modify config name (#544)

Author: Songyuanwei

configs/coat/README.md

@@ -14,8 +14,8 @@ Our reproduced model performance on ImageNet-1K is reported as follows.
 
 | Model           | Context   |  Top-1 (%)  |  Top-5 (%)  | Params (M) | Recipe                                                                                   | Weight                                                                            |
 |-----------------|-----------|-------|------------|------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------|----------------------------------------------------------------------------------|
-| coat_lite_tiny | D910x8-G | 77.35 | 93.43 | 5.72      | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/coat/coat_lite_tiny.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/coat/coat_lite_tiny_fa7bf894.ckpt) |
-| coat_lite_mini | D910x8-G | 78.51 | 93.84 | 11.01 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/coat/coat_lite_mini.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/coat/coat_lite_mini_55a52f05.ckpt) |
+| coat_lite_tiny | D910x8-G | 77.35 | 93.43 | 5.72      | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/coat/coat_lite_tiny_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/coat/coat_lite_tiny_fa7bf894.ckpt) |
+| coat_lite_mini | D910x8-G | 78.51 | 93.84 | 11.01 | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/coat/coat_lite_mini_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/coat/coat_lite_mini_55a52f05.ckpt) |
 
 </div>
 
@@ -42,7 +42,7 @@ It is easy to reproduce the reported results with the pre-defined training recip
 
 ```shell
 # distributed training on multiple GPU/Ascend devices
-mpirun -n 8 python train.py --config configs/coat/coat_lite_tiny.yaml --data_dir /path/to/imagenet
+mpirun -n 8 python train.py --config configs/coat/coat_lite_tiny_ascend.yaml --data_dir /path/to/imagenet
 ```
 
 > If the script is executed by the root user, the `--allow-run-as-root` parameter must be added to `mpirun`
@@ -59,15 +59,15 @@ If you want to train or finetune the model on a smaller dataset without distribu
 
 ```shell
 # standalone training on a CPU/GPU/Ascend device
-python train.py --config configs/coat/coat_lite_tiny.yaml --data_dir /path/to/dataset --distribute False
+python train.py --config configs/coat/coat_lite_tiny_ascend.yaml --data_dir /path/to/dataset --distribute False
 ```
 
 ### Validation
 
 To validate the accuracy of the trained model, you can use `validate.py` and parse the checkpoint path with `--ckpt_path`.
 
 ```shell
-python validate.py -c configs/coat/coat_lite_tiny.yaml --data_dir /path/to/imagenet --ckpt_path /path/to/ckpt
+python validate.py -c configs/coat/coat_lite_tiny_ascend.yaml --data_dir /path/to/imagenet --ckpt_path /path/to/ckpt
 ```
 
 ### Deployment

configs/coat/coat_lite_mini.yaml configs/coat/coat_lite_mini_ascend.yaml

@@ -14,11 +14,11 @@ Our reproduced model performance on ImageNet-1K is reported as follows.
 
 | Model           | Context   |  Top-1 (%)  | Top-5 (%)  | Params (M) | Recipe                                                                                   | Download                                                                         |
 |-----------------|-----------|-------|-------|------------|------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------|
-| rexnet_x09 | D910x8-G | 77.07 | 93.41    | 4.13       | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/rexnet/rexnet_x09.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/rexnet/rexnet0.9_acc77.07_bs64_8p.ckpt) |
-| rexnet_x10 | D910x8-G | 77.38 | 93.60    | 4.84       | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/rexnet/rexnet_x10.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/rexnet/rexnet1.0_acc77.4_bs64_8p.ckpt)   |
-| rexnet_x13 | D910x8-G | 79.06 | 94.28 | 7.61       | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/rexnet/rexnet_x13.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/rexnet/rexnet1.3_acc79.06_bs64_8p.ckpt)   |
-| rexnet_x15 | D910x8-G | 79.94 | 94.74  | 9.79       | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/rexnet/rexnet_x15.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/rexnet/rexnet1.5_acc79.94_bs64_8p.ckpt)   |
-| rexnet_x20 | D910x8-G | 80.6 | 94.99  | 16.45      | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/rexnet/rexnet_x20.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/rexnet/rexnet2.0_acc80.6_bs64_8p.ckpt)   |
+| rexnet_x09 | D910x8-G | 77.07 | 93.41    | 4.13       | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/rexnet/rexnet_x09_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/rexnet/rexnet0.9_acc77.07_bs64_8p.ckpt) |
+| rexnet_x10 | D910x8-G | 77.38 | 93.60    | 4.84       | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/rexnet/rexnet_x10_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/rexnet/rexnet1.0_acc77.4_bs64_8p.ckpt)   |
+| rexnet_x13 | D910x8-G | 79.06 | 94.28 | 7.61       | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/rexnet/rexnet_x13_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/rexnet/rexnet1.3_acc79.06_bs64_8p.ckpt)   |
+| rexnet_x15 | D910x8-G | 79.94 | 94.74  | 9.79       | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/rexnet/rexnet_x15_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/rexnet/rexnet1.5_acc79.94_bs64_8p.ckpt)   |
+| rexnet_x20 | D910x8-G | 80.64 | 94.99  | 16.45      | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/rexnet/rexnet_x20_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/rexnet/rexnet2.0_acc80.6_bs64_8p.ckpt)   |
 
 </div>
 
@@ -45,7 +45,7 @@ It is easy to reproduce the reported results with the pre-defined training recip
 
 ```shell
 # distributed training on multiple GPU/Ascend devices
-mpirun -n 8 python train.py --config configs/rexnet/rexnet_x09.yaml --data_dir /path/to/imagenet
+mpirun -n 8 python train.py --config configs/rexnet/rexnet_x09_ascend.yaml --data_dir /path/to/imagenet
 ```
 
 > If the script is executed by the root user, the `--allow-run-as-root` parameter must be added to `mpirun`.
@@ -62,15 +62,15 @@ If you want to train or finetune the model on a smaller dataset without distribu
 
 ```shell
 # standalone training on a CPU/GPU/Ascend device
-python train.py --config configs/rexnet/rexnet_x09.yaml --data_dir /path/to/dataset --distribute False
+python train.py --config configs/rexnet/rexnet_x09_ascend.yaml --data_dir /path/to/dataset --distribute False
 ```
 
 ### Validation
 
 To validate the accuracy of the trained model, you can use `validate.py` and parse the checkpoint path with `--ckpt_path`.
 
 ```shell
-python validate.py -c configs/rexnet/rexnet_x09.yaml --data_dir /path/to/imagenet --ckpt_path /path/to/ckpt
+python validate.py -c configs/rexnet/rexnet_x09_ascend.yaml --data_dir /path/to/imagenet --ckpt_path /path/to/ckpt
 ```
 
 ### Deployment

configs/coat/coat_lite_tiny.yaml configs/coat/coat_lite_tiny_ascend.yaml

@@ -2,11 +2,11 @@
 mode: 0
 distribute: True
 num_parallel_workers: 16
-device_target: "Ascend"
+val_while_train: True
+val_interval: 1
 
 # dataset
 dataset: "imagenet"
-data_url: "/cache/data"
 data_dir: "/path/to/imagenet"
 shuffle: True
 dataset_download: False
@@ -27,9 +27,6 @@ ckpt_path: ""
 keep_checkpoint_max: 10
 ckpt_save_dir: "./ckpt"
 ckpt_save_policy: "top_k"
-val_split: "val"
-val_while_train: True
-val_interval: 1
 epoch_size: 400
 dataset_sink_mode: True
 amp_level: "O2"
@@ -40,7 +37,7 @@ loss: "CE"
 label_smoothing: 0.1
 
 # lr scheduler
-scheduler: "warmup_cosine_decay"
+scheduler: "cosine_decay"
 min_lr: 1.0e-6
 lr: 0.5
 warmup_epochs: 5

configs/mixnet/README.MD configs/mixnet/README.md

@@ -2,11 +2,11 @@
 mode: 0
 distribute: True
 num_parallel_workers: 16
-device_target: "Ascend"
+val_while_train: True
+val_interval: 1
 
 # dataset
 dataset: "imagenet"
-data_url: "/cache/data"
 data_dir: "/path/to/imagenet"
 shuffle: True
 dataset_download: False
@@ -27,9 +27,6 @@ ckpt_path: ""
 keep_checkpoint_max: 10
 ckpt_save_dir: "./ckpt"
 ckpt_save_policy: "top_k"
-val_split: "val"
-val_while_train: True
-val_interval: 1
 epoch_size: 400
 dataset_sink_mode: True
 amp_level: "O2"
@@ -40,7 +37,7 @@ loss: "CE"
 label_smoothing: 0.1
 
 # lr scheduler
-scheduler: "warmup_cosine_decay"
+scheduler: "cosine_decay"
 min_lr: 1.0e-6
 lr: 0.5
 warmup_epochs: 5

configs/rexnet/README.md

@@ -2,11 +2,11 @@
 mode: 0
 distribute: True
 num_parallel_workers: 16
-device_target: "Ascend"
+val_while_train: True
+val_interval: 1
 
 # dataset
 dataset: "imagenet"
-data_url: "/cache/data"
 data_dir: "/path/to/imagenet"
 shuffle: True
 dataset_download: False
@@ -27,9 +27,6 @@ ckpt_path: ""
 keep_checkpoint_max: 10
 ckpt_save_dir: "./ckpt"
 ckpt_save_policy: "top_k"
-val_split: "val"
-val_while_train: True
-val_interval: 1
 epoch_size: 400
 dataset_sink_mode: True
 amp_level: "O2"
@@ -40,7 +37,7 @@ loss: "CE"
 label_smoothing: 0.1
 
 # lr scheduler
-scheduler: "warmup_cosine_decay"
+scheduler: "cosine_decay"
 min_lr: 1.0e-6
 lr: 0.5
 warmup_epochs: 5

configs/rexnet/rexnet_x09.yaml configs/rexnet/rexnet_x09_ascend.yaml

@@ -2,11 +2,11 @@
 mode: 0
 distribute: True
 num_parallel_workers: 16
-device_target: "Ascend"
+val_while_train: True
+val_interval: 1
 
 # dataset
 dataset: "imagenet"
-data_url: "/cache/data"
 data_dir: "/path/to/imagenet"
 shuffle: True
 dataset_download: False
@@ -27,9 +27,6 @@ ckpt_path: ""
 keep_checkpoint_max: 10
 ckpt_save_dir: "./ckpt"
 ckpt_save_policy: "top_k"
-val_split: "val"
-val_while_train: True
-val_interval: 1
 epoch_size: 400
 dataset_sink_mode: True
 amp_level: "O2"
@@ -41,7 +38,7 @@ loss: "CE"
 label_smoothing: 0.1
 
 # lr scheduler
-scheduler: "warmup_cosine_decay"
+scheduler: "cosine_decay"
 min_lr: 1.0e-6
 lr: 0.5
 warmup_epochs: 30

configs/rexnet/rexnet_x10.yaml configs/rexnet/rexnet_x10_ascend.yaml

@@ -2,11 +2,11 @@
 mode: 0
 distribute: True
 num_parallel_workers: 16
-device_target: "Ascend"
+val_while_train: True
+val_interval: 1
 
 # dataset
 dataset: "imagenet"
-data_url: "/cache/data"
 data_dir: "/path/to/imagenet"
 shuffle: True
 dataset_download: False
@@ -27,9 +27,6 @@ ckpt_path: ""
 keep_checkpoint_max: 10
 ckpt_save_dir: "./ckpt"
 ckpt_save_policy: "top_k"
-val_split: "val"
-val_while_train: True
-val_interval: 1
 epoch_size: 400
 dataset_sink_mode: True
 amp_level: "O2"
@@ -41,7 +38,7 @@ loss: "CE"
 label_smoothing: 0.1
 
 # lr scheduler
-scheduler: "warmup_cosine_decay"
+scheduler: "cosine_decay"
 min_lr: 1.0e-6
 lr: 0.5
 warmup_epochs: 30