OSError：SavedModel 文件不存在于：model/CPN_Model.h5\{saved_model.pbtxt|saved_model.pb}

Question

I am using python 3.9.10 Traceback (most recent call last): File "C:\Users\AbdiShakra\OneDrive\Documents\Diagnosticc-main\server.py", line 4, in import prediction File "C:\Users\AbdiShakra\OneDrive\Documents\Diagnosticc-main\prediction.py", line 5, in model = keras.models.load_model("model/CPN_Model.h5") File "C:\Users\AbdiShakra\AppData\Local\Programs\Python\Python39\lib\site-packages\keras\saving\save.py", line 205, in load_model return saved_model_load.load(filepath, compile, options) File "C:\Users\AbdiShakra\AppData\Local\Programs\Python\Python39\lib\site-packages\keras\saving\saved_model\load.py", line 108, in load meta_graph_def = tf. internal .saved_model.parse_saved_model(path).meta_graphs[0] File "C:\Users\AbdiShakra\AppData\Local\Programs\Python\Python39\lib\site-packages\tensorflow\python\saved_model\loader_impl.py", line 118, in parse_saved_model raise IOError( OSError: SavedModel file does not exist at: model/CPN_Model.h5{saved_model.pbtxt|saved_model.pb}

Answer 1

To load a model with tf.keras only pass the directory which contains the model, instead of the .pb or .h5 file itself. /tmp/saved_model may be a valid path, while /tmp/saved_model/mymodel.pb is not. Check the documentation to see some example code.