app.py

import streamlit as st

st.write("# URLs for GPU RTX Nvidia 3070 Nsight pages")

urls = {
    "GPUs Ampere architecture" : "https://en.wikipedia.org/wiki/GeForce_30_series",
    "Ray Tracing Interactive": "https://en.wikipedia.org/wiki/Ray_tracing_(graphics)#Interactive_ray_tracing",
    "GeForce RTX 30 Series": "https://www.nvidia.com/en-us/geforce/graphics-cards/30-series/",
}

for name, url in urls.items():
    st.write(f"- [{name}]({url})")


import streamlit as st
import tensorflow as tf
from tensorflow.keras.preprocessing import image
import numpy as np
import pycuda.autoinit
import pycuda.driver as cuda
import tensorrt as trt
import nvtabular as nvt
import nvidia.dali as dali
import nvidia.dali.ops as ops
import nvidia.dali.types as types
import deepstream as ds

# Set up the Streamlit app
st.set_page_config(page_title="Deep Learning Libraries Demo")

# NVIDIA cuDNN
st.header("NVIDIA cuDNN")
st.write("cuDNN is a GPU-accelerated library of primitives for deep neural networks.")

# NVIDIA TensorRT
st.header("NVIDIA TensorRT")
st.write("TensorRT is a high-performance deep learning inference optimizer and runtime for production deployment.")

# NVIDIA Riva
st.header("NVIDIA Riva")
st.write("Riva is a platform for developing engaging and contextual AI-powered conversation apps.")

# NVIDIA DeepStream SDK
st.header("NVIDIA DeepStream SDK")
st.write("DeepStream is a real-time streaming analytics toolkit for AI-based video understanding and multi-sensor processing.")

# NVIDIA DALI
st.header("NVIDIA DALI")
st.write("DALI is a portable, open-source library for decoding and augmenting images and videos to accelerate deep learning applications.")

# Load an image and run it through a pre-trained model
st.header("Example: Image Classification with TensorFlow")
model = tf.keras.applications.MobileNetV2()
img_path = "example.jpg"
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = tf.keras.applications.mobilenet_v2.preprocess_input(x)
preds = model.predict(x)
st.write(f"Predicted class: {tf.keras.applications.mobilenet_v2.decode_predictions(preds, top=1)[0][0][1]}")

# Clean up
del model, img, x, preds