Skip to content

Instantly share code, notes, and snippets.

View erikr's full-sized avatar

Erik Reinertsen erikr

View GitHub Profile
@erikr
erikr / error.txt
Created August 14, 2023 14:43
2023-08-14-error.txt
(base) root@dcc597189383:~/capsule# python src/main.py \
--mode train_image_segmentation \
--images /data/cedars-sinai-histopathology/ileum-image-regions \
--masks /data/cedars-sinai-histopathology/ileum-image-regions-masks-png \
--epochs 3 \
--sample_size 2 \
--batch_size 2 \
--buffer_size 2 \
--random_seed 2023 \
--learning_rate 0.08 \
@erikr
erikr / 2023-08-07-error.txt
Created August 7, 2023 23:08
2023-08-07-error.txt
(base) root@d0f6d976e858:~/capsule# bash train.sh
2023-08-07 23:06:18.187369: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F AVX512_VNNI FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-08-07 23:06:18.301916: I tensorflow/core/util/port.cc:104] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2023-08-07 23:06:18.988996: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64
2023-08-07 23:0
@erikr
erikr / error
Created July 25, 2023 18:25
error
(base) root@93318d67c350:~/capsule# python src/example.py
2023-07-25 18:24:43.540497: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F AVX512_VNNI FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-07-25 18:24:43.652319: I tensorflow/core/util/port.cc:104] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2023-07-25 18:24:44.328614: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /usr/local/nvidia/lib:/usr/local/nvidia/lib64
2023-0
@erikr
erikr / tensorflow-example.py
Created July 24, 2023 23:48
minimal working example
import tensorflow as tf
from tensorflow.keras import datasets, layers, models
(train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data()
# Normalize pixel values to be between 0 and 1
train_images, test_images = train_images / 255.0, test_images / 255.0
model = models.Sequential()