first commit

README.md

@@ -1,3 +1,52 @@
 ---
-license: unknown
+library_name: transformers.js
+pipeline_tag: depth-estimation
 ---
+
+https://huggingface.co/LiheYoung/depth-anything-small-hf with ONNX weights to be compatible with Transformers.js.
+
+## Usage (Transformers.js)
+
+If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@xenova/transformers) using:
+```bash
+npm i @xenova/transformers
+```
+
+**Example:** Depth estimation with `Xenova/depth-anything-small-hf`.
+
+```js
+import { pipeline } from '@xenova/transformers';
+
+// Create depth-estimation pipeline
+const depth_estimator = await pipeline('depth-estimation', 'Xenova/depth-anything-small-hf');
+
+// Predict depth map for the given image
+const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/bread_small.png';
+const output = await depth_estimator(url);
+// {
+//   predicted_depth: Tensor {
+//     dims: [350, 518],
+//     type: 'float32',
+//     data: Float32Array(181300) [...],
+//     size: 181300
+//   },
+//   depth: RawImage {
+//     data: Uint8Array(271360) [...],
+//     width: 640,
+//     height: 424,
+//     channels: 1
+//   }
+// }
+```
+
+You can visualize the output with:
+
+```js
+output.depth.save('depth.png');
+```
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b253b7ac5ecaae3d1efe0c/Zj77mcNlZS3TmlT5wKaAO.png)
+
+---
+
+Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

config.json

@@ -0,0 +1,53 @@
+{
+  "_commit_hash": "9103bc8e2d785bcfd024e4bfd7e7c4593bc50bba",
+  "_name_or_path": "LiheYoung/depth-anything-small-hf",
+  "architectures": [
+    "DepthAnythingForDepthEstimation"
+  ],
+  "backbone": null,
+  "backbone_config": {
+    "architectures": [
+      "Dinov2Model"
+    ],
+    "hidden_size": 384,
+    "image_size": 518,
+    "model_type": "dinov2",
+    "num_attention_heads": 6,
+    "out_features": [
+      "stage9",
+      "stage10",
+      "stage11",
+      "stage12"
+    ],
+    "out_indices": [
+      9,
+      10,
+      11,
+      12
+    ],
+    "patch_size": 14,
+    "reshape_hidden_states": false,
+    "torch_dtype": "float32"
+  },
+  "fusion_hidden_size": 64,
+  "head_hidden_size": 32,
+  "head_in_index": -1,
+  "initializer_range": 0.02,
+  "model_type": "depth_anything",
+  "neck_hidden_sizes": [
+    48,
+    96,
+    192,
+    384
+  ],
+  "patch_size": 14,
+  "reassemble_factors": [
+    4,
+    2,
+    1,
+    0.5
+  ],
+  "reassemble_hidden_size": 384,
+  "transformers_version": null,
+  "use_pretrained_backbone": false
+}

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c222151fa1a941b7a075efdee44a85bb22e1bc07dce3659a03cb3f4eb53dd213
+size 99170955

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e2ffe9b0396ebd4a0c09b855762b186aab338e79f76531b09777aafc91db84
+size 27524771

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_normalize": true,
+  "do_pad": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "ensure_multiple_of": 14,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "DPTImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "keep_aspect_ratio": true,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 518,
+    "width": 518
+  },
+  "size_divisor": null
+}

quantize_config.json

@@ -0,0 +1,40 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Constant",
+                "Gather",
+                "MatMul",
+                "Transpose",
+                "Equal",
+                "Expand",
+                "Concat",
+                "Sqrt",
+                "Pow",
+                "Relu",
+                "Cast",
+                "Conv",
+                "ConvTranspose",
+                "Slice",
+                "Unsqueeze",
+                "Reshape",
+                "Softmax",
+                "Erf",
+                "Sub",
+                "Identity",
+                "Where",
+                "ConstantOfShape",
+                "Squeeze",
+                "Div",
+                "ReduceMean",
+                "Shape",
+                "Resize",
+                "Mul",
+                "Add"
+            ],
+            "weight_type": "QUInt8"
+        }
+    }
+}