Skip to content

Instantly share code, notes, and snippets.

@abdulmuneer

abdulmuneer/copy-of-pytorch_type_issue.ipynb

Created July 2, 2019 09:43
Show Gist options
  • Save abdulmuneer/7b9fd91788945ebbfeb0ea6422a02142 to your computer and use it in GitHub Desktop.
Save abdulmuneer/7b9fd91788945ebbfeb0ea6422a02142 to your computer and use it in GitHub Desktop.
Download ZIP
Copy of pytorch_type_issue.ipynb
Display the source blob
Display the rendered blob
Raw
copy-of-pytorch_type_issue.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "Copy of pytorch_type_issue.ipynb",
"version": "0.3.2",
"provenance": [],
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/abdulmuneer/7b9fd91788945ebbfeb0ea6422a02142/copy-of-pytorch_type_issue.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"metadata": {
"id": "FUgDYi9YDDHt",
"colab_type": "code",
"colab": {}
},
"source": [
"import numpy as np\n",
"import torch\n",
"import torch.nn as nn\n",
"import torch.nn.functional as F\n",
"from torch import optim\n"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "COTcJx7CDIaF",
"colab_type": "code",
"outputId": "1d0e5029-0927-4742-917b-8a452ad6081f",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"torch.__version__"
],
"execution_count": 0,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"'1.1.0'"
]
},
"metadata": {
"tags": []
},
"execution_count": 2
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "WF9dyUOkDNa-",
"colab_type": "code",
"colab": {}
},
"source": [
"n_input, n_hidden, n_output = 5,3,1"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "GSRaQlHDDQ0n",
"colab_type": "code",
"colab": {}
},
"source": [
"x = torch.randn((1, n_input))\n",
"y = torch.from_numpy(np.array([[0.3]]))"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "MnZAjdcuDiOu",
"colab_type": "code",
"colab": {}
},
"source": [
"class Model(nn.Module):\n",
" def __init__(self):\n",
" super().__init__()\n",
" self.hidden1 = nn.Linear(n_input, n_hidden)\n",
" self.output = nn.Linear(n_hidden, n_output)\n",
" def forward(self, x):\n",
" x = self.hidden1(x)\n",
" x = F.sigmoid(x)\n",
" x = self.output(x)\n",
" x = F.sigmoid(x)\n",
" return x"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "rB3-Nqz1Dl98",
"colab_type": "code",
"colab": {}
},
"source": [
"model1 = Model()"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "7N1FXdVyDoHE",
"colab_type": "code",
"colab": {}
},
"source": [
"model2 = nn.Sequential(\n",
" nn.Linear(n_input, n_hidden),\n",
" nn.Sigmoid(),\n",
" nn.Linear(n_hidden, n_output)\n",
")"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "71K7EjqUDqLS",
"colab_type": "code",
"colab": {}
},
"source": [
"trainloader = [(x,y)]\n",
"validloader = [(x,y)]"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "2bAgZIUpDt4z",
"colab_type": "code",
"colab": {}
},
"source": [
"def train(model):\n",
" loss_function = nn.CrossEntropyLoss()\n",
" optimizer = optim.SGD(model.parameters(), lr=0.01)\n",
" for epoch in range(1, 11):\n",
" \n",
" train_loss, valid_loss = [], []\n",
"\n",
" # training\n",
" model.train()\n",
" for data, target in trainloader:\n",
" # reset gradients\n",
" optimizer.zero_grad()\n",
"\n",
" #forward\n",
" output = model.forward(data)\n",
" print(\"output, target\")\n",
" print(output, target)\n",
" #loss\n",
" loss = loss_function(output, target)\n",
"\n",
"\n",
" #backprop\n",
" loss.backward()\n",
"\n",
" #apply gradients\n",
" optimizer.step()\n",
"\n",
" train_loss.append(loss.item())\n",
"\n",
" #validation\n",
" model.eval()\n",
" for data, target in validloader():\n",
" # forward\n",
" output = model.forward(data)\n",
"\n",
" #loss\n",
" loss = loss_function(output, target)\n",
" valid_loss.append(loss)\n",
" print(\"Training loss: \", np.mean(train_loss))\n",
" print(\"Validation loss: \", np.mean(valid_loss))\n",
" "
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "vwBXmV0vDwZ7",
"colab_type": "code",
"outputId": "58d09de4-8742-4afc-fbe7-0a8839d1f2cd",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 380
}
},
"source": [
"train(model1)"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"output, target\n",
"tensor([[0.4965]], grad_fn=<SigmoidBackward>) tensor([[0.3000]], dtype=torch.float64)\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py:1386: UserWarning: nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.\n",
" warnings.warn(\"nn.functional.sigmoid is deprecated. Use torch.sigmoid instead.\")\n"
],
"name": "stderr"
},
{
"output_type": "error",
"ename": "RuntimeError",
"evalue": "ignored",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mRuntimeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-11-55e513123dba>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mtrain\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmodel1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m<ipython-input-9-0593434e41c0>\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(model)\u001b[0m\n\u001b[1;32m 17\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 18\u001b[0m \u001b[0;31m#loss\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 19\u001b[0;31m \u001b[0mloss\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mloss_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 20\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 21\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, *input, **kwargs)\u001b[0m\n\u001b[1;32m 491\u001b[0m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_slow_forward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 492\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 493\u001b[0;31m \u001b[0mresult\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 494\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mhook\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_forward_hooks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 495\u001b[0m \u001b[0mhook_result\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mhook\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mresult\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.6/dist-packages/torch/nn/modules/loss.py\u001b[0m in \u001b[0;36mforward\u001b[0;34m(self, input, target)\u001b[0m\n\u001b[1;32m 940\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 941\u001b[0m return F.cross_entropy(input, target, weight=self.weight,\n\u001b[0;32m--> 942\u001b[0;31m ignore_index=self.ignore_index, reduction=self.reduction)\n\u001b[0m\u001b[1;32m 943\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 944\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py\u001b[0m in \u001b[0;36mcross_entropy\u001b[0;34m(input, target, weight, size_average, ignore_index, reduce, reduction)\u001b[0m\n\u001b[1;32m 2054\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0msize_average\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mreduce\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2055\u001b[0m \u001b[0mreduction\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_Reduction\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlegacy_get_string\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msize_average\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreduce\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2056\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mnll_loss\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlog_softmax\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mweight\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mignore_index\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreduction\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 2057\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 2058\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py\u001b[0m in \u001b[0;36mnll_loss\u001b[0;34m(input, target, weight, size_average, ignore_index, reduce, reduction)\u001b[0m\n\u001b[1;32m 1869\u001b[0m .format(input.size(0), target.size(0)))\n\u001b[1;32m 1870\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mdim\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m2\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1871\u001b[0;31m \u001b[0mret\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_C\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_nn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnll_loss\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mweight\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_Reduction\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_enum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mreduction\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mignore_index\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1872\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0mdim\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;36m4\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1873\u001b[0m \u001b[0mret\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_C\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_nn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnll_loss2d\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtarget\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mweight\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_Reduction\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_enum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mreduction\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mignore_index\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mRuntimeError\u001b[0m: Expected object of scalar type Long but got scalar type Double for argument #2 'target'"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "QZSsEJDqDyGy",
"colab_type": "code",
"colab": {}
},
"source": [
""
],
"execution_count": 0,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment