categorical_crossentropy_example.py 文件源码

def save_prediction():

    model = get_model()
    model.load_weights('model_weights_'+loss_name+'.h5')

    img,mask= gen_random_image()

    y_pred= model.predict(img[None,...].astype(np.float32))[0]

    print('y_pred.shape', y_pred.shape)

    y_pred= y_pred.reshape((IMAGE_H,IMAGE_W,NUMBER_OF_CLASSES))

    print('np.min(mask[:,:,0])', np.min(mask[:,:,0]))
    print('np.max(mask[:,:,1])', np.max(mask[:,:,1]))

    print('np.min(y_pred)', np.min(y_pred))
    print('np.max(y_pred)', np.max(y_pred))

    res = np.zeros((IMAGE_H,5*IMAGE_W,3),np.uint8)
    res[:,:IMAGE_W,:] = img
    res[:,IMAGE_W:2*IMAGE_W,:] = cv2.cvtColor(mask[:,:,0],cv2.COLOR_GRAY2RGB)
    res[:,2*IMAGE_W:3*IMAGE_W,:] = cv2.cvtColor(mask[:,:,1],cv2.COLOR_GRAY2RGB)
    res[:,3*IMAGE_W:4*IMAGE_W,:] = 255*cv2.cvtColor(y_pred[:,:,0],cv2.COLOR_GRAY2RGB)
    res[:,4*IMAGE_W:5*IMAGE_W,:] = 255*cv2.cvtColor(y_pred[:,:,1],cv2.COLOR_GRAY2RGB)

    cv2.imwrite(loss_name+'_result.png', res)