{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":168799526,"defaultBranch":"main","name":"pytorch-image-models","ownerLogin":"huggingface","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2019-02-02T05:51:12.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/25720743?v=4","public":true,"private":false,"isOrgOwned":true},"refInfo":{"name":"","listCacheKey":"v0:1717999157.0","currentOid":""},"activityList":{"items":[{"before":"5efa15b2a2476a02c6f0ead515494e7b76cd13cd","after":"30ffa152de73cdec43bb9ab63122f042179ce95c","ref":"refs/heads/openai_clip_resnet","pushedAt":"2024-06-10T19:07:51.000Z","pushType":"push","commitsCount":3,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Fix load of larger ResNet CLIP models, experimenting with making AttentionPool *the* head, seems to fine-tune better, one less layer.","shortMessageHtmlLink":"Fix load of larger ResNet CLIP models, experimenting with making Atte…"}},{"before":"60d35735ee96cf2319fe896190624912842ebfb0","after":"2673693897757971b0177dbf7d49e731f542510f","ref":"refs/heads/main","pushedAt":"2024-06-10T14:58:18.000Z","pushType":"pr_merge","commitsCount":3,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Merge pull request #2200 from McPatate/feat/add_trufflehog_ci\n\nfeat(ci): add trufflehog secrets detection","shortMessageHtmlLink":"Merge pull request <a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2343153631\" data-permission-text=\"Title is private\" data-url=\"https://github.com/huggingface/pytorch-image-models/issues/2200\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/huggingface/pytorch-image-models/pull/2200/hovercard\" href=\"https://github.com/huggingface/pytorch-image-models/pull/2200\">#2200</a> from McPatate/feat/add_trufflehog_ci"}},{"before":null,"after":"3c46320f29be4174b484818a4e0463c5499cdabb","ref":"refs/heads/mobileclip_hub_id","pushedAt":"2024-06-10T05:59:17.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Prepping for final MobileCLIP weight locations","shortMessageHtmlLink":"Prepping for final MobileCLIP weight locations"}},{"before":null,"after":"5efa15b2a2476a02c6f0ead515494e7b76cd13cd","ref":"refs/heads/openai_clip_resnet","pushedAt":"2024-06-09T23:56:23.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Mapping OpenAI CLIP Modified ResNet weights -> ByobNet. Improve AttentionPool2d layers. Fix #1731","shortMessageHtmlLink":"Mapping OpenAI CLIP Modified ResNet weights -&gt; ByobNet. Improve Atten…"}},{"before":"7702d9afa178a2fc0cf98fcf590de800dc51ac8d","after":"60d35735ee96cf2319fe896190624912842ebfb0","ref":"refs/heads/main","pushedAt":"2024-06-09T05:01:53.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Update README.md","shortMessageHtmlLink":"Update README.md"}},{"before":"5517b054dd00113341fcd12e17880cc82f73fe25","after":"7702d9afa178a2fc0cf98fcf590de800dc51ac8d","ref":"refs/heads/main","pushedAt":"2024-06-08T03:39:38.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"ViTamin in_chans !=3 weight load fix","shortMessageHtmlLink":"ViTamin in_chans !=3 weight load fix"}},{"before":null,"after":"66a0eb46731d2c2c5ea2c035d4b83fc69fa0bd92","ref":"refs/heads/tiny_test_models","pushedAt":"2024-06-07T23:09:50.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Experimenting with tiny test models, how small can they go and be useful for regression tests?","shortMessageHtmlLink":"Experimenting with tiny test models, how small can they go and be use…"}},{"before":"4535a5412acd4d72d895f2e567a65d14e104f364","after":"5517b054dd00113341fcd12e17880cc82f73fe25","ref":"refs/heads/main","pushedAt":"2024-06-07T22:30:24.000Z","pushType":"pr_merge","commitsCount":3,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Merge pull request #2195 from huggingface/refactor_pre_logits\n\nFix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size","shortMessageHtmlLink":"Merge pull request <a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2335084182\" data-permission-text=\"Title is private\" data-url=\"https://github.com/huggingface/pytorch-image-models/issues/2195\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/huggingface/pytorch-image-models/pull/2195/hovercard\" href=\"https://github.com/huggingface/pytorch-image-models/pull/2195\">#2195</a> from huggingface/refactor_pre_logits"}},{"before":"bbb13deb202a1ef8fa1866f6a17a4ec5356ad8f9","after":"5ee06760dc4a7ac2115e0127acf188a5bb7227db","ref":"refs/heads/refactor_pre_logits","pushedAt":"2024-06-07T20:53:31.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Fix classifier input dim for mnv3 after last changes","shortMessageHtmlLink":"Fix classifier input dim for mnv3 after last changes"}},{"before":"5cce2185e187ae07274f4b31a12033725bcd3714","after":"4535a5412acd4d72d895f2e567a65d14e104f364","ref":"refs/heads/main","pushedAt":"2024-06-07T20:40:55.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Change default serialization for push_to_hf_hub to 'both'","shortMessageHtmlLink":"Change default serialization for push_to_hf_hub to 'both'"}},{"before":"52659842cc0c2cea302a4f0a3db7ccabcc593365","after":"5cce2185e187ae07274f4b31a12033725bcd3714","ref":"refs/heads/main","pushedAt":"2024-06-07T20:13:24.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Update version.py","shortMessageHtmlLink":"Update version.py"}},{"before":"5dce71010174ad6599653da4e8ba37fd5f9fa572","after":"52659842cc0c2cea302a4f0a3db7ccabcc593365","ref":"refs/heads/main","pushedAt":"2024-06-07T20:12:36.000Z","pushType":"pr_merge","commitsCount":33,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Merge pull request #2196 from huggingface/mega_merge\n\nMega merge","shortMessageHtmlLink":"Merge pull request <a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2338662082\" data-permission-text=\"Title is private\" data-url=\"https://github.com/huggingface/pytorch-image-models/issues/2196\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/huggingface/pytorch-image-models/pull/2196/hovercard\" href=\"https://github.com/huggingface/pytorch-image-models/pull/2196\">#2196</a> from huggingface/mega_merge"}},{"before":"ad026e6e33b8db4d5640f16bfc7aedf2f7359931","after":"7ccb10ebfff6a57002047fd4fabcd911ec4f9604","ref":"refs/heads/mega_merge","pushedAt":"2024-06-07T04:50:40.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Disable efficient_builder debug flag","shortMessageHtmlLink":"Disable efficient_builder debug flag"}},{"before":"fc1b66a51d35201ecc13c1c5697c4b2e28c9c49d","after":"ad026e6e33b8db4d5640f16bfc7aedf2f7359931","ref":"refs/heads/mega_merge","pushedAt":"2024-06-07T00:56:27.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Fix in_chans switching on create","shortMessageHtmlLink":"Fix in_chans switching on create"}},{"before":"88a1006e025c1a4e39fb2b4db7f8ad8cb85ae88f","after":"fc1b66a51d35201ecc13c1c5697c4b2e28c9c49d","ref":"refs/heads/mega_merge","pushedAt":"2024-06-06T20:42:42.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Fix first conv name for mci vit-b","shortMessageHtmlLink":"Fix first conv name for mci vit-b"}},{"before":"7d4ada6d16760a3815a50c5e7f1b724955429d07","after":"88a1006e025c1a4e39fb2b4db7f8ad8cb85ae88f","ref":"refs/heads/mega_merge","pushedAt":"2024-06-06T19:39:29.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"checkpoint filter fns with consistent name, add mobileclip-b pretrained cfgs","shortMessageHtmlLink":"checkpoint filter fns with consistent name, add mobileclip-b pretrain…"}},{"before":null,"after":"7d4ada6d16760a3815a50c5e7f1b724955429d07","ref":"refs/heads/mega_merge","pushedAt":"2024-06-06T16:16:58.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Update ViTamin model defs","shortMessageHtmlLink":"Update ViTamin model defs"}},{"before":"24872c9a65d43bc9dab0e1599f5e39f59afad3fa","after":"bbb13deb202a1ef8fa1866f6a17a4ec5356ad8f9","ref":"refs/heads/refactor_pre_logits","pushedAt":"2024-06-05T15:15:39.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Fix classifier input dim for mnv3 after last changes","shortMessageHtmlLink":"Fix classifier input dim for mnv3 after last changes"}},{"before":"58591a97f7607f9b860bd7a77cc69f29a008057d","after":"0e77c95ed7a45b14eb43c274d38a10be66491cb0","ref":"refs/heads/Beckschen-vitamin","pushedAt":"2024-06-05T07:20:18.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Add vitamin to non-std testing models","shortMessageHtmlLink":"Add vitamin to non-std testing models"}},{"before":null,"after":"24872c9a65d43bc9dab0e1599f5e39f59afad3fa","ref":"refs/heads/refactor_pre_logits","pushedAt":"2024-06-05T07:09:18.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size\n* add test that model supports forward_head(x, pre_logits=True)\n* add head_hidden_size attr to all models and set differently from num_features attr when head has hidden layers\n* test forward_features() feat dim == model.num_features and pre_logits feat dim == self.head_hidden_size\n* more consistency in reset_classifier signature, add typing\n* asserts in some heads where pooling cannot be disabled\nFix #2194","shortMessageHtmlLink":"Fix consistency, testing for forward_head w/ pre_logits, reset_classi…"}},{"before":"1b66ec7cf3cbd14390a2bc4f78904ba04608614d","after":"58591a97f7607f9b860bd7a77cc69f29a008057d","ref":"refs/heads/Beckschen-vitamin","pushedAt":"2024-06-04T23:57:31.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Enable features_only properly","shortMessageHtmlLink":"Enable features_only properly"}},{"before":null,"after":"1b66ec7cf3cbd14390a2bc4f78904ba04608614d","ref":"refs/heads/Beckschen-vitamin","pushedAt":"2024-06-04T00:15:02.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Fixup ViTamin, add hub weight reference","shortMessageHtmlLink":"Fixup ViTamin, add hub weight reference"}},{"before":"ce637771dc2abc5ae81a96af14724300815edd15","after":"7f96538052eb411003c2c38a7013353aa31ffc62","ref":"refs/heads/fastvit_mobileclip","pushedAt":"2024-05-31T19:00:13.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Add missing lkc act for mobileclip fastvits","shortMessageHtmlLink":"Add missing lkc act for mobileclip fastvits"}},{"before":null,"after":"ce637771dc2abc5ae81a96af14724300815edd15","ref":"refs/heads/fastvit_mobileclip","pushedAt":"2024-05-30T17:18:38.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Add fastvit to forward_intermediates test","shortMessageHtmlLink":"Add fastvit to forward_intermediates test"}},{"before":"4ff7c257665189aec80284d590fddf286a9aaf8a","after":"5fa6efa158e5c6a7edc3a322c33a4deba8badfce","ref":"refs/heads/efficientnet_x","pushedAt":"2024-05-28T05:10:57.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Add anti-aliasing support to mobilenetv3 and efficientnet family models. Update MobileNetV4 model defs, resolutions. Fix #599\n* create_aa helper function centralized for all timm uses (resnet, convbnact helper)\n* allow BlurPool w/ pre-defined channels (expand)\n* mobilenetv4 UIB block using ConvNormAct layers for improved clarity, esp with AA added\n* improve more mobilenetv3 and efficientnet related type annotations","shortMessageHtmlLink":"Add anti-aliasing support to mobilenetv3 and efficientnet family mode…"}},{"before":"e748805be31318da1a0e34b61294704666f50397","after":"5dce71010174ad6599653da4e8ba37fd5f9fa572","ref":"refs/heads/main","pushedAt":"2024-05-27T21:56:23.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Add vit_little in12k + in12k-ft-in1k weights","shortMessageHtmlLink":"Add vit_little in12k + in12k-ft-in1k weights"}},{"before":"a12b72b5c4f4cd28985ff1bae347b886f8f41e6d","after":"4ff7c257665189aec80284d590fddf286a9aaf8a","ref":"refs/heads/efficientnet_x","pushedAt":"2024-05-24T23:45:28.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Pass layer_scale_init_value to Mnv3Features module","shortMessageHtmlLink":"Pass layer_scale_init_value to Mnv3Features module"}},{"before":"7fe96e7a92262dbbc81325b1fc7583446c0996c0","after":"a12b72b5c4f4cd28985ff1bae347b886f8f41e6d","ref":"refs/heads/efficientnet_x","pushedAt":"2024-05-24T22:51:06.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Fix missing head_norm arg pop for feature model","shortMessageHtmlLink":"Fix missing head_norm arg pop for feature model"}},{"before":"28d76a97dbf092cb7c34aa9e5f68e4dedc716c58","after":"7fe96e7a92262dbbc81325b1fc7583446c0996c0","ref":"refs/heads/efficientnet_x","pushedAt":"2024-05-24T22:11:19.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"More MobileNet-v4 fixes\n* missed final norm after post pooling 1x1 PW head conv\n* improve repr of model by flipping a few modules to None when not used, nn.Sequential for MultiQueryAttention query/key/value/output\n* allow layer scaling to be enabled/disabled at model variant level, conv variants don't use it","shortMessageHtmlLink":"More MobileNet-v4 fixes"}},{"before":"0c6a69e7ef9d3e2ca82ac967e7a5bb132220b0b9","after":"28d76a97dbf092cb7c34aa9e5f68e4dedc716c58","ref":"refs/heads/efficientnet_x","pushedAt":"2024-05-24T18:51:22.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"rwightman","name":"Ross Wightman","path":"/rwightman","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/5702664?s=80&v=4"},"commit":{"message":"Mixed up kernel size for last blocks in mnv4-conv-small","shortMessageHtmlLink":"Mixed up kernel size for last blocks in mnv4-conv-small"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAEYXaxMQA","startCursor":null,"endCursor":null}},"title":"Activity · huggingface/pytorch-image-models"}