Upload 2 files

10_gradio_app.py

@@ -0,0 +1,53 @@
+import time
+from urllib.request import urlopen
+
+import gradio as gr
+import numpy as np
+import onnxruntime as ort
+import torch
+from PIL import Image
+
+from imagenet_classes import IMAGENET2012_CLASSES
+
+
+def read_image(image: Image.Image):
+    image = image.convert("RGB")
+    img_numpy = np.array(image).astype(np.float32)
+    img_numpy = img_numpy.transpose(2, 0, 1)
+    img_numpy = np.expand_dims(img_numpy, axis=0)
+    return img_numpy
+
+
+providers = ["CPUExecutionProvider"]
+
+session = ort.InferenceSession("merged_model_compose.onnx", providers=providers)
+
+input_name = session.get_inputs()[0].name
+output_name = session.get_outputs()[0].name
+
+
+def predict(img):
+    output = session.run([output_name], {input_name: read_image(img)})
+    output = torch.from_numpy(output[0])
+
+    top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1), k=5)
+
+    im_classes = list(IMAGENET2012_CLASSES.values())
+    class_names = [im_classes[i] for i in top5_class_indices[0]]
+
+    results = {
+        name: float(prob) for name, prob in zip(class_names, top5_probabilities[0])
+    }
+    return results
+
+
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Label(num_top_classes=5),
+    title="Image Classification with ONNX TensorRT",
+    description="Upload an image to classify it using the ONNX TensorRT model.",
+)
+
+if __name__ == "__main__":
+    iface.launch()

requirements.txt

@@ -0,0 +1,91 @@
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.6.0
+certifi==2024.8.30
+charset-normalizer==3.3.2
+click==8.1.7
+coloredlogs==15.0.1
+contourpy==1.3.0
+cupy-cuda12x==13.3.0
+cycler==0.12.1
+fastapi==0.115.0
+fastrlock==0.8.2
+ffmpy==0.4.0
+filelock==3.16.1
+flatbuffers==24.3.25
+fonttools==4.54.1
+fsspec==2024.9.0
+gradio==4.44.1
+gradio_client==1.3.0
+h11==0.14.0
+httpcore==1.0.6
+httpx==0.27.2
+huggingface-hub==0.25.1
+humanfriendly==10.0
+idna==3.10
+importlib_resources==6.4.5
+Jinja2==3.1.4
+kiwisolver==1.4.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.3
+numpy==2.1.1
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.68
+nvidia-nvtx-cu12==12.1.105
+onnx==1.16.2
+onnxruntime-gpu==1.19.2
+onnxsim==0.4.36
+opencv-python==4.10.0.84
+orjson==3.10.7
+packaging==24.1
+pandas==2.2.3
+pillow==10.4.0
+protobuf==5.28.2
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-multipart==0.0.12
+pytz==2024.2
+PyYAML==6.0.2
+requests==2.32.3
+rich==13.8.1
+ruff==0.6.9
+safetensors==0.4.5
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tensorrt==10.1.0
+tensorrt-cu12==10.1.0
+tensorrt-cu12-bindings==10.1.0
+tensorrt-cu12-libs==10.1.0
+timm==1.0.9
+tomlkit==0.12.0
+torch==2.4.1
+torchvision==0.19.1
+tqdm==4.66.5
+triton==3.0.0
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+uvicorn==0.31.0
+websockets==12.0