Upload encoders/vgg.py

encoders/vgg.py

@@ -0,0 +1,157 @@
+""" Each encoder should have following attributes and methods and be inherited from `_base.EncoderMixin`
+
+Attributes:
+
+    _out_channels (list of int): specify number of channels for each encoder feature tensor
+    _depth (int): specify number of stages in decoder (in other words number of downsampling operations)
+    _in_channels (int): default number of input channels in first Conv2d layer for encoder (usually 3)
+
+Methods:
+
+    forward(self, x: torch.Tensor)
+        produce list of features of different spatial resolutions, each feature is a 4D torch.tensor of
+        shape NCHW (features should be sorted in descending order according to spatial resolution, starting
+        with resolution same as input `x` tensor).
+
+        Input: `x` with shape (1, 3, 64, 64)
+        Output: [f0, f1, f2, f3, f4, f5] - features with corresponding shapes
+                [(1, 3, 64, 64), (1, 64, 32, 32), (1, 128, 16, 16), (1, 256, 8, 8),
+                (1, 512, 4, 4), (1, 1024, 2, 2)] (C - dim may differ)
+
+        also should support number of features according to specified depth, e.g. if depth = 5,
+        number of feature tensors = 6 (one with same resolution as input and 5 downsampled),
+        depth = 3 -> number of feature tensors = 4 (one with same resolution as input and 3 downsampled).
+"""
+
+import torch.nn as nn
+from torchvision.models.vgg import VGG
+from torchvision.models.vgg import make_layers
+from pretrainedmodels.models.torchvision_models import pretrained_settings
+
+from ._base import EncoderMixin
+
+# fmt: off
+cfg = {
+    'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
+    'B': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
+    'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
+    'E': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
+}
+# fmt: on
+
+
+class VGGEncoder(VGG, EncoderMixin):
+    def __init__(self, out_channels, config, batch_norm=False, depth=5, **kwargs):
+        super().__init__(make_layers(config, batch_norm=batch_norm), **kwargs)
+        self._out_channels = out_channels
+        self._depth = depth
+        self._in_channels = 3
+        del self.classifier
+
+    def make_dilated(self, stage_list, dilation_list):
+        raise ValueError("'VGG' models do not support dilated mode due to Max Pooling"
+                         " operations for downsampling!")
+
+    def get_stages(self):
+        stages = []
+        stage_modules = []
+        for module in self.features:
+            if isinstance(module, nn.MaxPool2d):
+                stages.append(nn.Sequential(*stage_modules))
+                stage_modules = []
+            stage_modules.append(module)
+        stages.append(nn.Sequential(*stage_modules))
+        return stages
+
+    def forward(self, x):
+        stages = self.get_stages()
+
+        features = []
+        for i in range(self._depth + 1):
+            x = stages[i](x)
+            features.append(x)
+
+        return features
+
+    def load_state_dict(self, state_dict, **kwargs):
+        keys = list(state_dict.keys())
+        for k in keys:
+            if k.startswith("classifier"):
+                state_dict.pop(k, None)
+        super().load_state_dict(state_dict, **kwargs)
+
+
+vgg_encoders = {
+    "vgg11": {
+        "encoder": VGGEncoder,
+        "pretrained_settings": pretrained_settings["vgg11"],
+        "params": {
+            "out_channels": (64, 128, 256, 512, 512, 512),
+            "config": cfg["A"],
+            "batch_norm": False,
+        },
+    },
+    "vgg11_bn": {
+        "encoder": VGGEncoder,
+        "pretrained_settings": pretrained_settings["vgg11_bn"],
+        "params": {
+            "out_channels": (64, 128, 256, 512, 512, 512),
+            "config": cfg["A"],
+            "batch_norm": True,
+        },
+    },
+    "vgg13": {
+        "encoder": VGGEncoder,
+        "pretrained_settings": pretrained_settings["vgg13"],
+        "params": {
+            "out_channels": (64, 128, 256, 512, 512, 512),
+            "config": cfg["B"],
+            "batch_norm": False,
+        },
+    },
+    "vgg13_bn": {
+        "encoder": VGGEncoder,
+        "pretrained_settings": pretrained_settings["vgg13_bn"],
+        "params": {
+            "out_channels": (64, 128, 256, 512, 512, 512),
+            "config": cfg["B"],
+            "batch_norm": True,
+        },
+    },
+    "vgg16": {
+        "encoder": VGGEncoder,
+        "pretrained_settings": pretrained_settings["vgg16"],
+        "params": {
+            "out_channels": (64, 128, 256, 512, 512, 512),
+            "config": cfg["D"],
+            "batch_norm": False,
+        },
+    },
+    "vgg16_bn": {
+        "encoder": VGGEncoder,
+        "pretrained_settings": pretrained_settings["vgg16_bn"],
+        "params": {
+            "out_channels": (64, 128, 256, 512, 512, 512),
+            "config": cfg["D"],
+            "batch_norm": True,
+        },
+    },
+    "vgg19": {
+        "encoder": VGGEncoder,
+        "pretrained_settings": pretrained_settings["vgg19"],
+        "params": {
+            "out_channels": (64, 128, 256, 512, 512, 512),
+            "config": cfg["E"],
+            "batch_norm": False,
+        },
+    },
+    "vgg19_bn": {
+        "encoder": VGGEncoder,
+        "pretrained_settings": pretrained_settings["vgg19_bn"],
+        "params": {
+            "out_channels": (64, 128, 256, 512, 512, 512),
+            "config": cfg["E"],
+            "batch_norm": True,
+        },
+    },
+}