Add application file

Dresses_DressShape

@@ -0,0 +1 @@
+Subproject commit 1f1afcd6658cbc0fb6238f3a0f6d3aa29593e172

app.py

@@ -0,0 +1,87 @@
+import torch
+from transformers import ViTForImageClassification, ViTFeatureExtractor, AutoConfig
+import gradio as gr
+from PIL import Image
+import os
+import logging
+from safetensors.torch import load_file  # Import safetensors loading function
+
+# Set up logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+
+# Define the directory containing the model files
+model_dir = "."  # Use current directory
+
+# Define paths to the specific model files
+model_path = os.path.join(model_dir, "model.safetensors")
+config_path = os.path.join(model_dir, "config.json")
+preprocessor_path = os.path.join(model_dir, "preprocessor_config.json")
+
+# Check if all required files exist
+for path in [model_path, config_path, preprocessor_path]:
+    if not os.path.exists(path):
+        logging.error(f"File not found: {path}")
+        raise FileNotFoundError(f"Required file not found: {path}")
+    else:
+        logging.info(f"Found file: {path}")
+
+# Load the configuration
+config = AutoConfig.from_pretrained(config_path)
+
+# Ensure the labels are consistent with the model's config
+labels = list(config.id2label.values())
+logging.info(f"Labels: {labels}")
+
+# Load the feature extractor
+feature_extractor = ViTFeatureExtractor.from_pretrained(preprocessor_path)
+
+# Load the model using the safetensors file
+state_dict = load_file(model_path)  # Use safetensors to load the model weights
+model = ViTForImageClassification.from_pretrained(
+    pretrained_model_name_or_path=None,
+    config=config,
+    state_dict=state_dict
+)
+
+# Ensure the model is in evaluation mode
+model.eval()
+logging.info("Model set to evaluation mode")
+
+# Define the prediction function
+def predict(image):
+    logging.info("Starting prediction")
+    logging.info(f"Input image shape: {image.size}")
+    
+    # Preprocess the image
+    logging.info("Preprocessing image")
+    inputs = feature_extractor(images=image, return_tensors="pt")
+    logging.info(f"Preprocessed input shape: {inputs['pixel_values'].shape}")
+    
+    logging.info("Running inference")
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+        probabilities = torch.nn.functional.softmax(logits[0], dim=0)
+    
+    logging.info(f"Raw logits: {logits}")
+    logging.info(f"Probabilities: {probabilities}")
+    
+    # Prepare the output dictionary
+    result = {labels[i]: float(probabilities[i]) for i in range(len(labels))}
+    logging.info(f"Prediction result: {result}")
+    
+    return result
+
+# Set up the Gradio Interface
+logging.info("Setting up Gradio interface")
+gradio_app = gr.Interface(
+    fn=predict, 
+    inputs=gr.Image(type="pil"), 
+    outputs=gr.Label(num_top_classes=6),
+    title="Dress DressShape Classifier"
+)
+
+# Launch the app
+if __name__ == "__main__":
+    logging.info("Launching the app")
+    gradio_app.launch()

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "A-line",
+    "1": "Shift",
+    "2": "Bodycon",
+    "3": "Wrap",
+    "4": "Trapeze",
+    "5": "SweaterDress",
+    "6": "Kimono",
+    "7": "ShirtDress",
+    "8": "Slip",
+    "9": "Kaftan",
+    "10": "Puffball",
+    "11": "Mermaid",
+    "12": "Trumpet",
+    "13": "Column",
+    "14": "PrincessCut",
+    "15": "BiasCut"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "A-line": 0,
+    "BiasCut": 15,
+    "Bodycon": 2,
+    "Column": 13,
+    "Kaftan": 9,
+    "Kimono": 6,
+    "Mermaid": 11,
+    "PrincessCut": 14,
+    "Puffball": 10,
+    "Shift": 1,
+    "ShirtDress": 7,
+    "Slip": 8,
+    "SweaterDress": 5,
+    "Trapeze": 4,
+    "Trumpet": 12,
+    "Wrap": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d320e526a8993080b8a27b2f754ebf70ef0fe4b1f936e91abf6442138a6fbdf0
+size 343267040

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df765db21f4dc2ec6c70334b4cd4beade54420c15c2093248cd4f694c339bdb
+size 5496