0
$\begingroup$

Im trying to learn and get the hang of tflearn. One thing that I have tried to do is save my model, and then reload it. I get an error that says:

W tensorflow/core/framework/op_kernel.cc:975] Not found: Unsuccessful TensorSliceReader constructor: Failed to find any matching files for quicktest.model

Below I have my model as well as that checkpoint file that gets created with the saving of a model. I have googled this error and tried many different file changes but nothing has fixed it.

    import tflearn
    data, labels = load_csv('my_csv', target_column=0, categorical_labels=True, n_classes=2)
    net = tflearn.input_data(shape=[None, 32])
    net = tflearn.fully_connected(net, 32)
    net = tflearn.fully_connected(net, 2, activation='softmax')
    net = tflearn.regression(net)
    model = tflearn.DNN(net)
    model.fit(data, labels, n_epoch=1, batch_size=10, show_metric=True)
    model.save('quicktest.model')
    model.load('quicktest.model')

checkpoint

model_checkpoint_path: "quicktest.model"
all_model_checkpoint_paths: "quicktest.model"
$\endgroup$
1
$\begingroup$

Found out what the issue was:

model.load('filename')

Should actually be:

model.load('./filename')

Hopefully this helps out someone else.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.