccl_config_dir:", args.hccl_config_dir)
-    os.environ['MINDSPORE_HCCL_CONFIG_PATH'] = args.hccl_config_dir
     os.environ['RANK_TABLE_FILE'] = args.hccl_config_dir
 
     cores = multiprocessing.cpu_count()