timm upgrade 0.6.12 (#696)

* config: timm version bump 0.4.12 -> 0.6.12

* fix: timm based EfficientNetBaseEncoder after timm upgrade to 0.6.12

EfficientNet act1 layer in timm is merged with bn1 layer after
ab49d275de8a9c344aea086fd86d04c4cabb6098 commit

* fix: use "public" API for timm models availability check

* fix: timm SkNetEncoder after timm upgrade to 0.6.12

`zero_init_last_bn` was renamed to `zero_init_last` in
372ad5fa0dbeb74dcec81db06e9ff69b3d5a2eb6 commit

* fix: timm RegNet encoder after timm upgrade to 0.6.12

Instead of plain dict config RegNet uses RegNetCfg dataclass.
Dataclasses module were added in Python 3.7, thats why min required
Python version for package is also increased.

* feat: bump Python version used in Github Actions to 3.7

Author: VadimLevin

.github/workflows/pypi.yml

@@ -12,7 +12,7 @@ jobs:
     - name: Set up Python
       uses: actions/setup-python@v2
       with:
-        python-version: '3.6'
+        python-version: '3.7'
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip

.github/workflows/tests.yml

@@ -18,7 +18,7 @@ jobs:
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v2
       with:
-        python-version: 3.6
+        python-version: 3.7
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.black]
 line-length = 119
-target-version = ['py36', 'py37', 'py38']
+target-version = ['py37', 'py38']
 include = '\.pyi?$'
 exclude = '''
 /(
@@ -16,4 +16,4 @@ exclude = '''
   | build
   | dist
 )/
-'''
+'''

requirements.txt

@@ -1,7 +1,7 @@
 torchvision>=0.5.0
 pretrainedmodels==0.7.4
 efficientnet-pytorch==0.7.1
-timm==0.4.12
+timm==0.6.12
 
 tqdm
 pillow

segmentation_models_pytorch/encoders/__init__.py

@@ -97,9 +97,9 @@ def get_preprocessing_params(encoder_name, pretrained="imagenet"):
 
     if encoder_name.startswith("tu-"):
         encoder_name = encoder_name[3:]
-        if encoder_name not in timm.models.registry._model_has_pretrained:
+        if not timm.models.is_model_pretrained(encoder_name):
             raise ValueError(f"{encoder_name} does not have pretrained weights and preprocessing parameters")
-        settings = timm.models.registry._model_default_cfgs[encoder_name]
+        settings = timm.models.get_pretrained_cfg(encoder_name)
     else:
         all_settings = encoders[encoder_name]["pretrained_settings"]
         if pretrained not in all_settings.keys():

segmentation_models_pytorch/encoders/timm_efficientnet.py

@@ -105,7 +105,7 @@ def __init__(self, stage_idxs, out_channels, depth=5, **kwargs):
     def get_stages(self):
         return [
             nn.Identity(),
-            nn.Sequential(self.conv_stem, self.bn1, self.act1),
+            nn.Sequential(self.conv_stem, self.bn1),
             self.blocks[: self._stage_idxs[0]],
             self.blocks[self._stage_idxs[0] : self._stage_idxs[1]],
             self.blocks[self._stage_idxs[1] : self._stage_idxs[2]],

segmentation_models_pytorch/encoders/timm_regnet.py

@@ -1,10 +1,11 @@
 from ._base import EncoderMixin
-from timm.models.regnet import RegNet
+from timm.models.regnet import RegNet, RegNetCfg
 import torch.nn as nn
 
 
 class RegNetEncoder(RegNet, EncoderMixin):
     def __init__(self, out_channels, depth=5, **kwargs):
+        kwargs["cfg"] = RegNetCfg(**kwargs["cfg"])
         super().__init__(**kwargs)
         self._depth = depth
         self._out_channels = out_channels
@@ -141,95 +142,95 @@ def _mcfg(**kwargs):
         "pretrained_settings": pretrained_settings["timm-regnetx_002"],
         "params": {
             "out_channels": (3, 32, 24, 56, 152, 368),
-            "cfg": _mcfg(w0=24, wa=36.44, wm=2.49, group_w=8, depth=13),
+            "cfg": _mcfg(w0=24, wa=36.44, wm=2.49, group_size=8, depth=13),
         },
     },
     "timm-regnetx_004": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnetx_004"],
         "params": {
             "out_channels": (3, 32, 32, 64, 160, 384),
-            "cfg": _mcfg(w0=24, wa=24.48, wm=2.54, group_w=16, depth=22),
+            "cfg": _mcfg(w0=24, wa=24.48, wm=2.54, group_size=16, depth=22),
         },
     },
     "timm-regnetx_006": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnetx_006"],
         "params": {
             "out_channels": (3, 32, 48, 96, 240, 528),
-            "cfg": _mcfg(w0=48, wa=36.97, wm=2.24, group_w=24, depth=16),
+            "cfg": _mcfg(w0=48, wa=36.97, wm=2.24, group_size=24, depth=16),
         },
     },
     "timm-regnetx_008": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnetx_008"],
         "params": {
             "out_channels": (3, 32, 64, 128, 288, 672),
-            "cfg": _mcfg(w0=56, wa=35.73, wm=2.28, group_w=16, depth=16),
+            "cfg": _mcfg(w0=56, wa=35.73, wm=2.28, group_size=16, depth=16),
         },
     },
     "timm-regnetx_016": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnetx_016"],
         "params": {
             "out_channels": (3, 32, 72, 168, 408, 912),
-            "cfg": _mcfg(w0=80, wa=34.01, wm=2.25, group_w=24, depth=18),
+            "cfg": _mcfg(w0=80, wa=34.01, wm=2.25, group_size=24, depth=18),
         },
     },
     "timm-regnetx_032": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnetx_032"],
         "params": {
             "out_channels": (3, 32, 96, 192, 432, 1008),
-            "cfg": _mcfg(w0=88, wa=26.31, wm=2.25, group_w=48, depth=25),
+            "cfg": _mcfg(w0=88, wa=26.31, wm=2.25, group_size=48, depth=25),
         },
     },
     "timm-regnetx_040": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnetx_040"],
         "params": {
             "out_channels": (3, 32, 80, 240, 560, 1360),
-            "cfg": _mcfg(w0=96, wa=38.65, wm=2.43, group_w=40, depth=23),
+            "cfg": _mcfg(w0=96, wa=38.65, wm=2.43, group_size=40, depth=23),
         },
     },
     "timm-regnetx_064": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnetx_064"],
         "params": {
             "out_channels": (3, 32, 168, 392, 784, 1624),
-            "cfg": _mcfg(w0=184, wa=60.83, wm=2.07, group_w=56, depth=17),
+            "cfg": _mcfg(w0=184, wa=60.83, wm=2.07, group_size=56, depth=17),
         },
     },
     "timm-regnetx_080": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnetx_080"],
         "params": {
             "out_channels": (3, 32, 80, 240, 720, 1920),
-            "cfg": _mcfg(w0=80, wa=49.56, wm=2.88, group_w=120, depth=23),
+            "cfg": _mcfg(w0=80, wa=49.56, wm=2.88, group_size=120, depth=23),
         },
     },
     "timm-regnetx_120": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnetx_120"],
         "params": {
             "out_channels": (3, 32, 224, 448, 896, 2240),
-            "cfg": _mcfg(w0=168, wa=73.36, wm=2.37, group_w=112, depth=19),
+            "cfg": _mcfg(w0=168, wa=73.36, wm=2.37, group_size=112, depth=19),
         },
     },
     "timm-regnetx_160": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnetx_160"],
         "params": {
             "out_channels": (3, 32, 256, 512, 896, 2048),
-            "cfg": _mcfg(w0=216, wa=55.59, wm=2.1, group_w=128, depth=22),
+            "cfg": _mcfg(w0=216, wa=55.59, wm=2.1, group_size=128, depth=22),
         },
     },
     "timm-regnetx_320": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnetx_320"],
         "params": {
             "out_channels": (3, 32, 336, 672, 1344, 2520),
-            "cfg": _mcfg(w0=320, wa=69.86, wm=2.0, group_w=168, depth=23),
+            "cfg": _mcfg(w0=320, wa=69.86, wm=2.0, group_size=168, depth=23),
         },
     },
     # regnety
@@ -238,95 +239,95 @@ def _mcfg(**kwargs):
         "pretrained_settings": pretrained_settings["timm-regnety_002"],
         "params": {
             "out_channels": (3, 32, 24, 56, 152, 368),
-            "cfg": _mcfg(w0=24, wa=36.44, wm=2.49, group_w=8, depth=13, se_ratio=0.25),
+            "cfg": _mcfg(w0=24, wa=36.44, wm=2.49, group_size=8, depth=13, se_ratio=0.25),
         },
     },
     "timm-regnety_004": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnety_004"],
         "params": {
             "out_channels": (3, 32, 48, 104, 208, 440),
-            "cfg": _mcfg(w0=48, wa=27.89, wm=2.09, group_w=8, depth=16, se_ratio=0.25),
+            "cfg": _mcfg(w0=48, wa=27.89, wm=2.09, group_size=8, depth=16, se_ratio=0.25),
         },
     },
     "timm-regnety_006": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnety_006"],
         "params": {
             "out_channels": (3, 32, 48, 112, 256, 608),
-            "cfg": _mcfg(w0=48, wa=32.54, wm=2.32, group_w=16, depth=15, se_ratio=0.25),
+            "cfg": _mcfg(w0=48, wa=32.54, wm=2.32, group_size=16, depth=15, se_ratio=0.25),
         },
     },
     "timm-regnety_008": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnety_008"],
         "params": {
             "out_channels": (3, 32, 64, 128, 320, 768),
-            "cfg": _mcfg(w0=56, wa=38.84, wm=2.4, group_w=16, depth=14, se_ratio=0.25),
+            "cfg": _mcfg(w0=56, wa=38.84, wm=2.4, group_size=16, depth=14, se_ratio=0.25),
         },
     },
     "timm-regnety_016": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnety_016"],
         "params": {
             "out_channels": (3, 32, 48, 120, 336, 888),
-            "cfg": _mcfg(w0=48, wa=20.71, wm=2.65, group_w=24, depth=27, se_ratio=0.25),
+            "cfg": _mcfg(w0=48, wa=20.71, wm=2.65, group_size=24, depth=27, se_ratio=0.25),
         },
     },
     "timm-regnety_032": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnety_032"],
         "params": {
             "out_channels": (3, 32, 72, 216, 576, 1512),
-            "cfg": _mcfg(w0=80, wa=42.63, wm=2.66, group_w=24, depth=21, se_ratio=0.25),
+            "cfg": _mcfg(w0=80, wa=42.63, wm=2.66, group_size=24, depth=21, se_ratio=0.25),
         },
     },
     "timm-regnety_040": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnety_040"],
         "params": {
             "out_channels": (3, 32, 128, 192, 512, 1088),
-            "cfg": _mcfg(w0=96, wa=31.41, wm=2.24, group_w=64, depth=22, se_ratio=0.25),
+            "cfg": _mcfg(w0=96, wa=31.41, wm=2.24, group_size=64, depth=22, se_ratio=0.25),
         },
     },
     "timm-regnety_064": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnety_064"],
         "params": {
             "out_channels": (3, 32, 144, 288, 576, 1296),
-            "cfg": _mcfg(w0=112, wa=33.22, wm=2.27, group_w=72, depth=25, se_ratio=0.25),
+            "cfg": _mcfg(w0=112, wa=33.22, wm=2.27, group_size=72, depth=25, se_ratio=0.25),
         },
     },
     "timm-regnety_080": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnety_080"],
         "params": {
             "out_channels": (3, 32, 168, 448, 896, 2016),
-            "cfg": _mcfg(w0=192, wa=76.82, wm=2.19, group_w=56, depth=17, se_ratio=0.25),
+            "cfg": _mcfg(w0=192, wa=76.82, wm=2.19, group_size=56, depth=17, se_ratio=0.25),
         },
     },
     "timm-regnety_120": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnety_120"],
         "params": {
             "out_channels": (3, 32, 224, 448, 896, 2240),
-            "cfg": _mcfg(w0=168, wa=73.36, wm=2.37, group_w=112, depth=19, se_ratio=0.25),
+            "cfg": _mcfg(w0=168, wa=73.36, wm=2.37, group_size=112, depth=19, se_ratio=0.25),
         },
     },
     "timm-regnety_160": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnety_160"],
         "params": {
             "out_channels": (3, 32, 224, 448, 1232, 3024),
-            "cfg": _mcfg(w0=200, wa=106.23, wm=2.48, group_w=112, depth=18, se_ratio=0.25),
+            "cfg": _mcfg(w0=200, wa=106.23, wm=2.48, group_size=112, depth=18, se_ratio=0.25),
         },
     },
     "timm-regnety_320": {
         "encoder": RegNetEncoder,
         "pretrained_settings": pretrained_settings["timm-regnety_320"],
         "params": {
             "out_channels": (3, 32, 232, 696, 1392, 3712),
-            "cfg": _mcfg(w0=232, wa=115.89, wm=2.53, group_w=232, depth=20, se_ratio=0.25),
+            "cfg": _mcfg(w0=232, wa=115.89, wm=2.53, group_size=232, depth=20, se_ratio=0.25),
         },
     },
 }

segmentation_models_pytorch/encoders/timm_sknet.py

@@ -73,7 +73,7 @@ def load_state_dict(self, state_dict, **kwargs):
             "out_channels": (3, 64, 64, 128, 256, 512),
             "block": SelectiveKernelBasic,
             "layers": [2, 2, 2, 2],
-            "zero_init_last_bn": False,
+            "zero_init_last": False,
             "block_args": {"sk_kwargs": {"rd_ratio": 1 / 8, "split_input": True}},
         },
     },
@@ -84,7 +84,7 @@ def load_state_dict(self, state_dict, **kwargs):
             "out_channels": (3, 64, 64, 128, 256, 512),
             "block": SelectiveKernelBasic,
             "layers": [3, 4, 6, 3],
-            "zero_init_last_bn": False,
+            "zero_init_last": False,
             "block_args": {"sk_kwargs": {"rd_ratio": 1 / 8, "split_input": True}},
         },
     },
@@ -95,7 +95,7 @@ def load_state_dict(self, state_dict, **kwargs):
             "out_channels": (3, 64, 256, 512, 1024, 2048),
             "block": SelectiveKernelBottleneck,
             "layers": [3, 4, 6, 3],
-            "zero_init_last_bn": False,
+            "zero_init_last": False,
             "cardinality": 32,
             "base_width": 4,
         },

setup.py

@@ -17,7 +17,7 @@
 URL = "https://github.com/qubvel/segmentation_models.pytorch"
 EMAIL = "qubvel@gmail.com"
 AUTHOR = "Pavel Iakubovskii"
-REQUIRES_PYTHON = ">=3.6.0"
+REQUIRES_PYTHON = ">=3.7.0"
 VERSION = None
 
 # The rest you shouldn't have to touch too much :)