commit 56bc99b8341638ce5b7dd080cd8923ace8990ab6
parent 67602639ae9cc4f8107178ef338b3eebc8a8ac28
Author: MTRNord <mtrnord1@gmail.com>
Date: Sun, 25 Sep 2022 17:00:40 +0200
Update model
Diffstat:
7 files changed, 92 insertions(+), 72 deletions(-)
diff --git a/logs/scalars/20220925-164347/train/events.out.tfevents.1664117027.DESKTOP-GS9C68O.13412.0.v2 b/logs/scalars/20220925-164347/train/events.out.tfevents.1664117027.DESKTOP-GS9C68O.13412.0.v2
Binary files differ.
diff --git a/logs/scalars/20220925-164347/validation/events.out.tfevents.1664117032.DESKTOP-GS9C68O.13412.1.v2 b/logs/scalars/20220925-164347/validation/events.out.tfevents.1664117032.DESKTOP-GS9C68O.13412.1.v2
Binary files differ.
diff --git a/models/spam_keras_1664117260.1010098/keras_metadata.pb b/models/spam_keras_1664117260.1010098/keras_metadata.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e77b605f3f16ba228cfd9967c843f229998da2d32e4d689594d2419cd490a8a
+size 11458
diff --git a/models/spam_keras_1664117260.1010098/saved_model.pb b/models/spam_keras_1664117260.1010098/saved_model.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96274eafec3e5ab61071ad31f91f628e58095c1584bc6f0c6ff7f708a57b12ab
+size 124581
diff --git a/models/spam_keras_1664117260.1010098/variables/variables.data-00000-of-00001 b/models/spam_keras_1664117260.1010098/variables/variables.data-00000-of-00001
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f60ab343c2622f28f4cc2126bdb48c6f96436e1dad3ecd143be7dc0dd3ed394
+size 200607
diff --git a/models/spam_keras_1664117260.1010098/variables/variables.index b/models/spam_keras_1664117260.1010098/variables/variables.index
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05d6bf2e4f3b18a41f2c85819faab9b6101b0e5583d6c6410cadccd8089c992
+size 1636
diff --git a/spam-keras.ipynb b/spam-keras.ipynb
@@ -17,12 +17,12 @@
"name": "stderr",
"output_type": "stream",
"text": [
- "2022-09-25 15:56:29.432992: 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 FMA\n",
+ "2022-09-25 16:43:40.699014: 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 FMA\n",
"To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
- "2022-09-25 15:56:29.572721: E tensorflow/stream_executor/cuda/cuda_blas.cc:2981] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
- "2022-09-25 15:56:30.191724: W tensorflow/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\n",
- "2022-09-25 15:56:30.191840: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory\n",
- "2022-09-25 15:56:30.191847: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.\n"
+ "2022-09-25 16:43:41.420174: E tensorflow/stream_executor/cuda/cuda_blas.cc:2981] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+ "2022-09-25 16:43:42.717884: W tensorflow/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\n",
+ "2022-09-25 16:43:42.718077: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory\n",
+ "2022-09-25 16:43:42.718084: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.\n"
]
}
],
@@ -82,7 +82,8 @@
"labels = data['label'].tolist()\n",
"\n",
"# Separate out the sentences and labels into training and test sets\n",
- "training_size = int(len(sentences) * 0.8)\n",
+ "#training_size = int(len(sentences) * 0.8)\n",
+ "training_size = int(len(sentences) * 0.7)\n",
"training_sentences = sentences[0:training_size]\n",
"testing_sentences = sentences[training_size:]\n",
"training_labels = labels[0:training_size]\n",
@@ -147,6 +148,31 @@
"metadata": {},
"outputs": [
{
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "2022-09-25 16:43:45.621721: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
+ "Your kernel may have been built without NUMA support.\n",
+ "2022-09-25 16:43:45.777165: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
+ "Your kernel may have been built without NUMA support.\n",
+ "2022-09-25 16:43:45.777250: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
+ "Your kernel may have been built without NUMA support.\n",
+ "2022-09-25 16:43:45.779091: 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 FMA\n",
+ "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
+ "2022-09-25 16:43:45.780964: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
+ "Your kernel may have been built without NUMA support.\n",
+ "2022-09-25 16:43:45.781071: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
+ "Your kernel may have been built without NUMA support.\n",
+ "2022-09-25 16:43:45.781133: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
+ "Your kernel may have been built without NUMA support.\n",
+ "2022-09-25 16:43:47.267758: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
+ "Your kernel may have been built without NUMA support.\n",
+ "2022-09-25 16:43:47.267970: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
+ "Your kernel may have been built without NUMA support.\n",
+ "2022-09-25 16:43:47.267984: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1700"
+ ]
+ },
+ {
"name": "stdout",
"output_type": "stream",
"text": [
@@ -178,28 +204,10 @@
"name": "stderr",
"output_type": "stream",
"text": [
- "2022-09-25 15:56:32.147052: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
- "Your kernel may have been built without NUMA support.\n",
- "2022-09-25 15:56:32.176653: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
- "Your kernel may have been built without NUMA support.\n",
- "2022-09-25 15:56:32.176739: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
- "Your kernel may have been built without NUMA support.\n",
- "2022-09-25 15:56:32.177492: 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 FMA\n",
- "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
- "2022-09-25 15:56:32.178205: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
- "Your kernel may have been built without NUMA support.\n",
- "2022-09-25 15:56:32.178280: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
- "Your kernel may have been built without NUMA support.\n",
- "2022-09-25 15:56:32.178320: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
- "Your kernel may have been built without NUMA support.\n",
- "2022-09-25 15:56:32.733186: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
- "Your kernel may have been built without NUMA support.\n",
- "2022-09-25 15:56:32.733276: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
- "Your kernel may have been built without NUMA support.\n",
- "2022-09-25 15:56:32.733285: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1700] Could not identify NUMA node of platform GPU id 0, defaulting to 0. Your kernel may not have been built with NUMA support.\n",
- "2022-09-25 15:56:32.733373: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
+ "] Could not identify NUMA node of platform GPU id 0, defaulting to 0. Your kernel may not have been built with NUMA support.\n",
+ "2022-09-25 16:43:47.268086: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:966] could not open file to read NUMA node: /sys/bus/pci/devices/0000:09:00.0/numa_node\n",
"Your kernel may have been built without NUMA support.\n",
- "2022-09-25 15:56:32.733424: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1616] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 5904 MB memory: -> device: 0, name: NVIDIA GeForce RTX 2080 SUPER, pci bus id: 0000:09:00.0, compute capability: 7.5\n"
+ "2022-09-25 16:43:47.268497: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1616] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 5904 MB memory: -> device: 0, name: NVIDIA GeForce RTX 2080 SUPER, pci bus id: 0000:09:00.0, compute capability: 7.5\n"
]
}
],
@@ -253,8 +261,8 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "Average train loss: 0.0944854474812746\n",
- "Average test loss: 0.12808816809207202\n"
+ "Average train loss: 0.09642073692753911\n",
+ "Average test loss: 0.10952864557504655\n"
]
}
],
@@ -284,12 +292,12 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "INFO:tensorflow:Assets written to: ./models/spam_keras_1664114429.671611/assets\n"
+ "INFO:tensorflow:Assets written to: ./models/spam_keras_1664117260.1010098/assets\n"
]
},
{
"data": {
- "image/png": "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",
+ "image/png": "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",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
@@ -323,81 +331,81 @@
"output_type": "stream",
"text": [
"['Greg, can you call me back once you get this?', 'Congrats on your new iPhone! Click here to claim your prize...', 'Really like that new photo of you', 'Did you hear the news today? Terrible what has happened...', 'Attend this free COVID webinar today: Book your session now...', 'Are you coming to the party tonight?', 'Your parcel has gone missing', 'Do not forget to bring friends!', 'You have won a million dollars! Fill out your bank details here...', 'Looking forward to seeing you again', 'oh wow https://github.com/MGCodesandStats/tensorflow-nlp/blob/master/spam%20detection%20tensorflow%20v2.ipynb works really good on spam detection. Guess I go with that as the base model then lol :D', 'ayo', 'Almost all my spam is coming to my non-gmail address actually', 'Oh neat I think I found the sizing sweetspot for my data :D', 'would never click on buttons in gmail :D always expecting there to be a bug in gmail that allows js to grab your google credentials :D XSS via email lol. I am too scared for touching spam in gmail', 'back to cacophony ', 'Room version 11 when', 'skip 11 and go straight to 12', '100 events should clear out any events that might be causing a request to fail lol']\n",
- "1/1 [==============================] - 0s 22ms/step\n",
- "Greg, can you call me back once you get this?\n",
- "[1.527862e-05]\n",
+ "1/1 [==============================] - 0s 21ms/step\n",
+ "Message: \"Greg, can you call me back once you get this?\"\n",
+ "Likeliness of spam in percentage: 0.009471816010773182\n",
"\n",
"\n",
- "Congrats on your new iPhone! Click here to claim your prize...\n",
- "[0.99988234]\n",
+ "Message: \"Congrats on your new iPhone! Click here to claim your prize...\"\n",
+ "Likeliness of spam in percentage: 1.0\n",
"\n",
"\n",
- "Really like that new photo of you\n",
- "[8.316931e-12]\n",
+ "Message: \"Really like that new photo of you\"\n",
+ "Likeliness of spam in percentage: 1.880475686277805e-08\n",
"\n",
"\n",
- "Did you hear the news today? Terrible what has happened...\n",
- "[4.049786e-12]\n",
+ "Message: \"Did you hear the news today? Terrible what has happened...\"\n",
+ "Likeliness of spam in percentage: 5.586861107076402e-07\n",
"\n",
"\n",
- "Attend this free COVID webinar today: Book your session now...\n",
- "[0.9273404]\n",
+ "Message: \"Attend this free COVID webinar today: Book your session now...\"\n",
+ "Likeliness of spam in percentage: 0.9543323516845703\n",
"\n",
"\n",
- "Are you coming to the party tonight?\n",
- "[4.417985e-22]\n",
+ "Message: \"Are you coming to the party tonight?\"\n",
+ "Likeliness of spam in percentage: 4.7180679502156764e-11\n",
"\n",
"\n",
- "Your parcel has gone missing\n",
- "[2.0575136e-08]\n",
+ "Message: \"Your parcel has gone missing\"\n",
+ "Likeliness of spam in percentage: 1.6956087165453937e-06\n",
"\n",
"\n",
- "Do not forget to bring friends!\n",
- "[2.7286378e-09]\n",
+ "Message: \"Do not forget to bring friends!\"\n",
+ "Likeliness of spam in percentage: 1.8877132745842573e-08\n",
"\n",
"\n",
- "You have won a million dollars! Fill out your bank details here...\n",
- "[0.00021836]\n",
+ "Message: \"You have won a million dollars! Fill out your bank details here...\"\n",
+ "Likeliness of spam in percentage: 0.9749099612236023\n",
"\n",
"\n",
- "Looking forward to seeing you again\n",
- "[2.4189583e-05]\n",
+ "Message: \"Looking forward to seeing you again\"\n",
+ "Likeliness of spam in percentage: 0.02266262285411358\n",
"\n",
"\n",
- "oh wow https://github.com/MGCodesandStats/tensorflow-nlp/blob/master/spam%20detection%20tensorflow%20v2.ipynb works really good on spam detection. Guess I go with that as the base model then lol :D\n",
- "[6.2298964e-25]\n",
+ "Message: \"oh wow https://github.com/MGCodesandStats/tensorflow-nlp/blob/master/spam%20detection%20tensorflow%20v2.ipynb works really good on spam detection. Guess I go with that as the base model then lol :D\"\n",
+ "Likeliness of spam in percentage: 1.610198989242387e-20\n",
"\n",
"\n",
- "ayo\n",
- "[6.080875e-05]\n",
+ "Message: \"ayo\"\n",
+ "Likeliness of spam in percentage: 0.0022364065516740084\n",
"\n",
"\n",
- "Almost all my spam is coming to my non-gmail address actually\n",
- "[5.039635e-35]\n",
+ "Message: \"Almost all my spam is coming to my non-gmail address actually\"\n",
+ "Likeliness of spam in percentage: 5.293677780858406e-19\n",
"\n",
"\n",
- "Oh neat I think I found the sizing sweetspot for my data :D\n",
- "[1.8463455e-16]\n",
+ "Message: \"Oh neat I think I found the sizing sweetspot for my data :D\"\n",
+ "Likeliness of spam in percentage: 5.452191733402729e-16\n",
"\n",
"\n",
- "would never click on buttons in gmail :D always expecting there to be a bug in gmail that allows js to grab your google credentials :D XSS via email lol. I am too scared for touching spam in gmail\n",
- "[1.5138318e-19]\n",
+ "Message: \"would never click on buttons in gmail :D always expecting there to be a bug in gmail that allows js to grab your google credentials :D XSS via email lol. I am too scared for touching spam in gmail\"\n",
+ "Likeliness of spam in percentage: 2.011877578043059e-18\n",
"\n",
"\n",
- "back to cacophony \n",
- "[0.07821694]\n",
+ "Message: \"back to cacophony \"\n",
+ "Likeliness of spam in percentage: 0.6930281519889832\n",
"\n",
"\n",
- "Room version 11 when\n",
- "[3.4843818e-12]\n",
+ "Message: \"Room version 11 when\"\n",
+ "Likeliness of spam in percentage: 4.439156597868532e-09\n",
"\n",
"\n",
- "skip 11 and go straight to 12\n",
- "[5.895254e-07]\n",
+ "Message: \"skip 11 and go straight to 12\"\n",
+ "Likeliness of spam in percentage: 1.7528971341107535e-07\n",
"\n",
"\n",
- "100 events should clear out any events that might be causing a request to fail lol\n",
- "[2.1740408e-13]\n",
+ "Message: \"100 events should clear out any events that might be causing a request to fail lol\"\n",
+ "Likeliness of spam in percentage: 5.269173430910712e-10\n",
"\n",
"\n"
]
@@ -437,8 +445,8 @@
"\n",
"# The closer the class is to 1, the more likely that the message is spam\n",
"for x in range(len(text_messages)):\n",
- " print(text_messages[x])\n",
- " print(classes[x])\n",
+ " print(f\"Message: \\\"{text_messages[x]}\\\"\")\n",
+ " print(f\"Likeliness of spam in percentage: {classes[x][0]}\")\n",
" print('\\n')\n"
]
},
