ymzhang319 commited on
Commit
4b49449
1 Parent(s): 0cdab5c

Upload 5 files

Browse files
semantic/image_encoder/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./image_encoder",
3
+ "architectures": [
4
+ "CLIPVisionModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dropout": 0.0,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 1280,
10
+ "image_size": 224,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5120,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 16,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 32,
19
+ "patch_size": 14,
20
+ "projection_dim": 1024,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.28.0.dev0"
23
+ }
semantic/image_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ec78d6e060e694c4d8c6fb08a991b07c1ec580aa9d721e34fd51dce224df764
3
+ size 965738496
semantic/semantic_adapter.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87db0038a5581334c0785d67a41dc7290aee4c3ad7f3564b96423366bbc1935c
3
+ size 89289954
temporal_adapter.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a22e45ee987a16cbf74c79d78047e2a1b74b6db5cd4787f76759c29f4114c04
3
+ size 4269801472
timestamp_detector.pth.tar ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa4fba46c38e16a3a96825a55c3690b4a72ffbb337f6eed11dc1eadf79a78cf
3
+ size 376654135