Replace arg with in mindspore.nn.Dropout (#644)

Author: horcham

mindocr/models/backbones/mindcv_models/cait.py

@@ -67,9 +67,9 @@ def __init__(self,
         self.q = nn.Dense(dim, dim, has_bias=qkv_bias)
         self.k = nn.Dense(dim, dim, has_bias=qkv_bias)
         self.v = nn.Dense(dim, dim, has_bias=qkv_bias)
-        self.attn_drop = nn.Dropout(1 - attn_drop_rate)
+        self.attn_drop = nn.Dropout(p=attn_drop_rate)
         self.proj = nn.Dense(dim, dim)
-        self.proj_drop = nn.Dropout(1 - proj_drop_rate)
+        self.proj_drop = nn.Dropout(p=proj_drop_rate)
         self.softmax = nn.Softmax(axis=-1)
 
         self.attn_matmul_v = ops.BatchMatMul()
@@ -156,14 +156,14 @@ def __init__(self,
         self.scale = qk_scale or head_dim ** -0.5
 
         self.qkv = nn.Dense(dim, dim * 3, has_bias=qkv_bias)
-        self.attn_drop = nn.Dropout(1 - attn_drop_rate)
+        self.attn_drop = nn.Dropout(p=attn_drop_rate)
 
         self.proj = nn.Dense(dim, dim, has_bias=False)
 
         self.proj_l = nn.Dense(num_heads, num_heads, has_bias=False)
         self.proj_w = nn.Dense(num_heads, num_heads, has_bias=False)
 
-        self.proj_drop = nn.Dropout(1 - proj_drop_rate)
+        self.proj_drop = nn.Dropout(p=proj_drop_rate)
 
         self.softmax = nn.Softmax(axis=-1)
 
@@ -271,7 +271,7 @@ def __init__(self,
         zeros = ops.Zeros()
         self.cls_token = Parameter(zeros((1, 1, embed_dim), ms.float32))
         self.pos_embed = Parameter(zeros((1, num_patches, embed_dim), ms.float32))
-        self.pos_drop = nn.Dropout(1 - drop_rate)
+        self.pos_drop = nn.Dropout(p=drop_rate)
 
         dpr = [drop_path_rate for i in range(depth)]
 

mindocr/models/backbones/mindcv_models/coat.py

@@ -76,7 +76,7 @@ def __init__(
         self.fc1 = nn.Dense(in_channels=in_features, out_channels=hidden_features, has_bias=True)
         self.act = nn.GELU(approximate=False)
         self.fc2 = nn.Dense(in_channels=hidden_features, out_channels=out_features, has_bias=True)
-        self.drop = nn.Dropout(keep_prob=1.0 - drop)
+        self.drop = nn.Dropout(p=drop)
 
     def construct(self, x: Tensor) -> Tensor:
         x = self.fc1(x)
@@ -173,9 +173,9 @@ def __init__(
         self.q = nn.Dense(in_channels=dim, out_channels=dim, has_bias=qkv_bias)
         self.k = nn.Dense(in_channels=dim, out_channels=dim, has_bias=qkv_bias)
         self.v = nn.Dense(in_channels=dim, out_channels=dim, has_bias=qkv_bias)
-        self.attn_drop = nn.Dropout(keep_prob=1 - attn_drop)
+        self.attn_drop = nn.Dropout(p=attn_drop)
         self.proj = nn.Dense(dim, dim)
-        self.proj_drop = nn.Dropout(keep_prob=1 - proj_drop)
+        self.proj_drop = nn.Dropout(p=proj_drop)
         self.softmax = nn.Softmax(axis=-1)
         self.batch_matmul = ops.BatchMatMul()
 

mindocr/models/backbones/mindcv_models/convit.py

@@ -85,10 +85,10 @@ def __init__(
         self.k = nn.Dense(in_channels=dim, out_channels=dim, has_bias=qkv_bias)
         self.v = nn.Dense(in_channels=dim, out_channels=dim, has_bias=qkv_bias)
 
-        self.attn_drop = nn.Dropout(keep_prob=1.0 - attn_drop)
+        self.attn_drop = nn.Dropout(p=attn_drop)
         self.proj = nn.Dense(in_channels=dim, out_channels=dim)
         self.pos_proj = nn.Dense(in_channels=3, out_channels=num_heads)
-        self.proj_drop = nn.Dropout(keep_prob=1.0 - proj_drop)
+        self.proj_drop = nn.Dropout(p=proj_drop)
         self.gating_param = Parameter(ops.ones((num_heads), ms.float32))
         self.softmax = nn.Softmax(axis=-1)
         self.batch_matmul = ops.BatchMatMul()
@@ -144,9 +144,9 @@ def __init__(
         self.q = nn.Dense(in_channels=dim, out_channels=dim, has_bias=qkv_bias)
         self.k = nn.Dense(in_channels=dim, out_channels=dim, has_bias=qkv_bias)
         self.v = nn.Dense(in_channels=dim, out_channels=dim, has_bias=qkv_bias)
-        self.attn_drop = nn.Dropout(keep_prob=1.0 - attn_drop)
+        self.attn_drop = nn.Dropout(p=attn_drop)
         self.proj = nn.Dense(in_channels=dim, out_channels=dim)
-        self.proj_drop = nn.Dropout(keep_prob=1.0 - proj_drop)
+        self.proj_drop = nn.Dropout(p=proj_drop)
         self.softmax = nn.Softmax(axis=-1)
         self.batch_matmul = ops.BatchMatMul()
 
@@ -261,7 +261,7 @@ def __init__(
         self.num_patches = self.patch_embed.num_patches
 
         self.cls_token = Parameter(ops.Zeros()((1, 1, embed_dim), ms.float32))
-        self.pos_drop = nn.Dropout(keep_prob=1.0 - drop_rate)
+        self.pos_drop = nn.Dropout(p=drop_rate)
 
         if self.use_pos_embed:
             self.pos_embed = Parameter(ops.Zeros()((1, self.num_patches, embed_dim), ms.float32))

mindocr/models/backbones/mindcv_models/crossvit.py

@@ -50,9 +50,9 @@ def __init__(self, dim, num_heads=8, qkv_bias=False, attn_drop=0., proj_drop=0.)
         self.scale = head_dim ** -0.5
 
         self.qkv = nn.Dense(dim, dim * 3, has_bias=qkv_bias)
-        self.attn_drop = nn.Dropout(1.0 - attn_drop)
+        self.attn_drop = nn.Dropout(p=attn_drop)
         self.proj = nn.Dense(dim, dim)
-        self.proj_drop = nn.Dropout(1.0 - proj_drop)
+        self.proj_drop = nn.Dropout(p=proj_drop)
 
     def construct(self, x: Tensor) -> Tensor:
         B, N, C = x.shape
@@ -152,9 +152,9 @@ def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0.
         self.wq = nn.Dense(dim, dim, has_bias=qkv_bias)
         self.wk = nn.Dense(dim, dim, has_bias=qkv_bias)
         self.wv = nn.Dense(dim, dim, has_bias=qkv_bias)
-        self.attn_drop = nn.Dropout(1.0 - attn_drop)
+        self.attn_drop = nn.Dropout(p=attn_drop)
         self.proj = nn.Dense(dim, dim)
-        self.proj_drop = nn.Dropout(1.0 - proj_drop)
+        self.proj_drop = nn.Dropout(p=proj_drop)
 
     def construct(self, x: Tensor) -> Tensor:
         B, N, C = x.shape  # 3,3,16
@@ -341,7 +341,7 @@ def __init__(self, img_size=(224, 224), patch_size=(8, 16), in_channels=3, num_c
             d.append(c)
         d = tuple(d)
         self.cls_token = ms.ParameterTuple(d)
-        self.pos_drop = nn.Dropout(1.0 - drop_rate)
+        self.pos_drop = nn.Dropout(p=drop_rate)
 
         total_depth = sum([sum(x[-2:]) for x in depth])
         dpr = np.linspace(0, drop_path_rate, total_depth)  # stochastic depth decay rule

mindocr/models/backbones/mindcv_models/densenet.py

@@ -61,7 +61,7 @@ def __init__(
         self.conv2 = nn.Conv2d(bn_size * growth_rate, growth_rate, kernel_size=3, stride=1, pad_mode="pad", padding=1)
 
         self.drop_rate = drop_rate
-        self.dropout = nn.Dropout(keep_prob=1 - self.drop_rate)
+        self.dropout = nn.Dropout(p=self.drop_rate)
 
     def construct(self, features: Tensor) -> Tensor:
         bottleneck = self.conv1(self.relu1(self.norm1(features)))

mindocr/models/backbones/mindcv_models/edgenext.py

@@ -264,9 +264,9 @@ def __init__(
         self.temperature = Parameter(Tensor(np.ones((num_heads, 1, 1)), ms.float32))
 
         self.qkv = nn.Dense(dim, dim * 3, has_bias=qkv_bias)
-        self.attn_drop = nn.Dropout(1 - attn_drop)
+        self.attn_drop = nn.Dropout(p=attn_drop)
         self.proj = nn.Dense(dim, dim)
-        self.proj_drop = nn.Dropout(1 - proj_drop)
+        self.proj_drop = nn.Dropout(p=proj_drop)
 
     def construct(self, x: Tensor) -> Tensor:
         B, N, C = x.shape
@@ -363,7 +363,7 @@ def __init__(self, in_chans=3, num_classes=1000,
         self.head = nn.Dense(dims[-1], num_classes)
 
         # self.head_dropout = nn.Dropout(kwargs["classifier_dropout"])
-        self.head_dropout = nn.Dropout(1.0)
+        self.head_dropout = nn.Dropout(p=0.0)
         self.head_init_scale = head_init_scale
         self._initialize_weights()
 

mindocr/models/backbones/mindcv_models/efficientnet.py

@@ -421,7 +421,7 @@ def __init__(
 
         self.features = nn.SequentialCell(layers)
         self.avgpool = GlobalAvgPooling()
-        self.dropout = nn.Dropout(1 - dropout_rate)
+        self.dropout = nn.Dropout(p=dropout_rate)
         self.mlp_head = nn.Dense(lastconv_output_channels, num_classes)
         self._initialize_weights()
 

mindocr/models/backbones/mindcv_models/ghostnet.py

@@ -177,7 +177,7 @@ class GhostNet(nn.Cell):
         num_classes: number of classification classes. Default: 1000.
         in_channels: number of input channels. Default: 3.
         width: base width of hidden channel in blocks. Default: 1.0
-        droupout: the probability of the features before classification. Default: 0.2
+        dropout: the probability of the features before classification. Default: 0.2
     """
 
     def __init__(
@@ -227,7 +227,7 @@ def __init__(
                                    padding=0, stride=1, has_bias=True, pad_mode="pad")
         self.act2 = nn.ReLU()
         if self.dropout_rate > 0:
-            self.dropout = nn.Dropout(self.dropout_rate)
+            self.dropout = nn.Dropout(p=self.dropout_rate)
         self.classifier = nn.Dense(output_channel, num_classes)
         self._initialize_weights()
 

mindocr/models/backbones/mindcv_models/googlenet.py

@@ -109,7 +109,7 @@ def __init__(
         self.fc2 = nn.Dense(1024, num_classes)
         self.flatten = nn.Flatten()
         self.relu = nn.ReLU()
-        self.dropout = nn.Dropout(1 - drop_rate)
+        self.dropout = nn.Dropout(p=drop_rate)
 
     def construct(self, x: Tensor) -> Tensor:
         x = self.avg_pool(x)
@@ -170,7 +170,7 @@ def __init__(
             self.aux2 = InceptionAux(528, num_classes, drop_rate=drop_rate_aux)
 
         self.pool = GlobalAvgPooling()
-        self.dropout = nn.Dropout(keep_prob=1 - drop_rate)
+        self.dropout = nn.Dropout(p=drop_rate)
         self.classifier = nn.Dense(1024, num_classes)
         self._initialize_weights()
 

mindocr/models/backbones/mindcv_models/inception_v3.py

@@ -266,7 +266,7 @@ def __init__(
         self.inception7c = InceptionE(2048)
 
         self.pool = GlobalAvgPooling()
-        self.dropout = nn.Dropout(keep_prob=1 - drop_rate)
+        self.dropout = nn.Dropout(p=drop_rate)
         self.num_features = 2048
         self.classifier = nn.Dense(self.num_features, num_classes)
         self._initialize_weights()