-
Notifications
You must be signed in to change notification settings - Fork 310
Open
Open
ResNeXt-50 accuracy is 0%#73
Description
About
ResNeXt-50 accuracy is 0% instead of 77.36%. Are the pre-trained weights here updated?
Steps to reproduce
- Install requirements:
pip install tensorflow-gpu==2.8.0
pip install git+https://github.com/qubvel/classification_models.git
- Load the model as follows:
ResNeXt, preprocess_input = Classifiers.get("resnext50)
model = ResNeXt(
include_top=True,
input_shape=(224, 224, 3),
weights="imagenet"
)
- Use
preprocess_inputas the preprocessing function on the ImageNet validation dataset. - Compile the model and evaluate:
model.compile(
optimizer="sgd",
loss=tf.keras.losses.SparseCategoricalCrossentropy(),
metrics=["accuracy"],
)
_, model_accuracy = model.evaluate(val_batches)
Note that there are no issues with the ResNet models when I follow the above steps.
System info
Python 3.8, Ubuntu 18.04
Metadata
Metadata
Assignees
Labels
No labels