Issues with loss, accuracy, and sklearn metrics for multi-label classification (eye/retinal images)
Nadie ha tomado este issue todavía.
Evaluación
- Dificultad
- 4/5
- Tiempo estimado
- 3-5 días
- Aptitud para principiantes
- 12/100
- Tipo de issue
- Error
- Claridad
- Bastante claro
- Estado de actividad
- Estancado
- Stack tecnológico
- jupyter-notebook, python, tensorflow
- Área
- ai, machine-learning
Línea de trabajo
The report is a user's own Colab training script, not code in this repository, so there is no file here to fix. Start from the sigmoid output layer and the binary_crossentropy loss in the model definition, and from the flat prediction range the reporter printed (about 0.495 to 0.4952). Done would be a diagnosis of why the outputs collapse to one value, such as the learning rate, the frozen conv_base, or the ZCA whitening, with an answer posted to the thread.
Escrito por el modelo de indexación a partir del texto del issue.
Descripción
Hello, I am having training issues with this model. I am attempting transfer learning on medical images (eyes/retinas). The training data has 2404 images and the validation data has 1031 images. I am using Google Colab Pro with GPUs. Here is my code:
augmentations
train_datagen = ImageDataGenerator(
rescale=1./255.,
rotation_range=360,
brightness_range=[0.5, 1.5],
zoom_range=[1, 1.2],
zca_whitening=True,
horizontal_flip=True,
vertical_flip=True,
fill_mode='constant'
)
initializing model
input_shape = (256, 256, 3)
dropout_rate = 0.2
number_of_classes = 3
conv_base = EfficientNetB7(weights=None, include_top=False, input_shape=input_shape)
learning rate schedule
initial_learning_rate=2e-6
lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(
initial_learning_rate,
decay_steps=100000,
decay_rate=0.96,
staircase=True
)
model
en_model = models.Sequential()
en_model.add(conv_base)
en_model.add(layers.GlobalMaxPooling2D(name='gap'))
# Avoid overfitting
en_model.add(layers.Dropout(rate=dropout_rate, name='dropout_out'))
# Set number_of_classes to the number of your final predictions
en_model.add(layers.Dense(number_of_classes, activation='sigmoid', name='fc_out')) #replaced softmax with sigmoid
conv_base.trainable = False
en_model.compile(
loss='binary_crossentropy',
optimizer=optimizers.Adam(learning_rate=lr_schedule),
metrics=['accuracy']
)
training
history = en_model.fit(
train_generator,
steps_per_epoch=10,
epochs=100,
validation_data=val_generator,
#validation_steps=None,
validation_freq=1,
verbose=1,
callbacks=[tensorboard_callbacks],
use_multiprocessing=True,
workers=4
)
print('Average test loss: ', np.average(history.history['loss']))
Why is the validation loss/accuracy a straight line? What could be wrong?


Now, the Sklearn metrics. You will see that the numbers repeat for all the metrics and the confusion matrix has zeros! What is going on?
Here are the results for one of the labels.
val_pred = EfficientNet_model_10.predict(val_generator, verbose=1)
y_true = val_generator.labels[:, 0]
y_pred = val_pred[:, 0]
y_pred = [round(x) for x in y_pred]
# y_true are the labels from the validation generator; we have three labels (DR, glaucoma, other)
print(f'Accuracy = {accuracy_score(y_true, y_pred)}')
print(f"F1 = {f1_score(y_true, y_pred, average='micro')}")
print(f"Precision = {precision_score(y_true, y_pred, average='micro')}")
print(f"Recall = {recall_score(y_true, y_pred, average='micro')}")
print('Confusion matrix =')
confusion_matrix(y_true, y_pred)
Output:
Accuracy = 0.7992240543161979
F1 = 0.7992240543161979
Precision = 0.7992240543161979
Recall = 0.7992240543161979
Confusion matrix =
array([[824, 0],
[207, 0]])
One thing that I noticed is that the ranges for the predictions are very narrow:
print(min(val_pred[:, 0:1]))
print(max(val_pred[:, 0:1]))
[0.49519995]
[0.49520218]
Any guidance would be highly appreciated!!
- Lenguaje dominante
- Jupyter Notebook
- Estrellas
- 5.3k
- Forks
- 1.7k
- Métricas de merge de PR
- Sin PR fusionados en 30 d
Preparar el entorno
Este proyecto no incluye contenedor de desarrollo, Dockerfile ni guía de contribución, así que la configuración corre por tu cuenta: empieza por su README y consulta nuestra guía para la primera contribución para los pasos generales.
Primeros pasos
- Lee el issue completo y luego la guía de contribución del proyecto.
- Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
- Haz un fork del repositorio y trabaja en una rama.
- Abre un pull request que haga referencia al número del issue.
Más de tensorflow/tpu
-
Dificultad 2/5 Medio día Aptitud para principiantes 62/100
tensorflow/tpu#3542 ·
-
imagenet_to_gcs.pyAbierto
Dificultad 1/5 Menos de una hora Aptitud para principiantes 78/100
tensorflow/tpu#951 · 2 reacciones ·
-
Broken linkAbierto
Dificultad 1/5 Menos de una hora Aptitud para principiantes 70/100
tensorflow/tpu#908 ·
-
Bug in imagenet_to_gcs.pyAbierto
Dificultad 1/5 Menos de una hora Aptitud para principiantes 62/100
tensorflow/tpu#889 · 1 comentario · 1 reacción ·
-
Round filters Comment has typoAbierto
Dificultad 1/5 Menos de una hora Aptitud para principiantes 78/100
tensorflow/tpu#582 · 1 comentario ·
Todos los issues de tensorflow/tpu
Issues similares
-
bug good first issue help wanted methodology
Dificultad 2/5 1-3 horas Aptitud para principiantes 80/100
oscarbol09/thesisforge#54 ·
-
Agent prompt never mentions the experience load limits, and refused loads only say "not available"Abierto
Dificultad 2/5 1-3 horas Aptitud para principiantes 79/100
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 83/100
AOSSIE-Org/Perspective#191 ·
-
Dificultad 2/5 1-3 horas Aptitud para principiantes 76/100
Los mantenedores suelen responder en 1 día
-
ai-generated
Dificultad 1/5 Menos de una hora Aptitud para principiantes 92/100
Los mantenedores suelen responder en 1 día