在 CPU 中使用 flask 加载预训练的 model

Question

I trained a model using machine learning algorithms, and I want to deploy this model using Flask. but as ı don't have GPU I am using my computer CPU to load the model and that's where I am getting errors. how I can ignore GPU?

load.py

import numpy as np
import keras.models
from keras.models import model_from_json
import tensorflow as tf

def model():
    json_file = open("model.json",'r')
    load_json_model = json_file.read()
    json_file.close()

    load_model = model_from_json(load_json_model)
    load_model.load_weights("model.h5")

    load_model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

errors

2021-02-13 10:48:53.891534: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2021-02-13 10:48:53.907500: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.

self._handle = _dlopen(self._name, mode)
OSError: [WinError 126] The specified module could not be found

Answer 1

It looks like this is a duplicate of this question: Could not load dynamic library 'cudart64_101.dll' on tensorflow CPU-only installation

However, this is a warning not an error. (The log line starts with a W ).

Try the following to resolve the issue:

• Make sure model.h5 and models.json are in the same folder as your script