Adding ONNX file of this model

README.md

@@ -2,6 +2,7 @@
 license: apache-2.0
 tags:
 - slimsam
+- onnx
 ---
 
 # SlimSAM: 0.1% Data Makes Segment Anything Slim

onnx/config.json

@@ -0,0 +1,64 @@
+{
+  "_attn_implementation_autoset": true,
+  "architectures": [
+    "SamModel"
+  ],
+  "initializer_range": 0.02,
+  "mask_decoder_config": {
+    "attention_downsample_rate": 2,
+    "hidden_act": "relu",
+    "hidden_size": 256,
+    "iou_head_depth": 3,
+    "iou_head_hidden_dim": 256,
+    "layer_norm_eps": 1e-06,
+    "mlp_dim": 2048,
+    "model_type": "",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 2,
+    "num_multimask_outputs": 3,
+    "torch_dtype": "float32"
+  },
+  "model_type": "sam",
+  "prompt_encoder_config": {
+    "hidden_act": "gelu",
+    "hidden_size": 256,
+    "image_embedding_size": 64,
+    "image_size": 1024,
+    "layer_norm_eps": 1e-06,
+    "mask_input_channels": 16,
+    "model_type": "",
+    "num_point_embeddings": 4,
+    "patch_size": 16,
+    "torch_dtype": "float32"
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "global_attn_indexes": [
+      2,
+      5,
+      8,
+      11
+    ],
+    "hidden_act": "gelu",
+    "hidden_size": 168,
+    "image_size": 1024,
+    "initializer_range": 1e-10,
+    "layer_norm_eps": 1e-06,
+    "mlp_dim": 696,
+    "mlp_ratio": 4.0,
+    "model_type": "sam_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_pos_feats": 128,
+    "output_channels": 256,
+    "patch_size": 16,
+    "qkv_bias": true,
+    "torch_dtype": "float32",
+    "use_abs_pos": true,
+    "use_rel_pos": true,
+    "window_size": 14
+  }
+}

onnx/preprocessor_config.json

@@ -0,0 +1,35 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "SamImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "mask_pad_size": {
+    "height": 256,
+    "width": 256
+  },
+  "mask_size": {
+    "longest_edge": 256
+  },
+  "pad_size": {
+    "height": 1024,
+    "width": 1024
+  },
+  "processor_class": "SamProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1024
+  }
+}

onnx/prompt_encoder_mask_decoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a873f6dbb7d1e7b8501e9dc97262651ad28192894573b94244ffad1d5fb1f523
+size 16544362

onnx/vision_encoder.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eba021a91cb2999b8ab21b12cddde171b18cb7360432b9315152f42d8e8be0eb
+size 23204762