我在Heroku服务器中部署了我的应用程序，并加载了第一页，但是一旦我渲染以预测页面，就会出现内部服务器错误。
我已经检查了关于stackoverflow的几乎所有解决方案，但仍然无法解决，我认为代码中的静态地址/文件中存在一些错误，但无法解决。
Potato.py
function ToDo(){
const [ input, setInput ] = React.useState('')
const [ toDo, setToDo ] = React.useState([])
const [ score, setScore ] = React.useState(0)
const [ speed, setSpeed ] = React.useState(0)
const [ urgency, setUrgency ] = React.useState(0)
return(
<div>
<h2>List of things to do</h2>
<input
value={ input }
onChange={ (e) => setInput( e.target.value ) }/>
<button
onClick={ () => {
setToDo( toDo.concat(input))
setInput('')
}}>Add
</button>
<ul>
{ toDo.map(( task, idTask ) => {
return (
<li
key={idTask}
score={ speed + urgency }>
{task}<br/>
<select onChange={(e) => { setSpeed(Number(e.target.value)) }}>
<option value={1}>slow</option>
<option value={2}>medium</option>
<option value={3}>fast</option>
</select><br/>
<select onChange={(e) => { setUrgency(Number(e.target.value)) }}>
<option value={1}>non-urgent</option>
<option value={3}>urgent</option>
</select>
<span
onClick={
(index) => {
const newTodos = [...toDo]
newTodos.splice(index, 1);
setToDo( newTodos)
}}>
[-------]
</span>
</li>
)
})
}
</ul>
<button onClick={
() => {
const sortMe = [...toDo].sort((a, b) => b - a)
setToDo( sortMe )
}}>Sort!</button>
</div>
)
}
ReactDOM.render(<ToDo/>, document.getElementById('app'));
Label_image.py
from flask import Flask, redirect, url_for, request,render_template
import numpy as np
import label_image as m1
from PIL import Image
import time
import os
app = Flask(__name__,static_url_path='/static')
@app.route('/')
def log():
return render_template('PotatoPrediction.html')
@app.route('/try',methods = ['GET', 'POST'])
def again():
return render_template('PotatoPrediction.html')
@app.route('/predict',methods = ['GET', 'POST'])
def Prediction():
data1 = request.files['image1']
print(data1)
image = "a" + str(time.time()) + ".jpg"
img = Image.open(data1)
path = 'static/' + image
for filename in os.listdir('static/'):
if filename.startswith('a'): # not to remove other images
os.remove('static/' + filename)
img.save(path,'JPEG')
b0,b1,b2 = m1.predict(image)
b0 = b0*100
b1 = b1*100
b2 = b2*100
data = 'Early_Blight_Percentage' +' ' + str(b0) +'\n'+'Late_Blight_Percentage'+' ' + str(b1) + '\n'+ 'Healthy_Leaves_Percentage'+' ' + str(b2) +'\n'
return render_template('prediction.html',a0=b0,a1=b1,a2=b2,image=image)
if __name__ == '__main__':
app.run(debug = True,host ='0.0.0.0')
马铃薯预测
def load_graph(model_file):
graph = tf.Graph()
graph_def = tf.GraphDef()
with open(model_file, "rb") as f:
graph_def.ParseFromString(f.read())
with graph.as_default():
tf.import_graph_def(graph_def)
return graph
def read_tensor_from_image_file(file_name, input_height=299, input_width=299,
input_mean=0, input_std=255):
input_name = "file_reader"
output_name = "normalized"
file_reader = tf.read_file(file_name, input_name)
if file_name.endswith(".png"):
image_reader = tf.image.decode_png(file_reader, channels = 3,
name='png_reader')
elif file_name.endswith(".gif"):
image_reader = tf.squeeze(tf.image.decode_gif(file_reader,
name='gif_reader'))
elif file_name.endswith(".bmp"):
image_reader = tf.image.decode_bmp(file_reader, name='bmp_reader')
else:
image_reader = tf.image.decode_jpeg(file_reader, channels = 3,
name='jpeg_reader')
float_caster = tf.cast(image_reader, tf.float32)
dims_expander = tf.expand_dims(float_caster, 0)
resized = tf.image.resize_bilinear(dims_expander, [input_height, input_width])
normalized = tf.divide(tf.subtract(resized, [input_mean]), [input_std])
sess = tf.Session()
result = sess.run(normalized)
return result
def load_labels(label_file):
label = []
proto_as_ascii_lines = tf.gfile.GFile(label_file).readlines()
for l in proto_as_ascii_lines:
label.append(l.rstrip())
return label
def predict(image):
file_name = "static/" + image
model_file = "model/my_model.pb"
label_file = "model/labels.txt"
input_height = 224
input_width = 224
input_mean = 128
input_std = 128
input_layer = ""
#input_layer = "zero_padding2d_1_input"
#output_layer = "dense_2/Softmax"
graph = load_graph(model_file)
t = read_tensor_from_image_file(file_name,
input_height=input_height,
input_width=input_width,
input_mean=input_mean,
input_std=input_std)
input_name = "import/" + input_layer
output_name = "import/" + output_layer
input_operation = graph.get_operation_by_name(input_name)
output_operation = graph.get_operation_by_name(output_name)
with tf.Session(graph=graph) as sess:
start = time.time()
results = sess.run(output_operation.outputs[0],{input_operation.outputs[0]: t})
end=time.time()
results = np.squeeze(results)
top_k = results.argsort()[-5:][::-1]
labels = load_labels(label_file)
return results[0],results[1],results[2]
预测
<!DOCTYPE html>
<html>
<head>
<title>Page Title</title>
</head>
<body style = "background-color:lightblue">
<h1 align="center">Potato Disease Detection</h1>
<form action = "/predict" method = "post" enctype="multipart/form-data" >
<div>
<label style="margin-left:40%;font-size:25px">Browse Your Image:</label><br/>
<input style="margin-left:40%;font-size:25px" type = "file" name = "image1" accept= ".jpg,.png,jpeg,"/>
</div><br/>
<input style="margin-left:40%;font-size:25px" type = "submit" value = "submit" />
</form>
</body>
</html>
https://potato-image-classifier.herokuapp.com/
这是到应用程序的链接，只要您提交图像就给服务器报错，只要我从终端运行，它就可以在localhost上正常工作。
我需要正确部署它。请帮助我。
我的应用的日志
<!DOCTYPE html>
<html>
<head>
<title>Page Title</title>
</head>
<body style = "background-color:lightblue">
<h1 align="center">Potato Plant Disease Detection </h1>
<div align="center">
<h4>Input Image</h4>
<img src="{{url_for('static', filename=image)}}" height="500px" width = "500px" />
<h4> Early Blight Percentage :- {{a0}} </h4>
<h4> Late Blight Percentage :- {{a1}} </h4>
<h4> Healthy_Leaves Percentage :- {{a2}} </h4>
<form action = "/try" method = "post">
<input style="margin-left:10%;font-size:25px" type = "submit" value = "Try Another Image" />
</form>
</div>
</body>