在 Colab OS 中保存并加载 keras tensorflow model 错误消息

Question

I want to run/fit a model, save this and then load it. I would like to take advantage of the SavedModel format and save the entire model and have a solution for this. This is not the HDF5 format, so not the.h5 format, but turns out that even with.h5 it is not working (see answer/comment below). I work in Colab. My code is as follows:

import tensorflow as tf

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D
from tensorflow.keras.preprocessing.image import ImageDataGenerator

import os
import numpy as np
import matplotlib.pyplot as plt
from tensorflow.python.keras.utils.version_utils import training
from tensorflow.keras.optimizers import RMSprop

_URL = 'https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip'

path_to_zip = tf.keras.utils.get_file('cats_and_dogs.zip', origin=_URL, extract=True, cache_subdir = '/tmp/catsdogs')

PATH = os.path.join(os.path.dirname(path_to_zip), 'cats_and_dogs_filtered')

training_dir = os.path.join(PATH, 'train')
validation_dir = os.path.join(PATH, 'validation')


train_image_generator = ImageDataGenerator(rescale=1./255)
validation_image_generator = ImageDataGenerator(rescale=1./255)

train_datagen = train_image_generator.flow_from_directory(
  directory=training_dir,
  target_size=(300, 300),
  shuffle=True,
  batch_size=128,
  class_mode='binary'
)

val_datagen = validation_image_generator.flow_from_directory(
  directory=validation_dir,
  target_size=(300, 300),
  batch_size=128,
  class_mode='binary'
)

model = Sequential([
    Conv2D(16, 3, padding = 'same', activation='relu', input_shape=(300, 300 ,3)),
    MaxPooling2D(),
    Conv2D(32, 3, padding = 'same', activation='relu'),
    MaxPooling2D(),
    Conv2D(64, 3, padding = 'same', activation='relu'),
    MaxPooling2D(),
    Dropout(0.2),
    Flatten(),
    Dense(512, activation='relu'),
    Dense(1)
])

model.compile(optimizer='Adam', loss=tf.keras.losses.BinaryCrossentropy(from_logits=True), metrics=['acc'])

model.summary()

history = model.fit(train_datagen,validation_data=val_datagen,epochs=1)

Now I want to save this model and load it:

model.save('saved_model')

from keras.models import load_model
modeldownload = load_model('saved_model')

However, this does not work (same issue, when I put from keras-models import load_model directly in the beginning where the other imports are). I get the following error message:

OSError: Unable to open file

whole text:

---------------------------------------------------------------------------

OSError                                   Traceback (most recent call last)

<ipython-input-24-1b29d8169144> in <module>()
      1 model.save('saved_model')
----> 2 modeldownload = load_model('saved_model')

4 frames

/usr/local/lib/python3.6/dist-packages/h5py/_hl/files.py in make_fid(name, mode, userblock_size, fapl, fcpl, swmr)
    171         if swmr and swmr_support:
    172             flags |= h5f.ACC_SWMR_READ
--> 173         fid = h5f.open(name, flags, fapl=fapl)
    174     elif mode == 'r+':
    175         fid = h5f.open(name, h5f.ACC_RDWR, fapl=fapl)

h5py/_objects.pyx in h5py._objects.with_phil.wrapper()

h5py/_objects.pyx in h5py._objects.with_phil.wrapper()

h5py/h5f.pyx in h5py.h5f.open()

OSError: Unable to open file (file read failed: time = Wed Jul  8 11:17:03 2020
, filename = 'saved_model', file descriptor = 62, errno = 21, error message = 'Is a directory', buf = 0x7fff87aca540, total read size = 8, bytes this sub-read = 8, bytes actually read = 18446744073709551615, offset = 0)

I tried to play around with us, using different folders, subdirectories and so. But I did not get it working. How to do it correctly? I also tried model.fit(train_datagen,validation_data=val_datagen,epochs=1) , so without the history = , but same error message.

Answer 1

Try this

model.save('modelname.h5') 

Then load model using

from keras.models import load_model  

modeldownload = load_model('modelname.h5')