Pythonによる機械学習にて学習済みネットワークの呼び出しでのエラー

前提・実現したいこと

Python 3.8でKerasを用いて機械学習を行っています。
画像の学習→判定をするシステムを作成しようとしています。

発生している問題・エラーメッセージ

Traceback (most recent call last):
  File "003train004.py", line 85, in <module>
    model.save_weights('../result/model.weight')
  File "C:\Users\babit\anaconda3\envs\p38\lib\site-packages\keras\engine\saving.py", line 449, in save_wrapper
    save_function(obj, filepath, overwrite, *args, **kwargs)
  File "C:\Users\babit\anaconda3\envs\p38\lib\site-packages\keras\engine\network.py", line 1183, in save_weights
    with h5py.File(filepath, 'w') as f:
  File "C:\Users\babit\anaconda3\envs\p38\lib\site-packages\h5py\_hl\files.py", line 312, in __init__
    fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
  File "C:\Users\babit\anaconda3\envs\p38\lib\site-packages\h5py\_hl\files.py", line 148, in make_fid
    fid = h5f.create(name, h5f.ACC_TRUNC, fapl=fapl, fcpl=fcpl)
  File "h5py\_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
  File "h5py\_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
  File "h5py\h5f.pyx", line 98, in h5py.h5f.create
OSError: Unable to create file (unable to open file: name = '../result/model.weight', errno = 2, error message = 'No such file or directory', flags = 13, o_flags = 302)

該当のソースコード

Python
1import params as P
2import os
3from PIL import Image
4import numpy as np
5num_classes=0
6n=0
7first=True
8for c in sorted(os.listdir(P.datadir)):
9    print(c)
10    for i in os.listdir(os.path.join(P.datadir,c)):
11        im=Image.open(os.path.join(P.datadir,c,i))      
12        img=np.zeros([1,P.W,P.H],dtype='uint8')
13        for x in range(P.W):
14            for y in range(P.H):
15                img[0,x,y]=im.getpixel((y,x))
16        label=np.zeros([1],dtype='uint8')
17        label[0]=num_classes
18        if first:
19            img_array=np.asarray(img)
20            label_array=np.asarray(label)
21            first=False
22        else:
23            img_array=np.append(img_array,img,axis=0)
24            label_array=np.append(label_array,label,axis=0)
25        n+=1
26    num_classes+=1
27th=int(n*0.9)
28train_data=np.zeros([th,P.W,P.H],dtype='uint8')
29test_data=np.zeros([n-th,P.W,P.H],dtype='uint8')
30train_teacher_labels=np.zeros([th],dtype='uint8')
31test_teacher_labels=np.zeros([n-th],dtype='uint8')
32perm=np.random.permutation(n)
33for i in range(n):
34    if i<th:
35        train_data[i]=img_array[perm[i]]
36        train_teacher_labels[i]=label_array[perm[i]]
37    else:
38        test_data[i-th]=img_array[perm[i]]
39        test_teacher_labels[i-th]=label_array[perm[i]]
40import keras
41from keras import backend as Keras
42if Keras.image_data_format()=='channels_first':
43     train_data=train_data.reshape(
44         train_data.shape[0],1,P.W,P.H)
45     test_data=test_data.reshape(
46         test_data.shape[0],1,P.W,P.H)
47     input_shape=(1,P.W,P.H)
48else:
49     train_data=train_data.reshape(
50         train_data.shape[0],P.W,P.H,1)
51     test_data=test_data.reshape(
52         test_data.shape[0],P.W,P.H,1)
53     input_shape=(P.W,P.H,1)
54train_data=train_data.astype('float32')
55test_data=test_data.astype('float32')
56train_data/=255
57test_data/=255
58train_teacher_labels=keras.utils.to_categorical(
59    train_teacher_labels,num_classes)
60test_teacher_labels=keras.utils.to_categorical(
61    test_teacher_labels,num_classes)
62from keras.models import Sequential
63model=Sequential()
64from keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPooling2D
65model.add(
66     Conv2D(32,kernel_size=(3,3),activation='relu',input_shape=input_shape))
67model.add(Conv2D(64,(3,3),activation='relu'))
68model.add(MaxPooling2D(pool_size=(2,2)))
69model.add(Dropout(0.25))
70model.add(Flatten())
71model.add(Dense(128,activation='relu'))
72model.add(Dropout(0.5))
73model.add(Dense(num_classes,activation='softmax'))
74model.summary()
75model.compile(optimizer=keras.optimizers.Adadelta(),
76              loss=keras.losses.categorical_crossentropy,
77              metrics=['accuracy'])
78BATCH_SIZE=256
79EPOCHS=10
80fit_record=model.fit(train_data,train_teacher_labels,
81                     batch_size=BATCH_SIZE,
82                     epochs=EPOCHS,
83                     verbose=1,
84                     validation_data=(test_data,test_teacher_labels))
85model.save_weights('../result/model.weight')
86result_score=model.evaluate(test_data,test_teacher_labels,verbose=0)
87print("loss    ",result_score[0])
88print("accuracy",result_score[1])
89