Merge remote-tracking branch 'origin/main' into refactor-imports

Author: rwightman

README.md

@@ -21,7 +21,37 @@ And a big thanks to all GitHub sponsors who helped with some of my costs before
 
 ## What's New
 
-# Dec 5, 2022
+### 🤗 Survey: Feedback Appreciated 🤗
+
+For a few months now, `timm` has been part of the Hugging Face ecosystem. Yearly, we survey users of our tools to see what we could do better, what we need to continue doing, or what we need to stop doing. 
+
+If you have a couple of minutes and want to participate in shaping the future of the ecosystem, please share your thoughts:
+[**hf.co/oss-survey**](https://hf.co/oss-survey) 🙏
+
+### Dec 8, 2022
+* Add 'EVA l' to `vision_transformer.py`, MAE style ViT-L/14 MIM pretrain w/ EVA-CLIP targets, FT on ImageNet-1k (w/ ImageNet-22k intermediate for some)
+  * original source: https://github.com/baaivision/EVA
+
+| model                                     | top1 | param_count |  gmac | macts | hub                                     |
+|:------------------------------------------|-----:|------------:|------:|------:|:----------------------------------------|
+| eva_large_patch14_336.in22k_ft_in22k_in1k | 89.2 |       304.5 | 191.1 | 270.2 | [link](https://huggingface.co/BAAI/EVA) |
+| eva_large_patch14_336.in22k_ft_in1k       | 88.7 |       304.5 | 191.1 | 270.2 | [link](https://huggingface.co/BAAI/EVA) |
+| eva_large_patch14_196.in22k_ft_in22k_in1k | 88.6 |       304.1 |  61.6 |  63.5 | [link](https://huggingface.co/BAAI/EVA) |
+| eva_large_patch14_196.in22k_ft_in1k       | 87.9 |       304.1 |  61.6 |  63.5 | [link](https://huggingface.co/BAAI/EVA) |
+
+### Dec 6, 2022
+* Add 'EVA g', BEiT style ViT-g/14 model weights w/ both MIM pretrain and CLIP pretrain to `beit.py`. 
+  * original source: https://github.com/baaivision/EVA
+  * paper: https://arxiv.org/abs/2211.07636
+
+| model                                    |   top1 |   param_count |   gmac |   macts | hub                                     |
+|:-----------------------------------------|-------:|--------------:|-------:|--------:|:----------------------------------------|
+| eva_giant_patch14_560.m30m_ft_in22k_in1k |   89.8 |        1014.4 | 1906.8 |  2577.2 | [link](https://huggingface.co/BAAI/EVA) |
+| eva_giant_patch14_336.m30m_ft_in22k_in1k |   89.6 |        1013   |  620.6 |   550.7 | [link](https://huggingface.co/BAAI/EVA) |
+| eva_giant_patch14_336.clip_ft_in1k       |   89.4 |        1013   |  620.6 |   550.7 | [link](https://huggingface.co/BAAI/EVA) |
+| eva_giant_patch14_224.clip_ft_in1k       |   89.1 |        1012.6 |  267.2 |   192.6 | [link](https://huggingface.co/BAAI/EVA) |
+
+### Dec 5, 2022
 
 * Pre-release (`0.8.0dev0`) of multi-weight support (`model_arch.pretrained_tag`). Install with `pip install --pre timm`
   * vision_transformer, maxvit, convnext are the first three model impl w/ support
@@ -376,6 +406,7 @@ A full version of the list below with source links can be found in the [document
     * MobileNet-V2 - https://arxiv.org/abs/1801.04381
     * Single-Path NAS - https://arxiv.org/abs/1904.02877
     * TinyNet - https://arxiv.org/abs/2010.14819
+* EVA - https://arxiv.org/abs/2211.07636
 * GCViT (Global Context Vision Transformer) - https://arxiv.org/abs/2206.09959
 * GhostNet - https://arxiv.org/abs/1911.11907
 * gMLP - https://arxiv.org/abs/2105.08050

benchmark.py

@@ -81,9 +81,11 @@
 parser.add_argument('--results-format', default='csv', type=str,
                     help='Format for results file one of (csv, json) (default: csv).')
 parser.add_argument('--num-warm-iter', default=10, type=int,
-                    metavar='N', help='Number of warmup iterations (default: 10)')
+                    help='Number of warmup iterations (default: 10)')
 parser.add_argument('--num-bench-iter', default=40, type=int,
-                    metavar='N', help='Number of benchmark iterations (default: 40)')
+                    help='Number of benchmark iterations (default: 40)')
+parser.add_argument('--device', default='cuda', type=str,
+                    help="device to run benchmark on")
 
 # common inference / train args
 parser.add_argument('--model', '-m', metavar='NAME', default='resnet50',

tests/test_models.py

@@ -27,7 +27,7 @@
     'vit_*', 'tnt_*', 'pit_*', 'swin_*', 'coat_*', 'cait_*', '*mixer_*', 'gmlp_*', 'resmlp_*', 'twins_*',
     'convit_*', 'levit*', 'visformer*', 'deit*', 'jx_nest_*', 'nest_*', 'xcit_*', 'crossvit_*', 'beit*',
     'poolformer_*', 'volo_*', 'sequencer2d_*', 'swinv2_*', 'pvt_v2*', 'mvitv2*', 'gcvit*', 'efficientformer*',
-    'coatnet*', 'coatnext*', 'maxvit*', 'maxxvit*',
+    'coatnet*', 'coatnext*', 'maxvit*', 'maxxvit*', 'eva_*'
 ]
 NUM_NON_STD = len(NON_STD_FILTERS)
 
@@ -39,7 +39,7 @@
         '*nfnet_f3*', '*nfnet_f4*', '*nfnet_f5*', '*nfnet_f6*', '*nfnet_f7*', '*efficientnetv2_xl*',
         '*resnetrs350*', '*resnetrs420*', 'xcit_large_24_p8*', 'vit_huge*', 'vit_gi*', 'swin*huge*',
         'swin*giant*']
-    NON_STD_EXCLUDE_FILTERS = ['vit_huge*', 'vit_gi*', 'swin*giant*']
+    NON_STD_EXCLUDE_FILTERS = ['vit_huge*', 'vit_gi*', 'swin*giant*', 'eva_giant*']
 else:
     EXCLUDE_FILTERS = []
     NON_STD_EXCLUDE_FILTERS = ['vit_gi*']

timm/models/_pretrained.py

@@ -62,10 +62,11 @@ def to_dict(self, remove_source=False, remove_null=True):
 
 def filter_pretrained_cfg(cfg, remove_source=False, remove_null=True):
     filtered_cfg = {}
+    keep_none = {'pool_size', 'first_conv', 'classifier'}  # always keep these keys, even if none
     for k, v in cfg.items():
         if remove_source and k in {'url', 'file', 'hf_hub_id', 'hf_hub_id', 'hf_hub_filename', 'source'}:
             continue
-        if remove_null and v is None:
+        if remove_null and v is None and k not in keep_none:
             continue
         filtered_cfg[k] = v
     return filtered_cfg