Estoy tratando de recrear la CNN imagen de modelo de reconocimiento de este papel(modelo 1) el uso de diferentes imágenes. Sin embargo, el montaje del modelo devuelve me ResourceExhaustedError en la primera época. El tamaño del lote es bastante pequeña, así que supongo que el problema es con mi definición de modelo que he copiado del papel. Algún consejo sobre lo que debe cambiar con el modelo que será apreciado. Gracias!
#Load dataset
BATCH_SIZE = 32
IMG_SIZE = (244,244)
train_set = tf.keras.preprocessing.image_dataset_from_directory(
main_dir,
shuffle = True,
image_size = IMG_SIZE,
batch_size = BATCH_SIZE)
val_set = tf.keras.preprocessing.image_dataset_from_directory(
main_dir,
shuffle = True,
image_size = IMG_SIZE,
batch_size = BATCH_SIZE)
class_names = train_set.class_names
print(class_names)
#Augment data by flipping image and random rotation
data_augmentation = tf.keras.Sequential([
tf.keras.layers.experimental.preprocessing.RandomFlip('horizontal'),
tf.keras.layers.experimental.preprocessing.RandomRotation(0.2),
])
#Model definition
model = Sequential([
data_augmentation,
tf.keras.layers.experimental.preprocessing.Rescaling(1./255),
Conv2D(filters=64,kernel_size=(4,4), activation='relu'),
Conv2D(filters=32,kernel_size=(3,3), activation='relu'),
AveragePooling2D(pool_size=(4,4)),
Conv2D(filters=32,kernel_size=(3,3), activation='relu'),
Conv2D(filters=32,kernel_size=(3,3), activation='relu'),
Conv2D(filters=32,kernel_size=(3,3), activation='relu'),
AveragePooling2D(pool_size=(2,2)),
Flatten(),
Dense(256, activation='relu'),
Dense(256, activation='relu'),
Dense(128, activation='relu'),
Dense(128, activation='relu'),
Dense(128, activation='tanh'),
Dense(1, activation='softmax')
])
model.compile(optimizer='RMSprop',
loss=keras.losses.CategoricalCrossentropy(from_logits=True),
metrics=[keras.metrics.CategoricalAccuracy()])
history = model.fit(train_set,validation_data=val_set, epochs=150)
De Error después de la colocación del modelo:
ResourceExhaustedError: OOM when allocating tensor with shape[32,32,239,239] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[node gradient_tape/sequential_1/average_pooling2d/AvgPoolGrad (defined at <ipython-input-10-ef749d320491>:1) ]]
nvidia-smi
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 460.91.03 Driver Version: 460.91.03 CUDA Version: 11.2 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 GeForce 940MX Off | 00000000:01:00.0 Off | N/A |
| N/A 46C P0 N/A / N/A | 1938MiB / 2004MiB | 2% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 959 G /usr/lib/xorg/Xorg 97MiB |
| 0 N/A N/A 1270 G /usr/bin/gnome-shell 25MiB |
| 0 N/A N/A 4635 G /usr/lib/firefox/firefox 212MiB |
| 0 N/A N/A 5843 C /usr/bin/python3 1595MiB |
+-----------------------------------------------------------------------------+