Skip to content

Instantly share code, notes, and snippets.

@tuna2134

tuna2134/untitled2.ipynb

Last active April 23, 2023 23:36
Show Gist options
  • Save tuna2134/026e959e395ff686af66d974149ea9f7 to your computer and use it in GitHub Desktop.
Save tuna2134/026e959e395ff686af66d974149ea9f7 to your computer and use it in GitHub Desktop.
Download ZIP
ume-or-sakura.ipynb
Display the source blob
Display the rendered blob
Raw
untitled2.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"mount_file_id": "1nacSmSSnoG7X4SEuKJF80npkJHp4rEQO",
"authorship_tag": "ABX9TyOHtlLTFLU7sNLIivYnplcU",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU",
"gpuClass": "standard"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/tuna2134/026e959e395ff686af66d974149ea9f7/untitled2.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "p8OqHCHKPZ2h",
"outputId": "8b13d701-c5cb-4d28-c880-49e6b2ce6c9c"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Collecting icrawler\n",
" Downloading icrawler-0.6.6-py2.py3-none-any.whl (35 kB)\n",
"Requirement already satisfied: six>=1.10.0 in /usr/local/lib/python3.9/dist-packages (from icrawler) (1.16.0)\n",
"Requirement already satisfied: Pillow in /usr/local/lib/python3.9/dist-packages (from icrawler) (8.4.0)\n",
"Requirement already satisfied: beautifulsoup4>=4.4.1 in /usr/local/lib/python3.9/dist-packages (from icrawler) (4.11.2)\n",
"Requirement already satisfied: lxml in /usr/local/lib/python3.9/dist-packages (from icrawler) (4.9.2)\n",
"Requirement already satisfied: requests>=2.9.1 in /usr/local/lib/python3.9/dist-packages (from icrawler) (2.27.1)\n",
"Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.9/dist-packages (from beautifulsoup4>=4.4.1->icrawler) (2.4.1)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests>=2.9.1->icrawler) (2022.12.7)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests>=2.9.1->icrawler) (3.4)\n",
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests>=2.9.1->icrawler) (1.26.15)\n",
"Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests>=2.9.1->icrawler) (2.0.12)\n",
"Installing collected packages: icrawler\n",
"Successfully installed icrawler-0.6.6\n"
]
}
],
"source": [
"!pip install icrawler"
]
},
{
"cell_type": "code",
"source": [
"from icrawler.builtin import GoogleImageCrawler\n",
"\n",
"google_crawler = GoogleImageCrawler(\n",
" feeder_threads=1,\n",
" parser_threads=1,\n",
" downloader_threads=4,\n",
" storage={'root_dir': 'images/ume'})\n",
"google_crawler.crawl(keyword='梅の花', max_num=1000)"
],
"metadata": {
"id": "8lqvrjU5Pee-"
},
"execution_count": 37,
"outputs": []
},
{
"cell_type": "code",
"source": [
"google_crawler = GoogleImageCrawler(\n",
" feeder_threads=1,\n",
" parser_threads=1,\n",
" downloader_threads=4,\n",
" storage={'root_dir': 'images/sakura'}\n",
")\n",
"google_crawler.crawl(keyword='桜の花', max_num=1000)"
],
"metadata": {
"id": "jvyGuE7RQOQr"
},
"execution_count": 38,
"outputs": []
},
{
"cell_type": "code",
"source": [
"from glob import glob\n",
"from PIL import Image"
],
"metadata": {
"id": "l7ewMATnRJ_y"
},
"execution_count": 39,
"outputs": []
},
{
"cell_type": "code",
"source": [
"for name in glob(\"images/**/*.jpg\"):\n",
" img = Image.open(name)\n",
" img = img.resize((224, 224))\n",
" img.save(name)"
],
"metadata": {
"id": "PQKtCzzORWTV"
},
"execution_count": 40,
"outputs": []
},
{
"cell_type": "code",
"source": [
"from tensorflow import keras\n",
"import tensorflow_hub as hub"
],
"metadata": {
"id": "_PgiNqobTQ-c"
},
"execution_count": 41,
"outputs": []
},
{
"cell_type": "code",
"source": [
"model = keras.Sequential([\n",
" hub.KerasLayer(\n",
" \"https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet1k_b0/feature_vector/2\",\n",
" trainable=False\n",
" ),\n",
" keras.layers.Dense(1, activation='sigmoid')\n",
"])\n",
"model.build([None, 224, 224, 3])"
],
"metadata": {
"id": "t76W5RtSTq09"
},
"execution_count": 42,
"outputs": []
},
{
"cell_type": "code",
"source": [
"model.compile(\n",
" optimizer=keras.optimizers.Adam(),\n",
" loss=\"binary_crossentropy\",\n",
" metrics=[\"accuracy\"],\n",
")"
],
"metadata": {
"id": "sfxGRdZxU_E9"
},
"execution_count": 43,
"outputs": []
},
{
"cell_type": "code",
"source": [
"train_datagen = keras.preprocessing.image.ImageDataGenerator(rescale=(1.0 / 255))\n",
"train_generator = train_datagen.flow_from_directory(\n",
" \"./images\",\n",
" target_size=(224, 224),\n",
" batch_size=20,\n",
" class_mode=\"binary\",\n",
")"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "EykP4ScSUfho",
"outputId": "0214ce19-8f6f-4d48-d3c8-4e3fa56d55db"
},
"execution_count": 44,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Found 204 images belonging to 2 classes.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"model.fit(train_generator, epochs=60)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "e5pOSsOdU0r9",
"outputId": "2a4f95c3-06ff-429b-dce8-b7b3676161e0"
},
"execution_count": 45,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/60\n",
"11/11 [==============================] - 10s 124ms/step - loss: 0.6758 - accuracy: 0.5490\n",
"Epoch 2/60\n",
"11/11 [==============================] - 1s 62ms/step - loss: 0.5909 - accuracy: 0.6814\n",
"Epoch 3/60\n",
"11/11 [==============================] - 1s 56ms/step - loss: 0.5302 - accuracy: 0.7745\n",
"Epoch 4/60\n",
"11/11 [==============================] - 1s 75ms/step - loss: 0.4877 - accuracy: 0.7843\n",
"Epoch 5/60\n",
"11/11 [==============================] - 1s 66ms/step - loss: 0.4596 - accuracy: 0.7990\n",
"Epoch 6/60\n",
"11/11 [==============================] - 1s 68ms/step - loss: 0.4343 - accuracy: 0.8284\n",
"Epoch 7/60\n",
"11/11 [==============================] - 1s 70ms/step - loss: 0.4104 - accuracy: 0.8137\n",
"Epoch 8/60\n",
"11/11 [==============================] - 1s 71ms/step - loss: 0.3913 - accuracy: 0.8284\n",
"Epoch 9/60\n",
"11/11 [==============================] - 1s 70ms/step - loss: 0.3787 - accuracy: 0.8578\n",
"Epoch 10/60\n",
"11/11 [==============================] - 1s 61ms/step - loss: 0.3565 - accuracy: 0.8578\n",
"Epoch 11/60\n",
"11/11 [==============================] - 1s 87ms/step - loss: 0.3444 - accuracy: 0.8431\n",
"Epoch 12/60\n",
"11/11 [==============================] - 1s 107ms/step - loss: 0.3304 - accuracy: 0.8725\n",
"Epoch 13/60\n",
"11/11 [==============================] - 1s 89ms/step - loss: 0.3163 - accuracy: 0.8873\n",
"Epoch 14/60\n",
"11/11 [==============================] - 1s 70ms/step - loss: 0.3044 - accuracy: 0.9020\n",
"Epoch 15/60\n",
"11/11 [==============================] - 1s 68ms/step - loss: 0.2941 - accuracy: 0.9020\n",
"Epoch 16/60\n",
"11/11 [==============================] - 1s 68ms/step - loss: 0.2822 - accuracy: 0.9020\n",
"Epoch 17/60\n",
"11/11 [==============================] - 1s 69ms/step - loss: 0.2733 - accuracy: 0.9216\n",
"Epoch 18/60\n",
"11/11 [==============================] - 1s 62ms/step - loss: 0.2668 - accuracy: 0.9265\n",
"Epoch 19/60\n",
"11/11 [==============================] - 1s 71ms/step - loss: 0.2570 - accuracy: 0.9265\n",
"Epoch 20/60\n",
"11/11 [==============================] - 1s 69ms/step - loss: 0.2464 - accuracy: 0.9314\n",
"Epoch 21/60\n",
"11/11 [==============================] - 1s 70ms/step - loss: 0.2401 - accuracy: 0.9363\n",
"Epoch 22/60\n",
"11/11 [==============================] - 1s 68ms/step - loss: 0.2352 - accuracy: 0.9412\n",
"Epoch 23/60\n",
"11/11 [==============================] - 1s 72ms/step - loss: 0.2279 - accuracy: 0.9412\n",
"Epoch 24/60\n",
"11/11 [==============================] - 1s 76ms/step - loss: 0.2238 - accuracy: 0.9412\n",
"Epoch 25/60\n",
"11/11 [==============================] - 1s 102ms/step - loss: 0.2174 - accuracy: 0.9363\n",
"Epoch 26/60\n",
"11/11 [==============================] - 1s 105ms/step - loss: 0.2082 - accuracy: 0.9461\n",
"Epoch 27/60\n",
"11/11 [==============================] - 1s 69ms/step - loss: 0.2047 - accuracy: 0.9461\n",
"Epoch 28/60\n",
"11/11 [==============================] - 1s 68ms/step - loss: 0.1985 - accuracy: 0.9657\n",
"Epoch 29/60\n",
"11/11 [==============================] - 1s 72ms/step - loss: 0.1934 - accuracy: 0.9657\n",
"Epoch 30/60\n",
"11/11 [==============================] - 1s 71ms/step - loss: 0.1898 - accuracy: 0.9657\n",
"Epoch 31/60\n",
"11/11 [==============================] - 1s 73ms/step - loss: 0.1839 - accuracy: 0.9657\n",
"Epoch 32/60\n",
"11/11 [==============================] - 1s 65ms/step - loss: 0.1796 - accuracy: 0.9657\n",
"Epoch 33/60\n",
"11/11 [==============================] - 1s 68ms/step - loss: 0.1763 - accuracy: 0.9657\n",
"Epoch 34/60\n",
"11/11 [==============================] - 1s 73ms/step - loss: 0.1734 - accuracy: 0.9706\n",
"Epoch 35/60\n",
"11/11 [==============================] - 1s 76ms/step - loss: 0.1684 - accuracy: 0.9755\n",
"Epoch 36/60\n",
"11/11 [==============================] - 1s 72ms/step - loss: 0.1656 - accuracy: 0.9804\n",
"Epoch 37/60\n",
"11/11 [==============================] - 1s 71ms/step - loss: 0.1620 - accuracy: 0.9804\n",
"Epoch 38/60\n",
"11/11 [==============================] - 1s 106ms/step - loss: 0.1588 - accuracy: 0.9755\n",
"Epoch 39/60\n",
"11/11 [==============================] - 1s 78ms/step - loss: 0.1531 - accuracy: 0.9804\n",
"Epoch 40/60\n",
"11/11 [==============================] - 1s 66ms/step - loss: 0.1509 - accuracy: 0.9804\n",
"Epoch 41/60\n",
"11/11 [==============================] - 1s 70ms/step - loss: 0.1469 - accuracy: 0.9853\n",
"Epoch 42/60\n",
"11/11 [==============================] - 1s 69ms/step - loss: 0.1446 - accuracy: 0.9853\n",
"Epoch 43/60\n",
"11/11 [==============================] - 1s 70ms/step - loss: 0.1424 - accuracy: 0.9853\n",
"Epoch 44/60\n",
"11/11 [==============================] - 1s 65ms/step - loss: 0.1391 - accuracy: 0.9853\n",
"Epoch 45/60\n",
"11/11 [==============================] - 1s 70ms/step - loss: 0.1355 - accuracy: 0.9902\n",
"Epoch 46/60\n",
"11/11 [==============================] - 1s 66ms/step - loss: 0.1334 - accuracy: 0.9902\n",
"Epoch 47/60\n",
"11/11 [==============================] - 1s 70ms/step - loss: 0.1309 - accuracy: 0.9902\n",
"Epoch 48/60\n",
"11/11 [==============================] - 1s 68ms/step - loss: 0.1284 - accuracy: 0.9902\n",
"Epoch 49/60\n",
"11/11 [==============================] - 1s 102ms/step - loss: 0.1264 - accuracy: 0.9902\n",
"Epoch 50/60\n",
"11/11 [==============================] - 1s 106ms/step - loss: 0.1236 - accuracy: 0.9902\n",
"Epoch 51/60\n",
"11/11 [==============================] - 1s 64ms/step - loss: 0.1217 - accuracy: 0.9902\n",
"Epoch 52/60\n",
"11/11 [==============================] - 1s 72ms/step - loss: 0.1198 - accuracy: 0.9902\n",
"Epoch 53/60\n",
"11/11 [==============================] - 1s 62ms/step - loss: 0.1175 - accuracy: 0.9902\n",
"Epoch 54/60\n",
"11/11 [==============================] - 1s 70ms/step - loss: 0.1159 - accuracy: 0.9902\n",
"Epoch 55/60\n",
"11/11 [==============================] - 1s 72ms/step - loss: 0.1134 - accuracy: 0.9902\n",
"Epoch 56/60\n",
"11/11 [==============================] - 1s 68ms/step - loss: 0.1119 - accuracy: 0.9902\n",
"Epoch 57/60\n",
"11/11 [==============================] - 1s 65ms/step - loss: 0.1096 - accuracy: 0.9902\n",
"Epoch 58/60\n",
"11/11 [==============================] - 1s 70ms/step - loss: 0.1079 - accuracy: 0.9902\n",
"Epoch 59/60\n",
"11/11 [==============================] - 1s 71ms/step - loss: 0.1061 - accuracy: 0.9902\n",
"Epoch 60/60\n",
"11/11 [==============================] - 1s 74ms/step - loss: 0.1041 - accuracy: 0.9902\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.callbacks.History at 0x7f7a0c0c1dc0>"
]
},
"metadata": {},
"execution_count": 45
}
]
},
{
"cell_type": "code",
"source": [
"model.evaluate(train_generator)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "y9SqHWV1Yk6-",
"outputId": "2cc8b1ae-3c3a-4159-d62c-26caf60130ca"
},
"execution_count": 48,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" 2/11 [====>.........................] - ETA: 0s - loss: 0.1082 - accuracy: 0.9750 "
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.9/dist-packages/PIL/Image.py:975: UserWarning: Palette images with Transparency expressed in bytes should be converted to RGBA images\n",
" warnings.warn(\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"11/11 [==============================] - 2s 100ms/step - loss: 0.1025 - accuracy: 0.9902\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"[0.102511465549469, 0.9901960492134094]"
]
},
"metadata": {},
"execution_count": 48
}
]
},
{
"cell_type": "code",
"source": [
"import numpy as np\n",
"\n",
"image = Image.open(\"./images/ume/000001.jpg\").convert(\"RGB\").resize((224, 224))\n",
"image = np.array(image) / 255\n",
"image = np.expand_dims(image, 0)\n",
"predictions = model.predict(image)\n",
"print(predictions)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "XTSgWx4wWK-_",
"outputId": "de0dd6a1-fa72-4df8-9e5f-04edaca8fadf"
},
"execution_count": 49,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"1/1 [==============================] - 0s 26ms/step\n",
"[[0.87228066]]\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"model.save(\"./model\")"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "dgP_yp3AYgw3",
"outputId": "f9c626b1-9ecd-440e-ee65-e3e21f5dd18d"
},
"execution_count": 51,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"WARNING:absl:Found untraced functions such as restored_function_body, restored_function_body, restored_function_body, restored_function_body, restored_function_body while saving (showing 5 of 334). These functions will not be directly callable after loading.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!pip install tf2onnx\n",
"!python -m tf2onnx.convert --saved-model model --output model.onnx"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 857
},
"id": "6yG0AR4RYzNq",
"outputId": "94286d80-97f2-4442-aad9-7f2f0fc7df18"
},
"execution_count": 53,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
"Collecting tf2onnx\n",
" Downloading tf2onnx-1.14.0-py3-none-any.whl (451 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m451.2/451.2 kB\u001b[0m \u001b[31m11.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting flatbuffers<3.0,>=1.12\n",
" Downloading flatbuffers-2.0.7-py2.py3-none-any.whl (26 kB)\n",
"Collecting onnx>=1.4.1\n",
" Downloading onnx-1.13.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (13.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.5/13.5 MB\u001b[0m \u001b[31m98.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: requests in /usr/local/lib/python3.9/dist-packages (from tf2onnx) (2.27.1)\n",
"Requirement already satisfied: six in /usr/local/lib/python3.9/dist-packages (from tf2onnx) (1.16.0)\n",
"Requirement already satisfied: numpy>=1.14.1 in /usr/local/lib/python3.9/dist-packages (from tf2onnx) (1.22.4)\n",
"Requirement already satisfied: typing-extensions>=3.6.2.1 in /usr/local/lib/python3.9/dist-packages (from onnx>=1.4.1->tf2onnx) (4.5.0)\n",
"Requirement already satisfied: protobuf<4,>=3.20.2 in /usr/local/lib/python3.9/dist-packages (from onnx>=1.4.1->tf2onnx) (3.20.3)\n",
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests->tf2onnx) (1.26.15)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests->tf2onnx) (2022.12.7)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests->tf2onnx) (3.4)\n",
"Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests->tf2onnx) (2.0.12)\n",
"Installing collected packages: flatbuffers, onnx, tf2onnx\n",
" Attempting uninstall: flatbuffers\n",
" Found existing installation: flatbuffers 23.3.3\n",
" Uninstalling flatbuffers-23.3.3:\n",
" Successfully uninstalled flatbuffers-23.3.3\n",
"Successfully installed flatbuffers-2.0.7 onnx-1.13.1 tf2onnx-1.14.0\n"
]
},
{
"output_type": "display_data",
"data": {
"application/vnd.colab-display-data+json": {
"pip_warning": {
"packages": [
"flatbuffers"
]
}
}
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"2023-04-23 13:53:21.767874: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
"/usr/lib/python3.9/runpy.py:127: RuntimeWarning: 'tf2onnx.convert' found in sys.modules after import of package 'tf2onnx', but prior to execution of 'tf2onnx.convert'; this may result in unpredictable behaviour\n",
" warn(RuntimeWarning(msg))\n",
"2023-04-23 13:53:24.345123: W tensorflow/core/common_runtime/gpu/gpu_bfc_allocator.cc:47] Overriding orig_value setting because the TF_FORCE_GPU_ALLOW_GROWTH environment variable is set. Original config value was 0.\n",
"2023-04-23 13:53:24,346 - WARNING - '--tag' not specified for saved_model. Using --tag serve\n",
"2023-04-23 13:53:31,810 - INFO - Signatures found in model: [serving_default].\n",
"2023-04-23 13:53:31,811 - WARNING - '--signature_def' not specified, using first signature: serving_default\n",
"2023-04-23 13:53:31,812 - INFO - Output names: ['dense_3']\n",
"2023-04-23 13:53:35,713 - INFO - Using tensorflow=2.12.0, onnx=1.13.1, tf2onnx=1.14.0/8f8d49\n",
"2023-04-23 13:53:35,713 - INFO - Using opset <onnx, 15>\n",
"2023-04-23 13:53:35,971 - INFO - Computed 0 values for constant folding\n",
"2023-04-23 13:53:36,579 - INFO - Optimizing ONNX model\n",
"2023-04-23 13:53:39,241 - INFO - After optimization: BatchNormalization -54 (59->5), Const -194 (394->200), GlobalAveragePool +17 (0->17), Identity -2 (2->0), ReduceMean -17 (17->0), Reshape -16 (16->0), Squeeze +1 (0->1), Transpose -315 (316->1)\n",
"2023-04-23 13:53:39,282 - INFO - \n",
"2023-04-23 13:53:39,282 - INFO - Successfully converted TensorFlow model model to ONNX\n",
"2023-04-23 13:53:39,282 - INFO - Model inputs: ['keras_layer_3_input']\n",
"2023-04-23 13:53:39,283 - INFO - Model outputs: ['dense_3']\n",
"2023-04-23 13:53:39,283 - INFO - ONNX model is saved at model.onnx\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!cp model.onnx drive/MyDrive/models"
],
"metadata": {
"id": "5pGGr7o4ZLSH"
},
"execution_count": 54,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment