Add standard Transformers image preprocessing

README.md

@@ -85,45 +85,32 @@ published classifier and is unnecessary when the input is already cropped.
 
 ## ONNX inference
 
-Install `huggingface_hub`, `onnxruntime`, `numpy`, `opencv-python-headless`, and
-`Pillow`, then run:
+Install `huggingface_hub`, `transformers`, `timm`, `torchvision`, `onnxruntime`,
+`numpy`, and `Pillow`, then run:
 
 ```python
 from huggingface_hub import hf_hub_download
-import cv2
 import numpy as np
 import onnxruntime as ort
 from PIL import Image, ImageOps
+from transformers import AutoImageProcessor
 
 REPO_ID = "electblake/clothing_type_classifier"
 LABELS = ["denim_shorts", "lingerie", "maid", "nurse", "swim_bikini"]
-HEIGHT = 384
-WIDTH = 256
-
 model_path = hf_hub_download(
     REPO_ID,
     "clothing_type-tf_efficientnetv2_s.in21k_ft_in1k.onnx",
 )
 
 image = ImageOps.exif_transpose(Image.open("person.jpg")).convert("RGB")
-image = np.asarray(image)
-scale = min(HEIGHT / image.shape[0], WIDTH / image.shape[1])
-resized_width = round(image.shape[1] * scale)
-resized_height = round(image.shape[0] * scale)
-interpolation = cv2.INTER_AREA if scale < 1 else cv2.INTER_CUBIC
-image = cv2.resize(image, (resized_width, resized_height), interpolation=interpolation)
-
-canvas = np.full((HEIGHT, WIDTH, 3), 127, dtype=np.uint8)
-top = (HEIGHT - resized_height) // 2
-left = (WIDTH - resized_width) // 2
-canvas[top : top + resized_height, left : left + resized_width] = image
-
-image = canvas.astype(np.float32) / 255.0
-image = (image - 0.5) / 0.5
-image = np.transpose(image, (2, 0, 1))[None, ...]
+image_processor = AutoImageProcessor.from_pretrained(REPO_ID)
+inputs = image_processor(image, return_tensors="pt")
 
 session = ort.InferenceSession(model_path, providers=["CPUExecutionProvider"])
-logits = session.run(["logits"], {"image": image})[0][0]
+logits = session.run(
+    ["logits"],
+    {"image": inputs["pixel_values"].numpy()},
+)[0][0]
 probabilities = np.exp(logits - logits.max())
 probabilities /= probabilities.sum()
 

config.json

@@ -24,15 +24,10 @@
       384,
       256
     ],
-    "fixed_input_size": true,
-    "interpolation": "bicubic",
-    "resize_mode": "longest_max_size",
-    "padding": "center",
-    "pad_value": [
-      127,
-      127,
-      127
-    ],
+    "fixed_input_size": true,
+    "interpolation": "bicubic",
+    "crop_pct": 1.0,
+    "crop_mode": "border",
     "mean": [
       0.5,
       0.5,

preprocessor_config.json

@@ -12,17 +12,13 @@
       0.5,
       0.5
     ],
-    "std": [
-      0.5,
-      0.5,
-      0.5
-    ],
-    "resize_mode": "longest_max_size",
-    "padding": "center",
-    "pad_value": [
-      127,
-      127,
-      127
-    ]
-  }
-}
+    "std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "crop_pct": 1.0,
+    "crop_mode": "border"
+  },
+  "image_processor_type": "TimmWrapperImageProcessor"
+}