Skip to content

Instantly share code, notes, and snippets.

@kahartma

kahartma/GAN_Error.ipynb Secret

Created July 6, 2017 16:47
Show Gist options
  • Save kahartma/ccf7279fb20a216905079f6b10b31b78 to your computer and use it in GitHub Desktop.
Save kahartma/ccf7279fb20a216905079f6b10b31b78 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
GAN_Error.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"%load_ext autoreload\n",
"%autoreload 2\n",
"\n",
"import numpy as np\n",
"import torch\n",
"import torch.nn as nn\n",
"from torch.autograd import Variable\n",
"from torch import optim\n",
"\n",
"import torch.autograd as autograd\n",
"\n",
"#torch.cuda.set_device(0)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"class WGAN_I_Discriminator(nn.Module):\n",
"\tdef __init__(self):\n",
"\t\tsuper(WGAN_I_Discriminator, self).__init__()\n",
"\n",
"\t\tself.did_init_train = False\n",
"\n",
"\tdef train_init(self,alpha=0.0001,betas=(0,0.9)):\n",
"\t\tself.loss = torch.nn.L1Loss()\n",
"\t\tself.optimizer = optim.Adam(self.parameters(),lr=alpha,betas=betas)\n",
"\t\tself.did_init_train = True\n",
"\n",
"\tdef train_batch(self, batch_real, batch_fake, lambd=10):\n",
"\t\tif not self.did_init_train:\n",
"\t\t\tself.train_init()\n",
"\n",
"\t\t# Reset gradients\n",
"\t\tself.optimizer.zero_grad()\n",
"\n",
"\t\t# Compute output and loss\n",
"\t\tfx_real = self.forward(batch_real)\n",
"\t\tloss_real = fx_real.mean()\n",
"\n",
"\t\tfx_fake = self.forward(batch_fake)\n",
"\t\tloss_fake = fx_fake.mean()\n",
"\n",
"\n",
"\t\t#dreist geklaut von\n",
"\t\t# https://github.com/caogang/wgan-gp/blob/master/gan_toy.py\n",
"\t\t# gradients = autograd.grad(outputs=fx_comb, inputs=interpolates,\n",
"\t\t# \t\t\t\t\t grad_outputs=grad_ones,\n",
"\t\t# \t\t\t\t\t create_graph=True, retain_graph=True, only_inputs=True)[0]\n",
"\t\t# gradient_penalty = ((gradients.norm(2, dim=1) - 1) ** 2).mean() * lambd\n",
"\t\tloss_penalty = self.calc_gradient_penalty(batch_real, batch_fake,lambd)\n",
"\n",
"\t\tloss = loss_fake - loss_real + loss_penalty\n",
"\n",
"\t\t# Backprop gradient\n",
"\t\tloss.backward()\n",
"\n",
"\t\t# Update parameters\n",
"\t\tself.optimizer.step()\n",
"\n",
"\t\tself.optimizer.zero_grad()\n",
"\n",
"\t\treturn loss.data[0] # return loss\n",
"\n",
"\n",
"\tdef calc_gradient_penalty(self, real_data, fake_data,lambd):\n",
"\t\talpha = torch.rand(real_data.size(0), 1,1,1)\n",
"\t\talpha = alpha.expand(real_data.size())\n",
"\t\talpha = alpha\n",
"\n",
"\t\tinterpolates = alpha * real_data.data + ((1 - alpha) * fake_data.data)\n",
"\n",
"\t\tinterpolates = interpolates\n",
"\t\tinterpolates = Variable(interpolates, requires_grad=True)\n",
"\n",
"\t\tdisc_interpolates = self(interpolates)\n",
"\n",
"\t\tgradients = autograd.grad(outputs=disc_interpolates, inputs=interpolates,\n",
"\t\t\t\t\t\t\t\t grad_outputs=torch.ones(disc_interpolates.size()),\n",
"\t\t\t\t\t\t\t\t create_graph=True, retain_graph=True, only_inputs=True)[0]\n",
"\n",
"\t\tgradient_penalty = ((gradients.norm(2, dim=1) - 1) ** 2).mean() * lambd\n",
"\n",
"\t\treturn gradient_penalty\n",
"\n",
"\n",
"class WGAN_I_Generator(nn.Module):\n",
"\tdef __init__(self):\n",
"\t\tsuper(WGAN_I_Generator, self).__init__()\n",
"\n",
"\t\tself.did_init_train = False\n",
"\n",
"\tdef train_init(self,alpha=0.0001,betas=(0,0.9)):\n",
"\t\tself.loss = None\n",
"\t\tself.optimizer = optim.Adam(self.parameters(),lr=alpha,betas=betas)\n",
"\t\tself.did_init_train = True\n",
"\n",
"\tdef train_batch(self, batch_noise, discriminator):\n",
"\t\tif not self.did_init_train:\n",
"\t\t\tself.train_init()\n",
"\n",
"\t\tnoise = batch_noise\n",
"\t\tzeros_label = Variable(torch.ones(noise.size(0)))\n",
"\n",
"\t\t# Reset gradients\n",
"\t\tself.optimizer.zero_grad()\n",
"\n",
"\t\t# Generate and discriminate\n",
"\t\tgen = self.forward(noise)\n",
"\t\tdisc = discriminator(gen)\n",
"\t\tloss = -disc.mean()\n",
"\n",
"\t\t# Backprop gradient\n",
"\t\tloss.backward()\n",
"\n",
"\t\t# Update parameters\n",
"\t\tself.optimizer.step()\n",
"\n",
"\t\tself.optimizer.zero_grad()\n",
"\n",
"\t\treturn loss.data[0] # return loss"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [],
"source": [
"class G(WGAN_I_Generator):\n",
"\tdef __init__(self):\n",
"\t\tsuper(G, self).__init__()\n",
"\t\tself.project = nn.Sequential(\n",
"\t\t\tnn.Linear(1,4),\n",
"\t\t\tnn.Tanh()\n",
"\t\t\t)\n",
"\n",
"\t\tself.did_init_train = False\n",
"\n",
"\tdef forward(self, inp):\n",
"\t\tx = self.project(inp)\n",
"\t\tx = x.view(x.size(0),1,2,2)\n",
"\t\treturn x"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
"class D1(WGAN_I_Discriminator):\n",
"\tdef __init__(self):\n",
"\t\tsuper(D1, self).__init__()\n",
"\t\tself.features = nn.Sequential(\n",
"\t\t\tnn.Conv2d(1,3,(2,1)),\n",
"\t\t\tnn.LeakyReLU(negative_slope=0.2),\n",
"\t\t\t)\n",
"\t\tself.classification = nn.Sequential(\n",
"\t\t\tnn.Linear(3*2,1)\n",
"\t\t\t)\n",
"\n",
"\t\tself.did_init_train = False\n",
"\n",
"\tdef forward(self, inp):\n",
"\t\tinp = inp.view(inp.size(0),1,2,2)\n",
"\t\tx = self.features(inp)\n",
"\t\tx = x.view(x.size(0),3*2)\n",
"\t\tx = self.classification(x)\n",
"\t\tprint x\n",
"\t\treturn x\n",
" \n",
"class D2(WGAN_I_Discriminator):\n",
"\tdef __init__(self):\n",
"\t\tsuper(D2, self).__init__()\n",
"\t\tself.features = nn.Sequential(\n",
"\t\t\tnn.Conv2d(1,3,(2,1)),\n",
"\t\t\tnn.Conv2d(3,3,1),\n",
"\t\t\tnn.LeakyReLU(negative_slope=0.2),\n",
"\t\t\t)\n",
"\t\tself.classification = nn.Sequential(\n",
"\t\t\tnn.Linear(3*2,1)\n",
"\t\t\t)\n",
"\n",
"\t\tself.did_init_train = False\n",
"\n",
"\tdef forward(self, inp):\n",
"\t\tinp = inp.view(inp.size(0),1,2,2)\n",
"\t\tx = self.features(inp)\n",
"\t\tx = x.view(x.size(0),3*2)\n",
"\t\tx = self.classification(x)\n",
"\t\tprint x\n",
"\t\treturn x\n",
" \n",
"class D3(WGAN_I_Discriminator):\n",
"\tdef __init__(self):\n",
"\t\tsuper(D3, self).__init__()\n",
"\t\tself.features = nn.Sequential(\n",
"\t\t\tnn.Conv2d(1,3,(2,1)),\n",
"\t\t\tnn.Conv2d(3,3,1),\n",
"\t\t\tnn.LeakyReLU(negative_slope=0.2),\n",
"\t\t\tnn.Conv2d(3,3,1),\n",
"\t\t\tnn.LeakyReLU(negative_slope=0.2)\n",
"\t\t\t)\n",
"\t\tself.classification = nn.Sequential(\n",
"\t\t\tnn.Linear(3*2,1)\n",
"\t\t\t)\n",
"\n",
"\t\tself.did_init_train = False\n",
"\n",
"\tdef forward(self, inp):\n",
"\t\tinp = inp.view(inp.size(0),1,2,2)\n",
"\t\tx = self.features(inp)\n",
"\t\tx = x.view(x.size(0),3*2)\n",
"\t\tx = self.classification(x)\n",
"\t\tprint x\n",
"\t\treturn x\n",
" \n",
"class D4(WGAN_I_Discriminator):\n",
"\tdef __init__(self):\n",
"\t\tsuper(D4, self).__init__()\n",
"\t\tself.features = nn.Sequential(\n",
"\t\t\tnn.Conv2d(1,3,(2,1)),\n",
"\t\t\tnn.Conv2d(3,3,1),\n",
"\t\t\tnn.LeakyReLU(negative_slope=0.2),\n",
"\t\t\tnn.Conv2d(3,3,1),\n",
"\t\t\tnn.Conv2d(3,3,1),\n",
"\t\t\tnn.LeakyReLU(negative_slope=0.2)\n",
"\t\t\t)\n",
"\t\tself.classification = nn.Sequential(\n",
"\t\t\tnn.Linear(3*2,1)\n",
"\t\t\t)\n",
"\n",
"\t\tself.did_init_train = False\n",
"\n",
"\tdef forward(self, inp):\n",
"\t\tinp = inp.view(inp.size(0),1,2,2)\n",
"\t\tx = self.features(inp)\n",
"\t\tx = x.view(x.size(0),3*2)\n",
"\t\tx = self.classification(x)\n",
"\t\tprint x\n",
"\t\treturn x\n",
" \n",
"class D5(WGAN_I_Discriminator):\n",
"\tdef __init__(self):\n",
"\t\tsuper(D5, self).__init__()\n",
"\t\tself.features = nn.Sequential(\n",
"\t\t\tnn.Conv2d(1,3,(2,1)),\n",
"\t\t\tnn.Conv2d(3,3,1),\n",
"\t\t\tnn.LeakyReLU(negative_slope=0.2),\n",
"\t\t\tnn.Conv2d(3,3,1),\n",
"\t\t\tnn.Conv2d(3,3,1),\n",
"\t\t\tnn.LeakyReLU(negative_slope=0.2)\n",
"\t\t\t)\n",
"\t\tself.classification = nn.Sequential(\n",
"\t\t\tnn.Linear(3*2,1)\n",
"\t\t\t)\n",
"\n",
"\t\tself.did_init_train = False\n",
"\n",
"\tdef forward(self, inp):\n",
"\t\tinp = inp.view(inp.size(0),1,2,2)\n",
"\t\tx = self.features(inp)\n",
"\t\tx = x.view(x.size(0),3*2)\n",
"\t\tx = self.classification(x)\n",
"\t\tx = 1/x\n",
"\t\tprint x\n",
"\t\treturn x"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [],
"source": [
"def train(gen,disc):\n",
" batch_size = 5\n",
"\n",
" ind = np.random.randint(4,size=(batch_size,1))\n",
" batch = np.zeros((batch_size,4))\n",
" batch[:,ind] = 1\n",
" batch = batch.reshape((batch_size,1,2,2))\n",
" X_batch = Variable(torch.from_numpy(batch).float(),requires_grad=False)\n",
" noise = np.random.uniform(-1,1,(batch_size,1))\n",
" noise = Variable(torch.from_numpy(noise).float(),volatile=True)\n",
"\n",
" fake_batch = Variable(gen.forward(noise).data,requires_grad=False)\n",
"\n",
" loss_d = disc.train_batch(X_batch,fake_batch)\n",
"\n",
" noise = np.random.uniform(-1,1,(batch_size,1))\n",
" noise = Variable(torch.from_numpy(noise).float(),requires_grad=False)\n",
"\n",
" loss_g = gen.train_batch(noise,disc)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Variable containing:\n",
" 0.1076\n",
" 0.1076\n",
" 0.1076\n",
" 0.1076\n",
" 0.1076\n",
"[torch.FloatTensor of size 5x1]\n",
"\n",
"Variable containing:\n",
"-0.1358\n",
" 0.1392\n",
"-0.0589\n",
" 0.0915\n",
"-0.0997\n",
"[torch.FloatTensor of size 5x1]\n",
"\n",
"Variable containing:\n",
"-0.0801\n",
" 0.1170\n",
" 0.0927\n",
" 0.0967\n",
"-0.0515\n",
"[torch.FloatTensor of size 5x1]\n",
"\n",
"Variable containing:\n",
" 0.1460\n",
"-0.0738\n",
" 0.0821\n",
" 0.1472\n",
" 0.1261\n",
"[torch.FloatTensor of size 5x1]\n",
"\n"
]
}
],
"source": [
"train(G(),disc=D1())"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Variable containing:\n",
" 0.2192\n",
" 0.2192\n",
" 0.2192\n",
" 0.2192\n",
" 0.2192\n",
"[torch.FloatTensor of size 5x1]\n",
"\n",
"Variable containing:\n",
" 0.4432\n",
" 0.3932\n",
" 0.4277\n",
" 0.4354\n",
" 0.3680\n",
"[torch.FloatTensor of size 5x1]\n",
"\n",
"Variable containing:\n",
" 0.3128\n",
" 0.3124\n",
" 0.2965\n",
" 0.4105\n",
" 0.2265\n",
"[torch.FloatTensor of size 5x1]\n",
"\n"
]
},
{
"ename": "RuntimeError",
"evalue": "ConvNdBackward: expected Variable at argument 0 (got None)",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mRuntimeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-36-a33a28fe4e3e>\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[0mG\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mdisc\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mD2\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[0m",
"\u001b[0;32m<ipython-input-34-0bc717f851b5>\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(gen, disc)\u001b[0m\n\u001b[1;32m 12\u001b[0m \u001b[0mfake_batch\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mVariable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mgen\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnoise\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mrequires_grad\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 14\u001b[0;31m \u001b[0mloss_d\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdisc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain_batch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_batch\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mfake_batch\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 15\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 16\u001b[0m \u001b[0mnoise\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrandom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0muniform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatch_size\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m<ipython-input-31-2f8373282c33>\u001b[0m in \u001b[0;36mtrain_batch\u001b[0;34m(self, batch_real, batch_fake, lambd)\u001b[0m\n\u001b[1;32m 36\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 37\u001b[0m \u001b[0;31m# Backprop gradient\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 38\u001b[0;31m \u001b[0mloss\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbackward\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 39\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 40\u001b[0m \u001b[0;31m# Update parameters\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/home/hartmank/anaconda2/lib/python2.7/site-packages/torch/autograd/variable.pyc\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(self, gradient, retain_graph, create_graph, retain_variables)\u001b[0m\n\u001b[1;32m 150\u001b[0m \u001b[0mDefaults\u001b[0m \u001b[0mto\u001b[0m \u001b[0mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0munless\u001b[0m \u001b[0;34m`\u001b[0m\u001b[0;34m`\u001b[0m\u001b[0mgradient\u001b[0m\u001b[0;34m`\u001b[0m\u001b[0;34m`\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0ma\u001b[0m \u001b[0mvolatile\u001b[0m \u001b[0mVariable\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 151\u001b[0m \"\"\"\n\u001b[0;32m--> 152\u001b[0;31m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mautograd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbackward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgradient\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mretain_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcreate_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mretain_variables\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 153\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 154\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mregister_hook\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mhook\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/home/hartmank/anaconda2/lib/python2.7/site-packages/torch/autograd/__init__.pyc\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(variables, grad_variables, retain_graph, create_graph, retain_variables)\u001b[0m\n\u001b[1;32m 96\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 97\u001b[0m Variable._execution_engine.run_backward(\n\u001b[0;32m---> 98\u001b[0;31m variables, grad_variables, retain_graph)\n\u001b[0m\u001b[1;32m 99\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 100\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mRuntimeError\u001b[0m: ConvNdBackward: expected Variable at argument 0 (got None)"
]
}
],
"source": [
"train(G(),disc=D2())"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Variable containing:\n",
"-0.3431\n",
"-0.3431\n",
"-0.3431\n",
"-0.3431\n",
"-0.3431\n",
"[torch.FloatTensor of size 5x1]\n",
"\n",
"Variable containing:\n",
"-0.3279\n",
"-0.3279\n",
"-0.3423\n",
"-0.3313\n",
"-0.3366\n",
"[torch.FloatTensor of size 5x1]\n",
"\n",
"Variable containing:\n",
"-0.3133\n",
"-0.3415\n",
"-0.3116\n",
"-0.3241\n",
"-0.3228\n",
"[torch.FloatTensor of size 5x1]\n",
"\n",
"Variable containing:\n",
"-0.3338\n",
"-0.3368\n",
"-0.3323\n",
"-0.3308\n",
"-0.3231\n",
"[torch.FloatTensor of size 5x1]\n",
"\n"
]
}
],
"source": [
"train(G(),disc=D3())"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Variable containing:\n",
"-0.4007\n",
"-0.4007\n",
"-0.4007\n",
"-0.4007\n",
"-0.4007\n",
"[torch.FloatTensor of size 5x1]\n",
"\n",
"Variable containing:\n",
"-0.3828\n",
"-0.3870\n",
"-0.3827\n",
"-0.3826\n",
"-0.3836\n",
"[torch.FloatTensor of size 5x1]\n",
"\n",
"Variable containing:\n",
"-0.3872\n",
"-0.3930\n",
"-0.3956\n",
"-0.3818\n",
"-0.3829\n",
"[torch.FloatTensor of size 5x1]\n",
"\n"
]
},
{
"ename": "RuntimeError",
"evalue": "ConvNdBackward: expected Variable at argument 0 (got None)",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mRuntimeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-38-617c87cc7824>\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[0mG\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mdisc\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mD4\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[0m",
"\u001b[0;32m<ipython-input-34-0bc717f851b5>\u001b[0m in \u001b[0;36mtrain\u001b[0;34m(gen, disc)\u001b[0m\n\u001b[1;32m 12\u001b[0m \u001b[0mfake_batch\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mVariable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mgen\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mforward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnoise\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mrequires_grad\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 14\u001b[0;31m \u001b[0mloss_d\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdisc\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain_batch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_batch\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mfake_batch\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 15\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 16\u001b[0m \u001b[0mnoise\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrandom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0muniform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatch_size\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m<ipython-input-31-2f8373282c33>\u001b[0m in \u001b[0;36mtrain_batch\u001b[0;34m(self, batch_real, batch_fake, lambd)\u001b[0m\n\u001b[1;32m 36\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 37\u001b[0m \u001b[0;31m# Backprop gradient\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 38\u001b[0;31m \u001b[0mloss\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbackward\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 39\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 40\u001b[0m \u001b[0;31m# Update parameters\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/home/hartmank/anaconda2/lib/python2.7/site-packages/torch/autograd/variable.pyc\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(self, gradient, retain_graph, create_graph, retain_variables)\u001b[0m\n\u001b[1;32m 150\u001b[0m \u001b[0mDefaults\u001b[0m \u001b[0mto\u001b[0m \u001b[0mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0munless\u001b[0m \u001b[0;34m`\u001b[0m\u001b[0;34m`\u001b[0m\u001b[0mgradient\u001b[0m\u001b[0;34m`\u001b[0m\u001b[0;34m`\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0ma\u001b[0m \u001b[0mvolatile\u001b[0m \u001b[0mVariable\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 151\u001b[0m \"\"\"\n\u001b[0;32m--> 152\u001b[0;31m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mautograd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbackward\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mgradient\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mretain_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcreate_graph\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mretain_variables\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 153\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 154\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mregister_hook\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mhook\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/home/hartmank/anaconda2/lib/python2.7/site-packages/torch/autograd/__init__.pyc\u001b[0m in \u001b[0;36mbackward\u001b[0;34m(variables, grad_variables, retain_graph, create_graph, retain_variables)\u001b[0m\n\u001b[1;32m 96\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 97\u001b[0m Variable._execution_engine.run_backward(\n\u001b[0;32m---> 98\u001b[0;31m variables, grad_variables, retain_graph)\n\u001b[0m\u001b[1;32m 99\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 100\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mRuntimeError\u001b[0m: ConvNdBackward: expected Variable at argument 0 (got None)"
]
}
],
"source": [
"train(G(),disc=D4())"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Variable containing:\n",
"-3.6873\n",
"-3.6873\n",
"-3.6873\n",
"-3.6873\n",
"-3.6873\n",
"[torch.FloatTensor of size 5x1]\n",
"\n",
"Variable containing:\n",
"-4.2763\n",
"-4.2791\n",
"-4.2800\n",
"-4.2772\n",
"-4.2787\n",
"[torch.FloatTensor of size 5x1]\n",
"\n",
"Variable containing:\n",
"-4.0579\n",
"-3.9405\n",
"-3.7507\n",
"-4.1994\n",
"-4.0711\n",
"[torch.FloatTensor of size 5x1]\n",
"\n",
"Variable containing:\n",
"-4.2828\n",
"-4.2846\n",
"-4.2845\n",
"-4.2837\n",
"-4.2790\n",
"[torch.FloatTensor of size 5x1]\n",
"\n"
]
}
],
"source": [
"train(G(),disc=D5())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.13"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment