Image Classification
Transformers
TensorBoard
Safetensors
PyTorch
swin
huggingpics
Eval Results (legacy)
Instructions to use Libidrave/CartoonOrNotv2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Libidrave/CartoonOrNotv2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="Libidrave/CartoonOrNotv2") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("Libidrave/CartoonOrNotv2") model = AutoModelForImageClassification.from_pretrained("Libidrave/CartoonOrNotv2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
commit files to HF hub
Browse files- README.md +24 -0
- config.json +63 -0
- model.safetensors +3 -0
- preprocessor_config.json +23 -0
- runs/events.out.tfevents.1707901374.7046f09e3fd0.195.0 +3 -0
README.md
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- image-classification
|
| 4 |
+
- pytorch
|
| 5 |
+
- huggingpics
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
|
| 9 |
+
model-index:
|
| 10 |
+
- name: CartoonOrNotv2
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Image Classification
|
| 14 |
+
type: image-classification
|
| 15 |
+
metrics:
|
| 16 |
+
- name: Accuracy
|
| 17 |
+
type: accuracy
|
| 18 |
+
value: 0.9836065769195557
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
# CartoonOrNotv2
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
CartoonOrNot Model using Swin Transformer Architecture
|
config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "umm-maybe/AI-image-detector",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"SwinForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"depths": [
|
| 8 |
+
2,
|
| 9 |
+
2,
|
| 10 |
+
18,
|
| 11 |
+
2
|
| 12 |
+
],
|
| 13 |
+
"drop_path_rate": 0.1,
|
| 14 |
+
"embed_dim": 128,
|
| 15 |
+
"encoder_stride": 32,
|
| 16 |
+
"hidden_act": "gelu",
|
| 17 |
+
"hidden_dropout_prob": 0.0,
|
| 18 |
+
"hidden_size": 1024,
|
| 19 |
+
"id2label": {
|
| 20 |
+
"0": "cartoon",
|
| 21 |
+
"1": "not_cartoon"
|
| 22 |
+
},
|
| 23 |
+
"image_size": 224,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"cartoon": "0",
|
| 27 |
+
"not_cartoon": "1"
|
| 28 |
+
},
|
| 29 |
+
"layer_norm_eps": 1e-05,
|
| 30 |
+
"max_length": 128,
|
| 31 |
+
"mlp_ratio": 4.0,
|
| 32 |
+
"model_type": "swin",
|
| 33 |
+
"num_channels": 3,
|
| 34 |
+
"num_heads": [
|
| 35 |
+
4,
|
| 36 |
+
8,
|
| 37 |
+
16,
|
| 38 |
+
32
|
| 39 |
+
],
|
| 40 |
+
"num_layers": 4,
|
| 41 |
+
"out_features": [
|
| 42 |
+
"stage4"
|
| 43 |
+
],
|
| 44 |
+
"out_indices": [
|
| 45 |
+
4
|
| 46 |
+
],
|
| 47 |
+
"padding": "max_length",
|
| 48 |
+
"patch_size": 4,
|
| 49 |
+
"path_norm": true,
|
| 50 |
+
"problem_type": "single_label_classification",
|
| 51 |
+
"qkv_bias": true,
|
| 52 |
+
"stage_names": [
|
| 53 |
+
"stem",
|
| 54 |
+
"stage1",
|
| 55 |
+
"stage2",
|
| 56 |
+
"stage3",
|
| 57 |
+
"stage4"
|
| 58 |
+
],
|
| 59 |
+
"torch_dtype": "float32",
|
| 60 |
+
"transformers_version": "4.35.2",
|
| 61 |
+
"use_absolute_embeddings": false,
|
| 62 |
+
"window_size": 7
|
| 63 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c87f0dd8282ea3c84ae6af2654bb25a4805ddff1216e453ce12dda7b9f216426
|
| 3 |
+
size 347498816
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"feature_extractor_type": "ViTFeatureExtractor",
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.229,
|
| 14 |
+
0.224,
|
| 15 |
+
0.225
|
| 16 |
+
],
|
| 17 |
+
"resample": 3,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|
runs/events.out.tfevents.1707901374.7046f09e3fd0.195.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3435cc205652cbaa3f3d3a26afad01f476b4e5e16a7d664c650815ce65f8be15
|
| 3 |
+
size 29051
|