ImageAI/Keras 無法加載 ResNet model

Question

我正在嘗試使用 imageai 庫中的圖像預測工具，但出現以下兩個錯誤...作為初學者，老實說，我無法理解這些錯誤，也找不到任何答案在線有效。 如果有人可以幫我解決它，我將不勝感激。

1.

ImportError: load_weights requires h5py when loading weights from HDF5.

但我確實安裝並更新了 h5py。 正如其他人在過去的問題中所建議的那樣，我還嘗試安裝 h5py==2.10.0 和 cython，但這對我也不起作用。

2.

ValueError: You have specified an incorrect path to the ResNet model file.

我嘗試了幾種不同的方法來編寫路徑，但這仍然行不通。

這是完整的錯誤文本：

Traceback (most recent call last):
  File "C:\Users\MYUSER\Miniconda3\envs\tensorflow\lib\site-packages\imageai\Prediction\__init__.py", line 125, in loadModel
    model = ResNet50(model_path=self.modelPath, model_input=image_input)
  File "C:\Users\MYUSER\Miniconda3\envs\tensorflow\lib\site-packages\imageai\Prediction\ResNet\resnet50.py", line 115, in ResNet50
    model.load_weights(weights_path)
  File "C:\Users\MYUSER\Miniconda3\envs\tensorflow\lib\site-packages\tensorflow\python\keras\engine\training.py", line 2341, in load_weights
    raise ImportError(
ImportError: `load_weights` requires h5py when loading weights from HDF5.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\MYUSER\Current_Working_Directory\brain.py", line 10, in <module>
    prediction.loadModel() 
  File "C:\Users\MYUSER\Miniconda3\envs\tensorflow\lib\site-packages\imageai\Prediction\__init__.py", line 129, in loadModel
    raise ValueError("You have specified an incorrect path to the ResNet model file.")
ValueError: You have specified an incorrect path to the ResNet model file.

這是我的代碼：

from imageai.Prediction import ImagePrediction 
import os 
execution_path=os.getcwd() 

prediction = ImagePrediction()
prediction.setModelTypeAsResNet() 
prediction.setModelPath(os.path.join(execution_path, "resnet50_imagenet_tf.2.0.h5")) 
prediction.loadModel() 

predictions, probabilities = prediction.predictImage(os.path.join(execution_path, "giraffe.jpg"), result_count=5 )

for eachPrediction, eachProbability in zip(predictions, probabilities): 
    print(eachPrediction , " : " , eachProbability)

Answer 1

嘗試這個：

from imageai.Detection import ObjectDetection
import os

execution_path = os.getcwd()

detector = ObjectDetection()
detector.setModelTypeAsRetinaNet()
detector.setModelPath( os.path.join(execution_path , "resnet50_coco_best_v2.1.0.h5"))
detector.loadModel()

detections, objects_path = detector.detectObjectsFromImage(input_image=os.path.join(execution_path , "input.jpg"), output_image_path=os.path.join(execution_path , "output.jpg"), minimum_percentage_probability=10,  extract_detected_objects=True)

for eachObject, eachObjectPath in zip(detections, objects_path):
    print(eachObject["name"] , " : " , eachObject["percentage_probability"], " : ", eachObject["box_points"] )
    print("Object's image saved in " + eachObjectPath)
    print("--------------------------------")

Imagenet 算法對我也不起作用，但使用 coco 算法（在 ImageAI 的 Github 上下載）為我節省了大量時間和精力。

此外，您的代碼不適合 windows，因為它需要文件的直接路徑，否則您將得到確切的錯誤。