Skip to content
This repository has been archived by the owner on Oct 19, 2023. It is now read-only.

Commit

Permalink
2쇄 업데이트
Browse files Browse the repository at this point in the history
  • Loading branch information
Keon Kim committed Oct 18, 2020
1 parent 18756c1 commit a987eb5
Show file tree
Hide file tree
Showing 13 changed files with 1,191 additions and 329 deletions.
5 changes: 2 additions & 3 deletions 03-파이토치로_구현하는_ANN/basic_neural_network.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -18,8 +18,7 @@
"import torch\n",
"import numpy\n",
"from sklearn.datasets import make_blobs\n",
"import matplotlib.pyplot as plt\n",
"import torch.nn.functional as F"
"import matplotlib.pyplot as plt"
]
},
{
Expand Down Expand Up @@ -309,7 +308,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.0"
"version": "3.8.5"
}
},
"nbformat": 4,
Expand Down
1 change: 0 additions & 1 deletion 03-파이토치로_구현하는_ANN/basic_neural_network.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,6 @@
import numpy
from sklearn.datasets import make_blobs
import matplotlib.pyplot as plt
import torch.nn.functional as F


n_dim = 2
Expand Down
225 changes: 170 additions & 55 deletions 04-패션_아이템을_구분하는_DNN/overfitting_and_regularization.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -58,10 +58,117 @@
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to ./.data/FashionMNIST/raw/train-images-idx3-ubyte.gz\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "1aeda6e7f2f949f3b40910d4bbe9f643",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(HTML(value=''), FloatProgress(value=1.0, bar_style='info', layout=Layout(width='20px'), max=1.0…"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Extracting ./.data/FashionMNIST/raw/train-images-idx3-ubyte.gz to ./.data/FashionMNIST/raw\n",
"Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to ./.data/FashionMNIST/raw/train-labels-idx1-ubyte.gz\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "32d0e96e1df2498aa0cd05bfef74a0cb",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(HTML(value=''), FloatProgress(value=1.0, bar_style='info', layout=Layout(width='20px'), max=1.0…"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Extracting ./.data/FashionMNIST/raw/train-labels-idx1-ubyte.gz to ./.data/FashionMNIST/raw\n",
"Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to ./.data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz\n",
"\n",
"\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "9ba3ba91a8114a3cb6c93dfdfb0716ea",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(HTML(value=''), FloatProgress(value=1.0, bar_style='info', layout=Layout(width='20px'), max=1.0…"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Extracting ./.data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz to ./.data/FashionMNIST/raw\n",
"Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz to ./.data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "b22aa7f5b217481da36362df3baf5082",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(HTML(value=''), FloatProgress(value=1.0, bar_style='info', layout=Layout(width='20px'), max=1.0…"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Extracting ./.data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to ./.data/FashionMNIST/raw\n",
"Processing...\n",
"Done!\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/keon/projects/3-min-pytorch/env/lib/python3.8/site-packages/torchvision/datasets/mnist.py:469: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at ../torch/csrc/utils/tensor_numpy.cpp:141.)\n",
" return torch.from_numpy(parsed.astype(m[2], copy=False)).view(*s)\n"
]
}
],
"source": [
"train_loader = torch.utils.data.DataLoader(\n",
" datasets.MNIST('./.data',\n",
" datasets.FashionMNIST('./.data',\n",
" train=True,\n",
" download=True,\n",
" transform=transforms.Compose([\n",
Expand All @@ -71,7 +178,7 @@
" ])),\n",
" batch_size=BATCH_SIZE, shuffle=True)\n",
"test_loader = torch.utils.data.DataLoader(\n",
" datasets.MNIST('./.data',\n",
" datasets.FashionMNIST('./.data',\n",
" train=False, \n",
" transform=transforms.Compose([\n",
" transforms.ToTensor(),\n",
Expand Down Expand Up @@ -182,7 +289,15 @@
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n"
]
}
],
"source": [
"def evaluate(model, test_loader):\n",
" model.eval()\n",
Expand Down Expand Up @@ -222,56 +337,56 @@
"name": "stdout",
"output_type": "stream",
"text": [
"[1] Test Loss: 0.5471, Accuracy: 82.80%\n",
"[2] Test Loss: 0.4169, Accuracy: 86.73%\n",
"[3] Test Loss: 0.3393, Accuracy: 89.36%\n",
"[4] Test Loss: 0.2775, Accuracy: 91.60%\n",
"[5] Test Loss: 0.2420, Accuracy: 92.51%\n",
"[6] Test Loss: 0.2205, Accuracy: 93.24%\n",
"[7] Test Loss: 0.1990, Accuracy: 93.90%\n",
"[8] Test Loss: 0.1828, Accuracy: 94.26%\n",
"[9] Test Loss: 0.1786, Accuracy: 94.53%\n",
"[10] Test Loss: 0.1625, Accuracy: 95.13%\n",
"[11] Test Loss: 0.1589, Accuracy: 95.22%\n",
"[12] Test Loss: 0.1493, Accuracy: 95.46%\n",
"[13] Test Loss: 0.1448, Accuracy: 95.60%\n",
"[14] Test Loss: 0.1388, Accuracy: 95.67%\n",
"[15] Test Loss: 0.1326, Accuracy: 95.97%\n",
"[16] Test Loss: 0.1292, Accuracy: 96.01%\n",
"[17] Test Loss: 0.1257, Accuracy: 96.06%\n",
"[18] Test Loss: 0.1234, Accuracy: 96.17%\n",
"[19] Test Loss: 0.1174, Accuracy: 96.36%\n",
"[20] Test Loss: 0.1149, Accuracy: 96.55%\n",
"[21] Test Loss: 0.1133, Accuracy: 96.46%\n",
"[22] Test Loss: 0.1121, Accuracy: 96.50%\n",
"[23] Test Loss: 0.1099, Accuracy: 96.63%\n",
"[24] Test Loss: 0.1071, Accuracy: 96.69%\n",
"[25] Test Loss: 0.1055, Accuracy: 96.76%\n",
"[26] Test Loss: 0.1039, Accuracy: 96.83%\n",
"[27] Test Loss: 0.1036, Accuracy: 96.73%\n",
"[28] Test Loss: 0.1011, Accuracy: 96.77%\n",
"[29] Test Loss: 0.0973, Accuracy: 96.91%\n",
"[30] Test Loss: 0.0973, Accuracy: 96.99%\n",
"[31] Test Loss: 0.0970, Accuracy: 96.97%\n",
"[32] Test Loss: 0.0949, Accuracy: 97.00%\n",
"[33] Test Loss: 0.0931, Accuracy: 97.19%\n",
"[34] Test Loss: 0.0918, Accuracy: 97.14%\n",
"[35] Test Loss: 0.0911, Accuracy: 97.20%\n",
"[36] Test Loss: 0.0927, Accuracy: 97.04%\n",
"[37] Test Loss: 0.0900, Accuracy: 97.18%\n",
"[38] Test Loss: 0.0923, Accuracy: 97.16%\n",
"[39] Test Loss: 0.0899, Accuracy: 97.13%\n",
"[40] Test Loss: 0.0896, Accuracy: 97.10%\n",
"[41] Test Loss: 0.0879, Accuracy: 97.23%\n",
"[42] Test Loss: 0.0872, Accuracy: 97.43%\n",
"[43] Test Loss: 0.0867, Accuracy: 97.24%\n",
"[44] Test Loss: 0.0854, Accuracy: 97.25%\n",
"[45] Test Loss: 0.0863, Accuracy: 97.36%\n",
"[46] Test Loss: 0.0838, Accuracy: 97.42%\n",
"[47] Test Loss: 0.0829, Accuracy: 97.47%\n",
"[48] Test Loss: 0.0834, Accuracy: 97.38%\n",
"[49] Test Loss: 0.0860, Accuracy: 97.34%\n",
"[50] Test Loss: 0.0816, Accuracy: 97.36%\n"
"[1] Test Loss: 0.6536, Accuracy: 76.92%\n",
"[2] Test Loss: 0.5359, Accuracy: 80.72%\n",
"[3] Test Loss: 0.4977, Accuracy: 82.18%\n",
"[4] Test Loss: 0.4584, Accuracy: 83.49%\n",
"[5] Test Loss: 0.4421, Accuracy: 84.22%\n",
"[6] Test Loss: 0.4245, Accuracy: 84.91%\n",
"[7] Test Loss: 0.4205, Accuracy: 84.82%\n",
"[8] Test Loss: 0.4067, Accuracy: 85.32%\n",
"[9] Test Loss: 0.4024, Accuracy: 85.54%\n",
"[10] Test Loss: 0.3923, Accuracy: 85.82%\n",
"[11] Test Loss: 0.3875, Accuracy: 86.22%\n",
"[12] Test Loss: 0.3772, Accuracy: 86.19%\n",
"[13] Test Loss: 0.3807, Accuracy: 86.11%\n",
"[14] Test Loss: 0.3762, Accuracy: 86.33%\n",
"[15] Test Loss: 0.3636, Accuracy: 86.70%\n",
"[16] Test Loss: 0.3699, Accuracy: 86.29%\n",
"[17] Test Loss: 0.3625, Accuracy: 86.92%\n",
"[18] Test Loss: 0.3567, Accuracy: 87.06%\n",
"[19] Test Loss: 0.3515, Accuracy: 87.41%\n",
"[20] Test Loss: 0.3490, Accuracy: 87.50%\n",
"[21] Test Loss: 0.3572, Accuracy: 86.86%\n",
"[22] Test Loss: 0.3504, Accuracy: 87.10%\n",
"[23] Test Loss: 0.3465, Accuracy: 87.48%\n",
"[24] Test Loss: 0.3383, Accuracy: 87.60%\n",
"[25] Test Loss: 0.3347, Accuracy: 87.91%\n",
"[26] Test Loss: 0.3370, Accuracy: 87.76%\n",
"[27] Test Loss: 0.3330, Accuracy: 88.07%\n",
"[28] Test Loss: 0.3338, Accuracy: 88.12%\n",
"[29] Test Loss: 0.3316, Accuracy: 87.98%\n",
"[30] Test Loss: 0.3280, Accuracy: 88.29%\n",
"[31] Test Loss: 0.3241, Accuracy: 88.31%\n",
"[32] Test Loss: 0.3279, Accuracy: 88.23%\n",
"[33] Test Loss: 0.3261, Accuracy: 88.05%\n",
"[34] Test Loss: 0.3262, Accuracy: 88.13%\n",
"[35] Test Loss: 0.3207, Accuracy: 88.47%\n",
"[36] Test Loss: 0.3287, Accuracy: 88.15%\n",
"[37] Test Loss: 0.3221, Accuracy: 88.43%\n",
"[38] Test Loss: 0.3215, Accuracy: 88.31%\n",
"[39] Test Loss: 0.3165, Accuracy: 88.60%\n",
"[40] Test Loss: 0.3178, Accuracy: 88.66%\n",
"[41] Test Loss: 0.3270, Accuracy: 88.00%\n",
"[42] Test Loss: 0.3130, Accuracy: 88.84%\n",
"[43] Test Loss: 0.3118, Accuracy: 89.00%\n",
"[44] Test Loss: 0.3142, Accuracy: 88.57%\n",
"[45] Test Loss: 0.3131, Accuracy: 88.70%\n",
"[46] Test Loss: 0.3202, Accuracy: 88.44%\n",
"[47] Test Loss: 0.3144, Accuracy: 88.76%\n",
"[48] Test Loss: 0.3121, Accuracy: 89.03%\n",
"[49] Test Loss: 0.3177, Accuracy: 88.58%\n",
"[50] Test Loss: 0.3127, Accuracy: 88.94%\n"
]
}
],
Expand Down Expand Up @@ -301,7 +416,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.0"
"version": "3.8.5"
}
},
"nbformat": 4,
Expand Down
4 changes: 2 additions & 2 deletions 04-패션_아이템을_구분하는_DNN/overfitting_and_regularization.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@
# ![horizontalflip.png](./assets/horizontalflip.png)

train_loader = torch.utils.data.DataLoader(
datasets.MNIST('./.data',
datasets.FashionMNIST('./.data',
train=True,
download=True,
transform=transforms.Compose([
Expand All @@ -35,7 +35,7 @@
])),
batch_size=BATCH_SIZE, shuffle=True)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('./.data',
datasets.FashionMNIST('./.data',
train=False,
transform=transforms.Compose([
transforms.ToTensor(),
Expand Down
Loading

0 comments on commit a987eb5

Please sign in to comment.