上傳圖片(0~9)辨識ImportError: Filepath looks like a hdf5 file but h5py ...
import streamlit as stfrom skimage import io
from skimage.transform import resize
import numpy as np
import tensorflow as tf
model = tf.keras.models.load_model('./mnist_model.h5')
uploaded_file = st.file_uploader("上傳圖片(.png)",type="png")
if uploaded_file is not None:
image1 = io.imread(uploaded_file, as_gray=True)
image_resized = resize(image1,(28,28), anti_aliasing=True)
X1 = image_resized.reshape(1,28,28,1)
X1 = np.abs(1-X1)
predictions = model.predict_classes(X1)
st.write(f'預測結果:{predictions}')
st.image(image1)錯誤代碼
ImportError: Filepath looks like a hdf5 file but h5pyis not available上面敘述加入
import h5py在Termainal
輸入
streamlit run D:\scrapytest\img-read.py
這時又出現錯誤
'Sequential' object has no attribute 'predict_classes'
代碼
predictions = model.predict_classes(X1)
st.write(f'預測結果:{predictions}')
st.image(image1)
改成
# 預測
predictions = model.predict(X1)
classes_x = np.argmax(predictions, axis=1)
# 顯示預測結果
st.write(f'預測結果:{classes_x}')
就正常了
參考文章
https://www.cjavapy.com/article/2239/
頁:
[1]