"2023-10-19 20:05:49.157929: I tensorflow/compiler/xla/stream_executor/cuda/cuda_gpu_executor.cc:981] could not open file to read NUMA node: /sys/bus/pci/devices/0000:29:00.0/numa_node\n",
"Your kernel may have been built without NUMA support.\n",
"2023-10-19 20:05:49.276668: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1960] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.\n",
"Skipping registering GPU devices...\n"
]
},
{
"name": "stdout",
"output_type": "stream",
...
...
@@ -171,7 +180,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.3"
"version": "3.11.5"
}
},
"nbformat": 4,
...
...
%% Cell type:code id: tags:
``` python
# imports
import tensorflow as tf
import math
import itertools
import numpy as np
import matplotlib.pyplot as plt
# because lazy
def exp(x):
return math.exp(x)
def tanh(x):
return math.tanh(x)
```
%% Cell type:code id: tags:
``` python
# define Model
class ForwardModel(tf.keras.Model):
def __init__(self, **kwargs):
super().__init__(**kwargs)
def build(self, _): # Create the state of the layer (weights)
for i, j in itertools.product(range(len(dimensions)), range(len(dimensions))):
x = dimensions[i]
y = dimensions[j]
x_coordinates.append(x)
y_coordinates.append(y)
class_val = -1
if model(tf.constant([x,y])) > 0:
class_val = 1
classes.append(class_val)
# Print the results
print("x_coordinates:", x_coordinates)
print("y_coordinates:", y_coordinates)
print("classes:", classes)
```
%% Output
2023-10-19 20:05:49.157929: I tensorflow/compiler/xla/stream_executor/cuda/cuda_gpu_executor.cc:981] could not open file to read NUMA node: /sys/bus/pci/devices/0000:29:00.0/numa_node
Your kernel may have been built without NUMA support.
2023-10-19 20:05:49.276668: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1960] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
No artists with labels found to put in legend. Note that artists whose label start with an underscore are ignored when legend() is called with no argument.