pytorch
This commit is contained in:
Adrian Charkiewicz
parent
468abe6648
commit
e762fcd010
|
|
@ -0,0 +1,8 @@
|
|||
# Default ignored files
|
||||
/shelf/
|
||||
/workspace.xml
|
||||
# Editor-based HTTP Client requests
|
||||
/httpRequests/
|
||||
# Datasource local storage ignored files
|
||||
/dataSources/
|
||||
/dataSources.local.xml
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
<component name="InspectionProjectProfileManager">
|
||||
<settings>
|
||||
<option name="USE_PROJECT_PROFILE" value="false" />
|
||||
<version value="1.0" />
|
||||
</settings>
|
||||
</component>
|
||||
|
|
@ -0,0 +1,8 @@
|
|||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<module type="PYTHON_MODULE" version="4">
|
||||
<component name="NewModuleRootManager">
|
||||
<content url="file://$MODULE_DIR$" />
|
||||
<orderEntry type="inheritedJdk" />
|
||||
<orderEntry type="sourceFolder" forTests="false" />
|
||||
</component>
|
||||
</module>
|
||||
|
|
@ -0,0 +1,4 @@
|
|||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9" project-jdk-type="Python SDK" />
|
||||
</project>
|
||||
|
|
@ -0,0 +1,8 @@
|
|||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="ProjectModuleManager">
|
||||
<modules>
|
||||
<module fileurl="file://$PROJECT_DIR$/.idea/ium_444354.iml" filepath="$PROJECT_DIR$/.idea/ium_444354.iml" />
|
||||
</modules>
|
||||
</component>
|
||||
</project>
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<project version="4">
|
||||
<component name="VcsDirectoryMappings">
|
||||
<mapping directory="$PROJECT_DIR$" vcs="Git" />
|
||||
</component>
|
||||
</project>
|
||||
25
Dockerfile
25
Dockerfile
|
|
@ -8,20 +8,27 @@ RUN apt install python3-pip -y
|
|||
RUN apt install unzip -y
|
||||
RUN pip3 install --upgrade pip
|
||||
RUN pip3 install --upgrade Pillow
|
||||
RUN pip3 install kaggle
|
||||
RUN pip3 install pandas
|
||||
RUN pip3 install scikit-learn
|
||||
RUN pip3 install matplotlib
|
||||
RUN mkdir ~/.kaggle/
|
||||
COPY ./script.sh ./
|
||||
RUN chmod a+x ./script.sh
|
||||
RUN pip3 install jovian
|
||||
RUN pip3 install torch
|
||||
RUN pip3 install seaborn
|
||||
RUN pip3 install torchvision
|
||||
|
||||
|
||||
# COPY ./script.sh ./
|
||||
COPY ./runTrain.sh ./runTrain.sh
|
||||
|
||||
# RUN chmod a+x ./script.sh
|
||||
# Create app directory in image
|
||||
WORKDIR /app
|
||||
COPY ./winequality-red.csv ./
|
||||
# Copy init dataset script to /app directory in image
|
||||
COPY ./data_processing.py ./
|
||||
# Download kaggle dataset
|
||||
#RUN kaggle datasets download -d uciml/red-wine-quality-cortez-et-al-2009
|
||||
#RUN unzip -o red-wine-quality-cortez-et-al-2009.zip
|
||||
COPY ./pytorch/pytorch.py ./
|
||||
|
||||
# Script executed after docker run
|
||||
CMD python3 ./data_processing.py
|
||||
# CMD python3 ./pytorch.py
|
||||
COPY ./runTrain.sh ./
|
||||
RUN chmod a+x ./runTrain.sh
|
||||
RUN ./runTrain.sh
|
||||
|
|
|
|||
|
|
@ -0,0 +1,531 @@
|
|||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"id": "e1c5e25d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import torch\n",
|
||||
"import jovian\n",
|
||||
"import torchvision\n",
|
||||
"import matplotlib\n",
|
||||
"import torch.nn as nn\n",
|
||||
"import pandas as pd\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"import seaborn as sns\n",
|
||||
"import torch.nn.functional as F\n",
|
||||
"from torchvision.datasets.utils import download_url\n",
|
||||
"from torch.utils.data import DataLoader, TensorDataset, random_split\n",
|
||||
"import random\n",
|
||||
"import os\n",
|
||||
"import sys"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "c77ff6aa",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"<div>\n",
|
||||
"<style scoped>\n",
|
||||
" .dataframe tbody tr th:only-of-type {\n",
|
||||
" vertical-align: middle;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" .dataframe tbody tr th {\n",
|
||||
" vertical-align: top;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" .dataframe thead th {\n",
|
||||
" text-align: right;\n",
|
||||
" }\n",
|
||||
"</style>\n",
|
||||
"<table border=\"1\" class=\"dataframe\">\n",
|
||||
" <thead>\n",
|
||||
" <tr style=\"text-align: right;\">\n",
|
||||
" <th></th>\n",
|
||||
" <th>fixed acidity</th>\n",
|
||||
" <th>volatile acidity</th>\n",
|
||||
" <th>citric acid</th>\n",
|
||||
" <th>residual sugar</th>\n",
|
||||
" <th>chlorides</th>\n",
|
||||
" <th>free sulfur dioxide</th>\n",
|
||||
" <th>total sulfur dioxide</th>\n",
|
||||
" <th>density</th>\n",
|
||||
" <th>pH</th>\n",
|
||||
" <th>sulphates</th>\n",
|
||||
" <th>alcohol</th>\n",
|
||||
" <th>quality</th>\n",
|
||||
" </tr>\n",
|
||||
" </thead>\n",
|
||||
" <tbody>\n",
|
||||
" <tr>\n",
|
||||
" <th>0</th>\n",
|
||||
" <td>7.4</td>\n",
|
||||
" <td>0.70</td>\n",
|
||||
" <td>0.00</td>\n",
|
||||
" <td>1.9</td>\n",
|
||||
" <td>0.076</td>\n",
|
||||
" <td>11.0</td>\n",
|
||||
" <td>34.0</td>\n",
|
||||
" <td>0.9978</td>\n",
|
||||
" <td>3.51</td>\n",
|
||||
" <td>0.56</td>\n",
|
||||
" <td>9.4</td>\n",
|
||||
" <td>5</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>1</th>\n",
|
||||
" <td>7.8</td>\n",
|
||||
" <td>0.88</td>\n",
|
||||
" <td>0.00</td>\n",
|
||||
" <td>2.6</td>\n",
|
||||
" <td>0.098</td>\n",
|
||||
" <td>25.0</td>\n",
|
||||
" <td>67.0</td>\n",
|
||||
" <td>0.9968</td>\n",
|
||||
" <td>3.20</td>\n",
|
||||
" <td>0.68</td>\n",
|
||||
" <td>9.8</td>\n",
|
||||
" <td>5</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>2</th>\n",
|
||||
" <td>7.8</td>\n",
|
||||
" <td>0.76</td>\n",
|
||||
" <td>0.04</td>\n",
|
||||
" <td>2.3</td>\n",
|
||||
" <td>0.092</td>\n",
|
||||
" <td>15.0</td>\n",
|
||||
" <td>54.0</td>\n",
|
||||
" <td>0.9970</td>\n",
|
||||
" <td>3.26</td>\n",
|
||||
" <td>0.65</td>\n",
|
||||
" <td>9.8</td>\n",
|
||||
" <td>5</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>3</th>\n",
|
||||
" <td>11.2</td>\n",
|
||||
" <td>0.28</td>\n",
|
||||
" <td>0.56</td>\n",
|
||||
" <td>1.9</td>\n",
|
||||
" <td>0.075</td>\n",
|
||||
" <td>17.0</td>\n",
|
||||
" <td>60.0</td>\n",
|
||||
" <td>0.9980</td>\n",
|
||||
" <td>3.16</td>\n",
|
||||
" <td>0.58</td>\n",
|
||||
" <td>9.8</td>\n",
|
||||
" <td>6</td>\n",
|
||||
" </tr>\n",
|
||||
" <tr>\n",
|
||||
" <th>4</th>\n",
|
||||
" <td>7.4</td>\n",
|
||||
" <td>0.70</td>\n",
|
||||
" <td>0.00</td>\n",
|
||||
" <td>1.9</td>\n",
|
||||
" <td>0.076</td>\n",
|
||||
" <td>11.0</td>\n",
|
||||
" <td>34.0</td>\n",
|
||||
" <td>0.9978</td>\n",
|
||||
" <td>3.51</td>\n",
|
||||
" <td>0.56</td>\n",
|
||||
" <td>9.4</td>\n",
|
||||
" <td>5</td>\n",
|
||||
" </tr>\n",
|
||||
" </tbody>\n",
|
||||
"</table>\n",
|
||||
"</div>"
|
||||
],
|
||||
"text/plain": [
|
||||
" fixed acidity volatile acidity citric acid residual sugar chlorides \\\n",
|
||||
"0 7.4 0.70 0.00 1.9 0.076 \n",
|
||||
"1 7.8 0.88 0.00 2.6 0.098 \n",
|
||||
"2 7.8 0.76 0.04 2.3 0.092 \n",
|
||||
"3 11.2 0.28 0.56 1.9 0.075 \n",
|
||||
"4 7.4 0.70 0.00 1.9 0.076 \n",
|
||||
"\n",
|
||||
" free sulfur dioxide total sulfur dioxide density pH sulphates \\\n",
|
||||
"0 11.0 34.0 0.9978 3.51 0.56 \n",
|
||||
"1 25.0 67.0 0.9968 3.20 0.68 \n",
|
||||
"2 15.0 54.0 0.9970 3.26 0.65 \n",
|
||||
"3 17.0 60.0 0.9980 3.16 0.58 \n",
|
||||
"4 11.0 34.0 0.9978 3.51 0.56 \n",
|
||||
"\n",
|
||||
" alcohol quality \n",
|
||||
"0 9.4 5 \n",
|
||||
"1 9.8 5 \n",
|
||||
"2 9.8 5 \n",
|
||||
"3 9.8 6 \n",
|
||||
"4 9.4 5 "
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"dataframe_raw = pd.read_csv(\"winequality-red.csv\")\n",
|
||||
"dataframe_raw.head()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "99f42861",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"(['fixed acidity',\n",
|
||||
" 'volatile acidity',\n",
|
||||
" 'citric acid',\n",
|
||||
" 'residual sugar',\n",
|
||||
" 'chlorides',\n",
|
||||
" 'free sulfur dioxide',\n",
|
||||
" 'total sulfur dioxide',\n",
|
||||
" 'density',\n",
|
||||
" 'pH',\n",
|
||||
" 'sulphates',\n",
|
||||
" 'alcohol'],\n",
|
||||
" ['quality'])"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"input_cols=list(dataframe_raw.columns)[:-1]\n",
|
||||
"output_cols = ['quality']\n",
|
||||
"input_cols,output_cols"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "87011c12",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"(array([[ 7.4 , 0.7 , 0. , ..., 3.51 , 0.56 , 9.4 ],\n",
|
||||
" [ 7.8 , 0.88 , 0. , ..., 3.2 , 0.68 , 9.8 ],\n",
|
||||
" [ 7.8 , 0.76 , 0.04 , ..., 3.26 , 0.65 , 9.8 ],\n",
|
||||
" ...,\n",
|
||||
" [ 6.3 , 0.51 , 0.13 , ..., 3.42 , 0.75 , 11. ],\n",
|
||||
" [ 5.9 , 0.645, 0.12 , ..., 3.57 , 0.71 , 10.2 ],\n",
|
||||
" [ 6. , 0.31 , 0.47 , ..., 3.39 , 0.66 , 11. ]]),\n",
|
||||
" array([[5],\n",
|
||||
" [5],\n",
|
||||
" [5],\n",
|
||||
" ...,\n",
|
||||
" [6],\n",
|
||||
" [5],\n",
|
||||
" [6]], dtype=int64))"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"def dataframe_to_arrays(dataframe):\n",
|
||||
" dataframe1 = dataframe_raw.copy(deep=True)\n",
|
||||
" inputs_array = dataframe1[input_cols].to_numpy()\n",
|
||||
" targets_array = dataframe1[output_cols].to_numpy()\n",
|
||||
" return inputs_array, targets_array\n",
|
||||
"\n",
|
||||
"inputs_array, targets_array = dataframe_to_arrays(dataframe_raw)\n",
|
||||
"inputs_array, targets_array"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "705fb5b7",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"(tensor([[ 7.4000, 0.7000, 0.0000, ..., 3.5100, 0.5600, 9.4000],\n",
|
||||
" [ 7.8000, 0.8800, 0.0000, ..., 3.2000, 0.6800, 9.8000],\n",
|
||||
" [ 7.8000, 0.7600, 0.0400, ..., 3.2600, 0.6500, 9.8000],\n",
|
||||
" ...,\n",
|
||||
" [ 6.3000, 0.5100, 0.1300, ..., 3.4200, 0.7500, 11.0000],\n",
|
||||
" [ 5.9000, 0.6450, 0.1200, ..., 3.5700, 0.7100, 10.2000],\n",
|
||||
" [ 6.0000, 0.3100, 0.4700, ..., 3.3900, 0.6600, 11.0000]]),\n",
|
||||
" tensor([[5.],\n",
|
||||
" [5.],\n",
|
||||
" [5.],\n",
|
||||
" ...,\n",
|
||||
" [6.],\n",
|
||||
" [5.],\n",
|
||||
" [6.]]))"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"inputs = torch.from_numpy(inputs_array).type(torch.float)\n",
|
||||
"targets = torch.from_numpy(targets_array).type(torch.float)\n",
|
||||
"inputs,targets"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "71f14b4a",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"<torch.utils.data.dataset.TensorDataset at 0x1f334183760>"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"dataset = TensorDataset(inputs, targets)\n",
|
||||
"dataset"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "c4f8cd40",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"train_ds, val_ds = random_split(dataset, [1300, 299])\n",
|
||||
"batch_size=50\n",
|
||||
"train_loader = DataLoader(train_ds, batch_size, shuffle=True)\n",
|
||||
"val_loader = DataLoader(val_ds, batch_size)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "56f75067",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"class WineQuality(nn.Module):\n",
|
||||
" def __init__(self):\n",
|
||||
" super().__init__()\n",
|
||||
" self.linear = nn.Linear(input_size,output_size) \n",
|
||||
" \n",
|
||||
" def forward(self, xb): \n",
|
||||
" out = self.linear(xb)\n",
|
||||
" return out\n",
|
||||
" \n",
|
||||
" def training_step(self, batch):\n",
|
||||
" inputs, targets = batch \n",
|
||||
" # Generate predictions\n",
|
||||
" out = self(inputs) \n",
|
||||
" # Calcuate loss\n",
|
||||
" loss = F.l1_loss(out,targets) \n",
|
||||
" return loss\n",
|
||||
" \n",
|
||||
" def validation_step(self, batch):\n",
|
||||
" inputs, targets = batch\n",
|
||||
" # Generate predictions\n",
|
||||
" out = self(inputs)\n",
|
||||
" # Calculate loss\n",
|
||||
" loss = F.l1_loss(out,targets) \n",
|
||||
" return {'val_loss': loss.detach()}\n",
|
||||
" \n",
|
||||
" def validation_epoch_end(self, outputs):\n",
|
||||
" batch_losses = [x['val_loss'] for x in outputs]\n",
|
||||
" epoch_loss = torch.stack(batch_losses).mean() \n",
|
||||
" return {'val_loss': epoch_loss.item()}\n",
|
||||
" \n",
|
||||
" def epoch_end(self, epoch, result, num_epochs):\n",
|
||||
" # Print result every 100th epoch\n",
|
||||
" if (epoch+1) % 100 == 0 or epoch == num_epochs-1:\n",
|
||||
" print(\"Epoch [{}], val_loss: {:.4f}\".format(epoch+1, result['val_loss']))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "57f354ce",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"input_size = len(input_cols)\n",
|
||||
"output_size = len(output_cols)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "4a926cfa",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model=WineQuality()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "3df1733d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def evaluate(model, val_loader):\n",
|
||||
" outputs = [model.validation_step(batch) for batch in val_loader]\n",
|
||||
" return model.validation_epoch_end(outputs)\n",
|
||||
"\n",
|
||||
"def fit(epochs, lr, model, train_loader, val_loader, opt_func=torch.optim.SGD):\n",
|
||||
" history = []\n",
|
||||
" optimizer = opt_func(model.parameters(), lr)\n",
|
||||
" for epoch in range(epochs):\n",
|
||||
" for batch in train_loader:\n",
|
||||
" loss = model.training_step(batch)\n",
|
||||
" loss.backward()\n",
|
||||
" optimizer.step()\n",
|
||||
" optimizer.zero_grad()\n",
|
||||
" result = evaluate(model, val_loader)\n",
|
||||
" model.epoch_end(epoch, result, epochs)\n",
|
||||
" history.append(result)\n",
|
||||
" return history"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "3ed5f872",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Epoch [100], val_loss: 4.1732\n",
|
||||
"Epoch [200], val_loss: 1.6444\n",
|
||||
"Epoch [300], val_loss: 1.4860\n",
|
||||
"Epoch [400], val_loss: 1.4119\n",
|
||||
"Epoch [500], val_loss: 1.3407\n",
|
||||
"Epoch [600], val_loss: 1.2709\n",
|
||||
"Epoch [700], val_loss: 1.2045\n",
|
||||
"Epoch [800], val_loss: 1.1401\n",
|
||||
"Epoch [900], val_loss: 1.0783\n",
|
||||
"Epoch [1000], val_loss: 1.0213\n",
|
||||
"Epoch [1100], val_loss: 0.9678\n",
|
||||
"Epoch [1200], val_loss: 0.9186\n",
|
||||
"Epoch [1300], val_loss: 0.8729\n",
|
||||
"Epoch [1400], val_loss: 0.8320\n",
|
||||
"Epoch [1500], val_loss: 0.7959\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"epochs = 1500\n",
|
||||
"lr = 1e-6\n",
|
||||
"history5 = fit(epochs, lr, model, train_loader, val_loader)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"id": "413ab394",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def predict_single(input, target, model):\n",
|
||||
" inputs = input.unsqueeze(0)\n",
|
||||
" predictions = model(inputs)\n",
|
||||
" prediction = predictions[0].detach()\n",
|
||||
"\n",
|
||||
" return \"Target: \"+str(target)+\"----- Prediction: \"+str(prediction)+\"\\n\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 32,
|
||||
"id": "b1ab4522",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Target: tensor([5.])----- Prediction: tensor([4.9765])\n",
|
||||
"Target: tensor([5.])----- Prediction: tensor([6.6649])\n",
|
||||
"Target: tensor([5.])----- Prediction: tensor([5.2627])\n",
|
||||
"Target: tensor([7.])----- Prediction: tensor([5.7054])\n",
|
||||
"Target: tensor([5.])----- Prediction: tensor([5.1168])\n",
|
||||
"Target: tensor([7.])----- Prediction: tensor([5.3928])\n",
|
||||
"Target: tensor([5.])----- Prediction: tensor([4.8501])\n",
|
||||
"Target: tensor([4.])----- Prediction: tensor([5.4210])\n",
|
||||
"Target: tensor([5.])----- Prediction: tensor([4.6719])\n",
|
||||
"Target: tensor([5.])----- Prediction: tensor([7.8635])\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"#wylosuj 10 próbek predykcji\n",
|
||||
"for i in random.sample(range(0, len(val_ds)), 10):\n",
|
||||
" input_, target = val_ds[i]\n",
|
||||
" print(predict_single(input_, target, model),end=\"\")\n",
|
||||
" "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 36,
|
||||
"id": "a754aaff",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with open(\"result.txt\", \"w+\") as file:\n",
|
||||
" for i in range(0, len(val_ds), 1):\n",
|
||||
" input_, target = val_ds[i]\n",
|
||||
" file.write(str(predict_single(input_, target, model)))"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.7"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
{
|
||||
"notebooks": {}
|
||||
}
|
||||
|
|
@ -0,0 +1,33 @@
|
|||
FROM ubuntu:latest
|
||||
# Install required dependencies
|
||||
RUN apt update
|
||||
RUN apt-get update
|
||||
RUN apt install -y figlet
|
||||
RUN export PATH=”$PATH:/usr/local/bin/python”
|
||||
RUN apt install python3-pip -y
|
||||
RUN apt install unzip -y
|
||||
RUN pip3 install --upgrade pip
|
||||
RUN pip3 install --upgrade Pillow
|
||||
RUN pip3 install pandas
|
||||
RUN pip3 install scikit-learn
|
||||
RUN pip3 install matplotlib
|
||||
RUN pip3 install jovian
|
||||
RUN pip3 install torch
|
||||
RUN pip3 install seaborn
|
||||
RUN pip3 install random
|
||||
RUN pip3 install torchvision
|
||||
|
||||
|
||||
# COPY ./script.sh ./
|
||||
# RUN chmod a+x ./script.sh
|
||||
# Create app directory in image
|
||||
WORKDIR /app
|
||||
COPY ./winequality-red.csv ./
|
||||
# Copy init dataset script to /app directory in image
|
||||
COPY ./pytorch.py ./
|
||||
|
||||
# Script executed after docker run
|
||||
# CMD python3 ./pytorch.py
|
||||
|
||||
RUN chmod o+wrx ./runTrain.sh
|
||||
RUN ./runTrain.sh
|
||||
|
|
@ -2,7 +2,7 @@
|
|||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"execution_count": 18,
|
||||
"id": "e1c5e25d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
@ -18,7 +18,9 @@
|
|||
"import torch.nn.functional as F\n",
|
||||
"from torchvision.datasets.utils import download_url\n",
|
||||
"from torch.utils.data import DataLoader, TensorDataset, random_split\n",
|
||||
"import random"
|
||||
"import random\n",
|
||||
"import os\n",
|
||||
"import sys"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -295,7 +297,7 @@
|
|||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"<torch.utils.data.dataset.TensorDataset at 0x16db5c32af0>"
|
||||
"<torch.utils.data.dataset.TensorDataset at 0x1f334183760>"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
|
|
@ -366,7 +368,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"execution_count": 9,
|
||||
"id": "57f354ce",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
@ -377,7 +379,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"execution_count": 10,
|
||||
"id": "4a926cfa",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
@ -387,7 +389,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"execution_count": 11,
|
||||
"id": "3df1733d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
@ -413,7 +415,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"execution_count": 12,
|
||||
"id": "3ed5f872",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
|
|
@ -421,21 +423,21 @@
|
|||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Epoch [100], val_loss: 5.1117\n",
|
||||
"Epoch [200], val_loss: 1.7651\n",
|
||||
"Epoch [300], val_loss: 1.4800\n",
|
||||
"Epoch [400], val_loss: 1.3942\n",
|
||||
"Epoch [500], val_loss: 1.3119\n",
|
||||
"Epoch [600], val_loss: 1.2326\n",
|
||||
"Epoch [700], val_loss: 1.1571\n",
|
||||
"Epoch [800], val_loss: 1.0863\n",
|
||||
"Epoch [900], val_loss: 1.0224\n",
|
||||
"Epoch [1000], val_loss: 0.9642\n",
|
||||
"Epoch [1100], val_loss: 0.9100\n",
|
||||
"Epoch [1200], val_loss: 0.8617\n",
|
||||
"Epoch [1300], val_loss: 0.8200\n",
|
||||
"Epoch [1400], val_loss: 0.7816\n",
|
||||
"Epoch [1500], val_loss: 0.7484\n"
|
||||
"Epoch [100], val_loss: 4.1732\n",
|
||||
"Epoch [200], val_loss: 1.6444\n",
|
||||
"Epoch [300], val_loss: 1.4860\n",
|
||||
"Epoch [400], val_loss: 1.4119\n",
|
||||
"Epoch [500], val_loss: 1.3407\n",
|
||||
"Epoch [600], val_loss: 1.2709\n",
|
||||
"Epoch [700], val_loss: 1.2045\n",
|
||||
"Epoch [800], val_loss: 1.1401\n",
|
||||
"Epoch [900], val_loss: 1.0783\n",
|
||||
"Epoch [1000], val_loss: 1.0213\n",
|
||||
"Epoch [1100], val_loss: 0.9678\n",
|
||||
"Epoch [1200], val_loss: 0.9186\n",
|
||||
"Epoch [1300], val_loss: 0.8729\n",
|
||||
"Epoch [1400], val_loss: 0.8320\n",
|
||||
"Epoch [1500], val_loss: 0.7959\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -447,7 +449,7 @@
|
|||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 19,
|
||||
"execution_count": 27,
|
||||
"id": "413ab394",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
|
|
@ -456,15 +458,13 @@
|
|||
" inputs = input.unsqueeze(0)\n",
|
||||
" predictions = model(inputs)\n",
|
||||
" prediction = predictions[0].detach()\n",
|
||||
" #print(\"Input:\", input)\n",
|
||||
" #print(\"Target:\", target)\n",
|
||||
" #print(\"Prediction:\", prediction)\n",
|
||||
" print(\"Target: \", target, \"----- Prediction: \", prediction)"
|
||||
"\n",
|
||||
" return \"Target: \"+str(target)+\"----- Prediction: \"+str(prediction)+\"\\n\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 24,
|
||||
"execution_count": 32,
|
||||
"id": "b1ab4522",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
|
|
@ -472,16 +472,16 @@
|
|||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Target: tensor([6.]) ----- Prediction: tensor([5.1011])\n",
|
||||
"Target: tensor([6.]) ----- Prediction: tensor([7.1398])\n",
|
||||
"Target: tensor([5.]) ----- Prediction: tensor([5.1009])\n",
|
||||
"Target: tensor([6.]) ----- Prediction: tensor([5.2282])\n",
|
||||
"Target: tensor([5.]) ----- Prediction: tensor([4.8219])\n",
|
||||
"Target: tensor([6.]) ----- Prediction: tensor([4.8082])\n",
|
||||
"Target: tensor([7.]) ----- Prediction: tensor([5.0764])\n",
|
||||
"Target: tensor([5.]) ----- Prediction: tensor([6.3668])\n",
|
||||
"Target: tensor([6.]) ----- Prediction: tensor([5.0642])\n",
|
||||
"Target: tensor([5.]) ----- Prediction: tensor([5.4656])\n"
|
||||
"Target: tensor([5.])----- Prediction: tensor([4.9765])\n",
|
||||
"Target: tensor([5.])----- Prediction: tensor([6.6649])\n",
|
||||
"Target: tensor([5.])----- Prediction: tensor([5.2627])\n",
|
||||
"Target: tensor([7.])----- Prediction: tensor([5.7054])\n",
|
||||
"Target: tensor([5.])----- Prediction: tensor([5.1168])\n",
|
||||
"Target: tensor([7.])----- Prediction: tensor([5.3928])\n",
|
||||
"Target: tensor([5.])----- Prediction: tensor([4.8501])\n",
|
||||
"Target: tensor([4.])----- Prediction: tensor([5.4210])\n",
|
||||
"Target: tensor([5.])----- Prediction: tensor([4.6719])\n",
|
||||
"Target: tensor([5.])----- Prediction: tensor([7.8635])\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
|
|
@ -489,17 +489,22 @@
|
|||
"#wylosuj 10 próbek predykcji\n",
|
||||
"for i in random.sample(range(0, len(val_ds)), 10):\n",
|
||||
" input_, target = val_ds[i]\n",
|
||||
" predict_single(input_, target, model)\n",
|
||||
" print(predict_single(input_, target, model),end=\"\")\n",
|
||||
" "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "0237aad2",
|
||||
"execution_count": 36,
|
||||
"id": "a754aaff",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
"source": [
|
||||
"with open(\"result.txt\", \"w+\") as file:\n",
|
||||
" for i in range(0, len(val_ds), 1):\n",
|
||||
" input_, target = val_ds[i]\n",
|
||||
" file.write(str(predict_single(input_, target, model)))"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
|
@ -0,0 +1,187 @@
|
|||
#!/usr/bin/env python
|
||||
# coding: utf-8
|
||||
|
||||
# In[18]:
|
||||
|
||||
|
||||
import torch
|
||||
import jovian
|
||||
import torchvision
|
||||
import matplotlib
|
||||
import torch.nn as nn
|
||||
import pandas as pd
|
||||
import matplotlib.pyplot as plt
|
||||
import seaborn as sns
|
||||
import torch.nn.functional as F
|
||||
from torchvision.datasets.utils import download_url
|
||||
from torch.utils.data import DataLoader, TensorDataset, random_split
|
||||
import random
|
||||
import os
|
||||
import sys
|
||||
|
||||
|
||||
# In[2]:
|
||||
|
||||
|
||||
dataframe_raw = pd.read_csv("winequality-red.csv")
|
||||
dataframe_raw.head()
|
||||
|
||||
|
||||
# In[3]:
|
||||
|
||||
|
||||
input_cols=list(dataframe_raw.columns)[:-1]
|
||||
output_cols = ['quality']
|
||||
input_cols,output_cols
|
||||
|
||||
|
||||
# In[4]:
|
||||
|
||||
|
||||
def dataframe_to_arrays(dataframe):
|
||||
dataframe1 = dataframe_raw.copy(deep=True)
|
||||
inputs_array = dataframe1[input_cols].to_numpy()
|
||||
targets_array = dataframe1[output_cols].to_numpy()
|
||||
return inputs_array, targets_array
|
||||
|
||||
inputs_array, targets_array = dataframe_to_arrays(dataframe_raw)
|
||||
inputs_array, targets_array
|
||||
|
||||
|
||||
# In[5]:
|
||||
|
||||
|
||||
inputs = torch.from_numpy(inputs_array).type(torch.float)
|
||||
targets = torch.from_numpy(targets_array).type(torch.float)
|
||||
inputs,targets
|
||||
|
||||
|
||||
# In[6]:
|
||||
|
||||
|
||||
dataset = TensorDataset(inputs, targets)
|
||||
dataset
|
||||
|
||||
|
||||
# In[7]:
|
||||
|
||||
|
||||
train_ds, val_ds = random_split(dataset, [1300, 299])
|
||||
batch_size=50
|
||||
train_loader = DataLoader(train_ds, batch_size, shuffle=True)
|
||||
val_loader = DataLoader(val_ds, batch_size)
|
||||
|
||||
|
||||
# In[8]:
|
||||
|
||||
|
||||
class WineQuality(nn.Module):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
self.linear = nn.Linear(input_size,output_size)
|
||||
|
||||
def forward(self, xb):
|
||||
out = self.linear(xb)
|
||||
return out
|
||||
|
||||
def training_step(self, batch):
|
||||
inputs, targets = batch
|
||||
# Generate predictions
|
||||
out = self(inputs)
|
||||
# Calcuate loss
|
||||
loss = F.l1_loss(out,targets)
|
||||
return loss
|
||||
|
||||
def validation_step(self, batch):
|
||||
inputs, targets = batch
|
||||
# Generate predictions
|
||||
out = self(inputs)
|
||||
# Calculate loss
|
||||
loss = F.l1_loss(out,targets)
|
||||
return {'val_loss': loss.detach()}
|
||||
|
||||
def validation_epoch_end(self, outputs):
|
||||
batch_losses = [x['val_loss'] for x in outputs]
|
||||
epoch_loss = torch.stack(batch_losses).mean()
|
||||
return {'val_loss': epoch_loss.item()}
|
||||
|
||||
def epoch_end(self, epoch, result, num_epochs):
|
||||
# Print result every 100th epoch
|
||||
if (epoch+1) % 100 == 0 or epoch == num_epochs-1:
|
||||
print("Epoch [{}], val_loss: {:.4f}".format(epoch+1, result['val_loss']))
|
||||
|
||||
|
||||
# In[9]:
|
||||
|
||||
|
||||
input_size = len(input_cols)
|
||||
output_size = len(output_cols)
|
||||
|
||||
|
||||
# In[10]:
|
||||
|
||||
|
||||
model=WineQuality()
|
||||
|
||||
|
||||
# In[11]:
|
||||
|
||||
|
||||
def evaluate(model, val_loader):
|
||||
outputs = [model.validation_step(batch) for batch in val_loader]
|
||||
return model.validation_epoch_end(outputs)
|
||||
|
||||
def fit(epochs, lr, model, train_loader, val_loader, opt_func=torch.optim.SGD):
|
||||
history = []
|
||||
optimizer = opt_func(model.parameters(), lr)
|
||||
for epoch in range(epochs):
|
||||
for batch in train_loader:
|
||||
loss = model.training_step(batch)
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
optimizer.zero_grad()
|
||||
result = evaluate(model, val_loader)
|
||||
model.epoch_end(epoch, result, epochs)
|
||||
history.append(result)
|
||||
return history
|
||||
|
||||
|
||||
# In[12]:
|
||||
|
||||
|
||||
epochs = 1500
|
||||
lr = 1e-6
|
||||
history5 = fit(epochs, lr, model, train_loader, val_loader)
|
||||
|
||||
|
||||
# In[27]:
|
||||
|
||||
|
||||
def predict_single(input, target, model):
|
||||
inputs = input.unsqueeze(0)
|
||||
predictions = model(inputs)
|
||||
prediction = predictions[0].detach()
|
||||
|
||||
return "Target: "+str(target)+"----- Prediction: "+str(prediction)+"\n"
|
||||
|
||||
|
||||
# In[32]:
|
||||
|
||||
|
||||
#wylosuj 10 próbek predykcji
|
||||
for i in random.sample(range(0, len(val_ds)), 10):
|
||||
input_, target = val_ds[i]
|
||||
print(predict_single(input_, target, model),end="")
|
||||
|
||||
|
||||
|
||||
# In[36]:
|
||||
|
||||
|
||||
with open("result.txt", "w+") as file:
|
||||
for i in range(0, len(val_ds), 1):
|
||||
input_, target = val_ds[i]
|
||||
file.write(str(predict_single(input_, target, model)))
|
||||
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,299 @@
|
|||
Target: tensor([4.])----- Prediction: tensor([2.5912])
|
||||
Target: tensor([7.])----- Prediction: tensor([5.3811])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.4516])
|
||||
Target: tensor([5.])----- Prediction: tensor([6.6527])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.6947])
|
||||
Target: tensor([7.])----- Prediction: tensor([3.0992])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.5280])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.8694])
|
||||
Target: tensor([5.])----- Prediction: tensor([10.5723])
|
||||
Target: tensor([6.])----- Prediction: tensor([1.5417])
|
||||
Target: tensor([6.])----- Prediction: tensor([1.5702])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.8206])
|
||||
Target: tensor([6.])----- Prediction: tensor([5.5910])
|
||||
Target: tensor([7.])----- Prediction: tensor([2.1009])
|
||||
Target: tensor([5.])----- Prediction: tensor([1.9532])
|
||||
Target: tensor([6.])----- Prediction: tensor([5.4789])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.4121])
|
||||
Target: tensor([6.])----- Prediction: tensor([5.6153])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.7008])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.4302])
|
||||
Target: tensor([5.])----- Prediction: tensor([11.2693])
|
||||
Target: tensor([7.])----- Prediction: tensor([2.9486])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.0228])
|
||||
Target: tensor([5.])----- Prediction: tensor([5.8602])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.8908])
|
||||
Target: tensor([6.])----- Prediction: tensor([10.1888])
|
||||
Target: tensor([5.])----- Prediction: tensor([6.6399])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.7961])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.8239])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.6467])
|
||||
Target: tensor([6.])----- Prediction: tensor([5.6153])
|
||||
Target: tensor([5.])----- Prediction: tensor([4.1886])
|
||||
Target: tensor([6.])----- Prediction: tensor([7.4703])
|
||||
Target: tensor([5.])----- Prediction: tensor([6.7674])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.9402])
|
||||
Target: tensor([5.])----- Prediction: tensor([10.8020])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.7203])
|
||||
Target: tensor([6.])----- Prediction: tensor([4.3365])
|
||||
Target: tensor([6.])----- Prediction: tensor([4.0502])
|
||||
Target: tensor([5.])----- Prediction: tensor([5.1851])
|
||||
Target: tensor([7.])----- Prediction: tensor([3.8488])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.4501])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.9132])
|
||||
Target: tensor([7.])----- Prediction: tensor([3.3335])
|
||||
Target: tensor([5.])----- Prediction: tensor([7.8335])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.5696])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.7571])
|
||||
Target: tensor([6.])----- Prediction: tensor([5.0917])
|
||||
Target: tensor([5.])----- Prediction: tensor([12.2102])
|
||||
Target: tensor([5.])----- Prediction: tensor([7.3395])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.2568])
|
||||
Target: tensor([7.])----- Prediction: tensor([3.2961])
|
||||
Target: tensor([5.])----- Prediction: tensor([1.6766])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.5993])
|
||||
Target: tensor([6.])----- Prediction: tensor([5.0940])
|
||||
Target: tensor([5.])----- Prediction: tensor([9.0951])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.0024])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.1072])
|
||||
Target: tensor([7.])----- Prediction: tensor([7.0583])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.1533])
|
||||
Target: tensor([5.])----- Prediction: tensor([11.8913])
|
||||
Target: tensor([5.])----- Prediction: tensor([1.7950])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.5572])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.9728])
|
||||
Target: tensor([7.])----- Prediction: tensor([2.1861])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.7599])
|
||||
Target: tensor([6.])----- Prediction: tensor([4.5269])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.1787])
|
||||
Target: tensor([7.])----- Prediction: tensor([2.6388])
|
||||
Target: tensor([5.])----- Prediction: tensor([6.9238])
|
||||
Target: tensor([7.])----- Prediction: tensor([4.8372])
|
||||
Target: tensor([6.])----- Prediction: tensor([4.9583])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.8367])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.2148])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.2810])
|
||||
Target: tensor([5.])----- Prediction: tensor([5.5056])
|
||||
Target: tensor([6.])----- Prediction: tensor([1.5980])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.2662])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.0195])
|
||||
Target: tensor([5.])----- Prediction: tensor([10.5990])
|
||||
Target: tensor([7.])----- Prediction: tensor([2.8631])
|
||||
Target: tensor([5.])----- Prediction: tensor([8.1595])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.9324])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.2511])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.6911])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.7448])
|
||||
Target: tensor([4.])----- Prediction: tensor([1.5203])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.9098])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.7416])
|
||||
Target: tensor([7.])----- Prediction: tensor([2.1332])
|
||||
Target: tensor([6.])----- Prediction: tensor([6.7936])
|
||||
Target: tensor([5.])----- Prediction: tensor([5.2619])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.4828])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.9184])
|
||||
Target: tensor([7.])----- Prediction: tensor([3.9367])
|
||||
Target: tensor([6.])----- Prediction: tensor([4.4000])
|
||||
Target: tensor([5.])----- Prediction: tensor([4.0671])
|
||||
Target: tensor([8.])----- Prediction: tensor([8.0165])
|
||||
Target: tensor([5.])----- Prediction: tensor([4.5995])
|
||||
Target: tensor([6.])----- Prediction: tensor([7.7532])
|
||||
Target: tensor([5.])----- Prediction: tensor([9.6909])
|
||||
Target: tensor([5.])----- Prediction: tensor([5.7997])
|
||||
Target: tensor([6.])----- Prediction: tensor([8.8374])
|
||||
Target: tensor([6.])----- Prediction: tensor([4.0067])
|
||||
Target: tensor([5.])----- Prediction: tensor([10.5642])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.3271])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.0700])
|
||||
Target: tensor([6.])----- Prediction: tensor([1.7528])
|
||||
Target: tensor([6.])----- Prediction: tensor([5.2573])
|
||||
Target: tensor([7.])----- Prediction: tensor([3.1217])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.4221])
|
||||
Target: tensor([4.])----- Prediction: tensor([2.1967])
|
||||
Target: tensor([6.])----- Prediction: tensor([1.8576])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.9776])
|
||||
Target: tensor([4.])----- Prediction: tensor([1.8588])
|
||||
Target: tensor([7.])----- Prediction: tensor([8.4651])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.0248])
|
||||
Target: tensor([5.])----- Prediction: tensor([9.5106])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.3674])
|
||||
Target: tensor([7.])----- Prediction: tensor([7.9203])
|
||||
Target: tensor([6.])----- Prediction: tensor([5.6564])
|
||||
Target: tensor([5.])----- Prediction: tensor([4.9836])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.6858])
|
||||
Target: tensor([6.])----- Prediction: tensor([4.3583])
|
||||
Target: tensor([7.])----- Prediction: tensor([2.9855])
|
||||
Target: tensor([5.])----- Prediction: tensor([7.3182])
|
||||
Target: tensor([5.])----- Prediction: tensor([7.9802])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.2287])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.9656])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.4347])
|
||||
Target: tensor([6.])----- Prediction: tensor([5.8240])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.6369])
|
||||
Target: tensor([7.])----- Prediction: tensor([1.8155])
|
||||
Target: tensor([5.])----- Prediction: tensor([10.1038])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.3575])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.9901])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.4601])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.8243])
|
||||
Target: tensor([5.])----- Prediction: tensor([7.7295])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.4800])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.6094])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.6338])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.7549])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.0682])
|
||||
Target: tensor([7.])----- Prediction: tensor([23.9401])
|
||||
Target: tensor([7.])----- Prediction: tensor([2.9943])
|
||||
Target: tensor([6.])----- Prediction: tensor([5.7540])
|
||||
Target: tensor([7.])----- Prediction: tensor([3.5938])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.8617])
|
||||
Target: tensor([6.])----- Prediction: tensor([4.4898])
|
||||
Target: tensor([6.])----- Prediction: tensor([4.1527])
|
||||
Target: tensor([6.])----- Prediction: tensor([13.8834])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.4153])
|
||||
Target: tensor([5.])----- Prediction: tensor([10.9910])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.2680])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.7166])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.7429])
|
||||
Target: tensor([6.])----- Prediction: tensor([1.8801])
|
||||
Target: tensor([5.])----- Prediction: tensor([4.7673])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.3313])
|
||||
Target: tensor([5.])----- Prediction: tensor([8.0485])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.2194])
|
||||
Target: tensor([7.])----- Prediction: tensor([4.6185])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.9581])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.2511])
|
||||
Target: tensor([5.])----- Prediction: tensor([9.4976])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.8048])
|
||||
Target: tensor([7.])----- Prediction: tensor([2.3068])
|
||||
Target: tensor([5.])----- Prediction: tensor([5.2228])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.4355])
|
||||
Target: tensor([6.])----- Prediction: tensor([5.8229])
|
||||
Target: tensor([6.])----- Prediction: tensor([4.9710])
|
||||
Target: tensor([7.])----- Prediction: tensor([4.0948])
|
||||
Target: tensor([5.])----- Prediction: tensor([9.8520])
|
||||
Target: tensor([6.])----- Prediction: tensor([1.6064])
|
||||
Target: tensor([7.])----- Prediction: tensor([4.0091])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.1055])
|
||||
Target: tensor([5.])----- Prediction: tensor([5.5266])
|
||||
Target: tensor([5.])----- Prediction: tensor([1.5365])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.0232])
|
||||
Target: tensor([6.])----- Prediction: tensor([4.7462])
|
||||
Target: tensor([8.])----- Prediction: tensor([3.0388])
|
||||
Target: tensor([6.])----- Prediction: tensor([7.3761])
|
||||
Target: tensor([8.])----- Prediction: tensor([4.0455])
|
||||
Target: tensor([7.])----- Prediction: tensor([8.4651])
|
||||
Target: tensor([7.])----- Prediction: tensor([2.2083])
|
||||
Target: tensor([5.])----- Prediction: tensor([13.7213])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.4370])
|
||||
Target: tensor([5.])----- Prediction: tensor([4.2159])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.0294])
|
||||
Target: tensor([5.])----- Prediction: tensor([11.3286])
|
||||
Target: tensor([4.])----- Prediction: tensor([3.1563])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.0204])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.1787])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.4895])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.9059])
|
||||
Target: tensor([7.])----- Prediction: tensor([2.2940])
|
||||
Target: tensor([5.])----- Prediction: tensor([6.0839])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.4874])
|
||||
Target: tensor([5.])----- Prediction: tensor([12.2298])
|
||||
Target: tensor([6.])----- Prediction: tensor([1.9277])
|
||||
Target: tensor([5.])----- Prediction: tensor([4.9739])
|
||||
Target: tensor([7.])----- Prediction: tensor([4.5098])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.4803])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.3278])
|
||||
Target: tensor([6.])----- Prediction: tensor([8.8388])
|
||||
Target: tensor([7.])----- Prediction: tensor([2.6388])
|
||||
Target: tensor([7.])----- Prediction: tensor([1.8263])
|
||||
Target: tensor([5.])----- Prediction: tensor([1.7058])
|
||||
Target: tensor([5.])----- Prediction: tensor([4.7320])
|
||||
Target: tensor([5.])----- Prediction: tensor([7.0629])
|
||||
Target: tensor([8.])----- Prediction: tensor([6.6816])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.3679])
|
||||
Target: tensor([5.])----- Prediction: tensor([6.4106])
|
||||
Target: tensor([5.])----- Prediction: tensor([12.3476])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.1205])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.6261])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.4900])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.5584])
|
||||
Target: tensor([5.])----- Prediction: tensor([4.1916])
|
||||
Target: tensor([5.])----- Prediction: tensor([5.9044])
|
||||
Target: tensor([6.])----- Prediction: tensor([5.7723])
|
||||
Target: tensor([6.])----- Prediction: tensor([6.3909])
|
||||
Target: tensor([5.])----- Prediction: tensor([4.7932])
|
||||
Target: tensor([5.])----- Prediction: tensor([4.7548])
|
||||
Target: tensor([5.])----- Prediction: tensor([8.0386])
|
||||
Target: tensor([5.])----- Prediction: tensor([5.5603])
|
||||
Target: tensor([3.])----- Prediction: tensor([5.2508])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.8790])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.0702])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.0624])
|
||||
Target: tensor([5.])----- Prediction: tensor([8.8042])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.9469])
|
||||
Target: tensor([7.])----- Prediction: tensor([4.1208])
|
||||
Target: tensor([7.])----- Prediction: tensor([3.2084])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.2332])
|
||||
Target: tensor([4.])----- Prediction: tensor([4.9973])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.9620])
|
||||
Target: tensor([6.])----- Prediction: tensor([1.6706])
|
||||
Target: tensor([5.])----- Prediction: tensor([6.3914])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.2084])
|
||||
Target: tensor([6.])----- Prediction: tensor([5.7970])
|
||||
Target: tensor([7.])----- Prediction: tensor([3.4445])
|
||||
Target: tensor([5.])----- Prediction: tensor([8.4952])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.4870])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.4096])
|
||||
Target: tensor([6.])----- Prediction: tensor([8.2855])
|
||||
Target: tensor([6.])----- Prediction: tensor([1.8462])
|
||||
Target: tensor([4.])----- Prediction: tensor([4.3964])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.4177])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.5993])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.0421])
|
||||
Target: tensor([5.])----- Prediction: tensor([8.7133])
|
||||
Target: tensor([5.])----- Prediction: tensor([10.1540])
|
||||
Target: tensor([7.])----- Prediction: tensor([2.3574])
|
||||
Target: tensor([7.])----- Prediction: tensor([3.2022])
|
||||
Target: tensor([5.])----- Prediction: tensor([1.6709])
|
||||
Target: tensor([3.])----- Prediction: tensor([4.6296])
|
||||
Target: tensor([5.])----- Prediction: tensor([7.6198])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.4627])
|
||||
Target: tensor([5.])----- Prediction: tensor([8.2276])
|
||||
Target: tensor([4.])----- Prediction: tensor([2.4551])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.6208])
|
||||
Target: tensor([7.])----- Prediction: tensor([3.0895])
|
||||
Target: tensor([4.])----- Prediction: tensor([3.6925])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.2303])
|
||||
Target: tensor([6.])----- Prediction: tensor([4.6480])
|
||||
Target: tensor([5.])----- Prediction: tensor([6.2549])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.6234])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.1382])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.3479])
|
||||
Target: tensor([5.])----- Prediction: tensor([5.1068])
|
||||
Target: tensor([7.])----- Prediction: tensor([2.4958])
|
||||
Target: tensor([6.])----- Prediction: tensor([1.8829])
|
||||
Target: tensor([6.])----- Prediction: tensor([6.7703])
|
||||
Target: tensor([7.])----- Prediction: tensor([3.2449])
|
||||
Target: tensor([5.])----- Prediction: tensor([5.7864])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.5621])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.1336])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.8112])
|
||||
Target: tensor([5.])----- Prediction: tensor([7.0639])
|
||||
Target: tensor([5.])----- Prediction: tensor([8.0485])
|
||||
Target: tensor([6.])----- Prediction: tensor([4.8817])
|
||||
Target: tensor([5.])----- Prediction: tensor([1.4661])
|
||||
Target: tensor([5.])----- Prediction: tensor([4.0572])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.6261])
|
||||
Target: tensor([5.])----- Prediction: tensor([6.3413])
|
||||
Target: tensor([5.])----- Prediction: tensor([10.9089])
|
||||
Target: tensor([5.])----- Prediction: tensor([2.8428])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.0931])
|
||||
Target: tensor([5.])----- Prediction: tensor([9.9907])
|
||||
Target: tensor([6.])----- Prediction: tensor([5.4379])
|
||||
Target: tensor([6.])----- Prediction: tensor([2.5430])
|
||||
Target: tensor([5.])----- Prediction: tensor([6.8091])
|
||||
Target: tensor([5.])----- Prediction: tensor([3.3554])
|
||||
Target: tensor([5.])----- Prediction: tensor([7.0773])
|
||||
Target: tensor([6.])----- Prediction: tensor([3.1898])
|
||||
Target: tensor([6.])----- Prediction: tensor([8.0325])
|
||||
Target: tensor([6.])----- Prediction: tensor([4.2776])
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,2 @@
|
|||
#!/bin/bash
|
||||
python3 ./pytorch.py
|
||||
Loading…
Reference in New Issue