SmilingWolf commited on
Commit
790b0e9
1 Parent(s): 5c6bcf3

Update model files

Browse files
Files changed (5) hide show
  1. README.md +15 -2
  2. model.msgpack +1 -1
  3. model.onnx +1 -1
  4. model.safetensors +1 -1
  5. sw_jax_cv_config.json +1 -1
README.md CHANGED
@@ -17,11 +17,16 @@ Images with less than 10 general tags were filtered out.
17
  Tags with less than 600 images were filtered out.
18
 
19
  ## Validation results
20
- `P=R: threshold = 0.2547, F1 = 0.4278`
 
21
 
22
  ## What's new
 
 
 
 
23
  Model v1.1/Dataset v3:
24
- Amended the JAX model config file: add image size.
25
  No change to the trained weights.
26
 
27
  Model v1.0/Dataset v3:
@@ -31,6 +36,14 @@ ONNX model is compatible with code developed for the v2 series of models.
31
  The batch dimension of the ONNX model is not fixed to 1 anymore. Now you can go crazy with batch inference.
32
  Switched to Macro-F1 to measure model performance since it gives me a better gauge of overall training progress.
33
 
 
 
 
 
 
 
 
 
34
  ## Final words
35
  Subject to change and updates.
36
  Downstream users are encouraged to use tagged releases rather than relying on the head of the repo.
 
17
  Tags with less than 600 images were filtered out.
18
 
19
  ## Validation results
20
+ `v2.0: P=R: threshold = 0.2614, F1 = 0.4402`
21
+ `v1.0: P=R: threshold = 0.2547, F1 = 0.4278`
22
 
23
  ## What's new
24
+ Model v2.0/Dataset v3:
25
+ Trained for a few more epochs.
26
+ Used tag frequency-based loss scaling to combat class imbalance.
27
+
28
  Model v1.1/Dataset v3:
29
+ Amended the JAX model config file: add image size.
30
  No change to the trained weights.
31
 
32
  Model v1.0/Dataset v3:
 
36
  The batch dimension of the ONNX model is not fixed to 1 anymore. Now you can go crazy with batch inference.
37
  Switched to Macro-F1 to measure model performance since it gives me a better gauge of overall training progress.
38
 
39
+ # Runtime deps
40
+ ONNX model requires `onnxruntime >= 1.17.0`
41
+
42
+ # Inference code examples
43
+ For timm: https://github.com/neggles/wdv3-timm
44
+ For ONNX: https://huggingface.co/spaces/SmilingWolf/wd-tagger
45
+ For JAX: https://github.com/SmilingWolf/wdv3-jax
46
+
47
  ## Final words
48
  Subject to change and updates.
49
  Downstream users are encouraged to use tagged releases rather than relying on the head of the repo.
model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b06edd4477d3a5407afbc41a2e0d36773bc00e549eda5d19ad0395a0d23618bd
3
  size 378408630
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4b68183d5db1191ed4dbe0bfa816483454e55612b4e3a0c76e06229734c4ed6
3
  size 378408630
model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c21152f1febcd04867c4dbc7bddf781db701f7c0e14fa3b787656477a16514c
3
  size 378536310
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35f23693620b668f4d53fd3c62bf65e40af739bc52c7eb0fbc49258b58d065b6
3
  size 378536310
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:021ace976c1e9f944ea51d591c3f6a5722125ae8bd21c51caec3fd1275587ed5
3
  size 378417260
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee78db0cd9f1c7e01578cc89661a10c73675d60c30e235e505c391f57ea4d4e5
3
  size 378417260
sw_jax_cv_config.json CHANGED
@@ -11,4 +11,4 @@
11
  "drop_path_rate": 0.1,
12
  "layer_norm_eps": 1e-05
13
  }
14
- }
 
11
  "drop_path_rate": 0.1,
12
  "layer_norm_eps": 1e-05
13
  }
14
+ }