I am not sure what I am doing wrong. I am trying to run ResNet152 on Jupyter Notebooks within a Conda Environment. Here’s my code:

from tensorflow.keras.applications import ResNet50, ResNet101, ResNet152, InceptionResNetV2, DenseNet121
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D, Activation, BatchNormalization
from tensorflow.keras import mixed_precision, layers, models
import tensorflow as tf
from tensorflow.keras.optimizers.schedules import ExponentialDecay
from tensorflow.keras.optimizers import Adam, RMSprop

mixed_precision.set_global_policy('mixed_float16')

base_model = ResNet152(weights='imagenet', include_top=False, input_shape=(256, 256, 3))


for layer in base_model.layers:
    layer.trainable = True 

pooling_layer = layers.GlobalAveragePooling2D()(base_model.output)  # GlobalAveragePooling2D layer
output_layer = layers.Dense(1, activation='sigmoid', name='output_layer')(pooling_layer)

model = Model(inputs=base_model.input, outputs=output_layer)

initial_learning_rate = 0.001
lr_schedule = ExponentialDecay(
    initial_learning_rate,
    decay_steps=50,  # Adjust the decay steps as needed
    decay_rate=0.9,     # Adjust the decay rate as needed
    staircase=False)

optimizer = Adam(learning_rate=lr_schedule)

model.compile(
    optimizer=optimizer,
    loss='binary_crossentropy',
    metrics=['accuracy', tf.keras.metrics.Precision(), tf.keras.metrics.Recall(), tf.keras.metrics.AUC(name='auc')]
)

model.summary()

os.environ['CUDA_VISIBLE_DEVICES'] = '0'
history = model.fit(dataset_batched_withoutnames, epochs=5)

I get the following error:

DNN library is not found.
[[{{node model/conv1_conv/Conv2D}}]] [Op:__inference_train_function_55822]
(there’s a long box but didn’t copy and paste it all)

I went back and downgraded my Tensorflow, CUDA, and cuDNN. I am on CUDA 11.2, cuDNN 8.1.0 and Tensorflow 2.10.0

I went back to my paths and have cleaned it all up and I added all the following to path

I am not sure why this isn’t working. Anybody have any ideas?