feat: add crossvit9 ckpt, yaml and ut test (mindspore-lab#585)

configs/crossvit/README.md

@@ -23,6 +23,7 @@ Our reproduced model performance on ImageNet-1K is reported as follows.
 
 | Model       | Context  | Top-1 (%) | Top-5 (%) | Params (M) | Recipe                                                                                  | Download                                                                              |
 |-------------|----------|-----------|-----------|------------|-----------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------|
+| crossvit_9 | D910x8-G | 73.56     | 91.79     | 8.55      | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/crossvit/crossvit_9_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/crossvit/crossvit_9-e74c8e18.ckpt)     |
 | crossvit_15 | D910x8-G | 81.08     | 95.33     | 27.27      | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/crossvit/crossvit_15_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/crossvit/crossvit_15-eaa43c02.ckpt)     |
 | crossvit_18 | D910x8-G | 81.93     | 95.75     | 43.27      | [yaml](https://github.com/mindspore-lab/mindcv/blob/main/configs/crossvit/crossvit_18_ascend.yaml) | [weights](https://download.mindspore.cn/toolkits/mindcv/crossvit/crossvit_18-ca0a2e43.ckpt) |
 

configs/crossvit/crossvit_9_ascend.yaml

@@ -0,0 +1,63 @@
+# system
+mode: 0
+distribute: True
+num_parallel_workers: 8
+val_while_train: True
+
+# dataset
+dataset: 'imagenet'
+data_dir: '/path/to/imagenet'
+shuffle: True
+dataset_download: False
+batch_size: 256
+drop_remainder: True
+
+# augmentation
+image_resize: 240
+scale: [0.08, 1.0]
+ratio: [0.75, 1.333]
+hflip: 0.5
+vflip: 0.
+interpolation: 'bicubic'
+auto_augment: 'randaug-m9-mstd0.5-inc1'
+re_prob: 0.25
+mixup: 0.8
+cutmix: 1.0
+color_jitter: 0.4
+crop_pct: 0.935
+
+# model
+model: 'crossvit9'
+num_classes: 1000
+pretrained: False
+ckpt_path: ''
+keep_checkpoint_max: 10
+ckpt_save_dir: './ckpt'
+epoch_size: 300
+dataset_sink_mode: True
+amp_level: 'O2'
+drop_path_rate: 0.1
+
+# loss
+loss: 'CE'
+label_smoothing: 0.1
+
+# lr scheduler
+scheduler: 'cosine_decay'
+lr: 0.0011
+min_lr: 0.00001
+warmup_epochs: 30
+decay_epochs: 270
+decay_rate: 0.1
+
+# optimizer
+opt: 'adamw'
+weight_decay: 0.05
+filter_bias_and_bn: True
+loss_scale_type: 'dynamic'
+drop_overflow_update: True
+use_nesterov: False
+eps: 1e-8
+
+# Scheduler parameters
+lr_epoch_stair: True

mindcv/models/crossvit.py

@@ -21,6 +21,7 @@
 from .utils import load_pretrained
 
 __all__ = [
+    "crossvit9",
     "crossvit15",
     "crossvit18",
 ]
@@ -30,13 +31,17 @@ def _cfg(url='', **kwargs):
     return {
         'url': url,
         'num_classes': 1000,
+        "input_size": (3, 224, 224),
         'first_conv': 'patch_embed.proj',
         'classifier': 'head',
         **kwargs
     }
 
 
 default_cfgs = {
+    "crossvit_9": _cfg(
+        url="https://download.mindspore.cn/toolkits/mindcv/crossvit/crossvit_9-e74c8e18.ckpt",
+        input_size=(3, 240, 240)),
     "crossvit_15": _cfg(url="https://download.mindspore.cn/toolkits/mindcv/crossvit/crossvit_15-eaa43c02.ckpt"),
     "crossvit_18": _cfg(url="https://download.mindspore.cn/toolkits/mindcv/crossvit/crossvit_18-ca0a2e43.ckpt"),
 }
@@ -445,6 +450,18 @@ def construct(self, x: Tensor) -> Tensor:
         return x
 
 
+@register_model
+def crossvit9(pretrained: bool = False, num_classes: int = 1000, in_channels=3, **kwargs):
+    model = VisionTransformer(img_size=[240, 224],
+                              patch_size=[12, 16], embed_dim=[128, 256], depth=[[1, 3, 0], [1, 3, 0], [1, 3, 0]],
+                              num_heads=[4, 4], mlp_ratio=[3, 3, 1], qkv_bias=True,
+                              norm_layer=nn.LayerNorm, in_channels=in_channels, num_classes=num_classes, **kwargs)
+    default_cfg = default_cfgs["crossvit_9"]
+    if pretrained:
+        load_pretrained(model, default_cfg, num_classes=num_classes, in_channels=in_channels)
+    return model
+
+
 @register_model
 def crossvit15(pretrained: bool = False, num_classes: int = 1000, in_channels=3, **kwargs) -> VisionTransformer:
     model = VisionTransformer(img_size=[240, 224],

tests/modules/test_models.py

@@ -24,6 +24,7 @@
     "RepMLPNet_T224",
     "convit_tiny",
     "convnext_tiny",
+    "crossvit9",
     "densenet121",
     "dpn92",
     "edgenext_small",