ClementWalter

@tf.function(input_signature=(tf.TensorSpec(shape=[None], dtype=tf.string),))
def decode(image_bytes):
"""
Takes a base64 encoded image and returns the preprocessed input tensor ready for the inference 
"""
    # not working on GPU if tf.__version__ < 2.3, see https://github.com/tensorflow/tensorflow/issues/28007
    with tf.device("/cpu:0"):
        input_tensor = tf.map_fn(
            lambda x: preprocessing(tf.io.decode_jpeg(contents=tf.io.decode_base64(x), channels=3))["output_0"],
            image_bytes,

ClementWalter

tf.saved_model.save(
    classifier,
    export_dir="classifier/1",
    signatures={
        "serving_default": decode_and_serve,
        "preprocessing": preprocessing,
    },
)

ClementWalter

response = requests.post(
    "http://localhost:8501/v1/models/classifier:predict",
    json={
        "signature_name": "serving_default",  # can be omitted
        "inputs": {
            "image_bytes": [image.numpy().decode("utf-8") for image in image_bytes][:2],  # batch request
        },
    },
)

ClementWalter

FROM tensorflow/serving

ENV MODEL_BASE_PATH /models
ENV MODEL_NAME classifier

COPY models/classifier /models/classifier

# Fix because base tf_serving_entrypoint.sh does not take $PORT env variable while $PORT is set by Heroku
# CMD is required to run on Heroku
COPY tf_serving_entrypoint.sh /usr/bin/tf_serving_entrypoint.sh

ClementWalter

#!/bin/bash

tensorflow_model_server --port=8500 --rest_api_port="${PORT}" --model_name="${MODEL_NAME}" --model_base_path="${MODEL_BASE_PATH}"/"${MODEL_NAME}" "$@"

ClementWalter

How to deploy a tensorflow model on Heroku with tensorflow serving

After spending minutes or hours playing around with all the wonderful examples available for instance on the Google AI hub, one may wants to deploy one model or another online.

This article presents a fast, optimal and neat way of doing it with Tensorflow Serving and Heroku.

Introduction

ClementWalter

ClementWalter

ClementWalter

How to locally unit-test a contract using Chainlink VRF V2

While it is quite straightforward to use the Chainlink VRF V2 oracle, the Request & Receive Data cycle is a bit less easy to use on a local network (e.g. a hardhat node for testing) when there is no Chainlink node listening to the calls.

This articles aims at giving a step-by-step guide to a working solution for unit-testing a contract using the new Chainlink VRF oracle (Chainlink actually provides an example for the VRF V1 version, see the hardhat starter kit)

Using the Chainlink VRF V2 oracle

ClementWalter

How I deployed an on-chain 10k pfp NFT project for less than 0.1 ETH

Yes, as few as 0.1 ETH or more precisely as you can see on the etherscan contract transaction page for as few as 0.096212736214 ETH, most of it being the contract itself (0.075760070358 ETH), i.e. all the general decoding functions that could be embedded once for all in a library. In other words, the image part of the cost is only about 0.02 ETH!

Of course the gas price at the time of deploying was low (approximately 20 gwei) but even with a fairly high price (say ten times bigger) this would have resulted, for the image part, to only 0.2 ETH.