wangwei
/
machinelearning_notebook
Not watched
1
0
Fork 0
Code
Releases 0 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
Browse Source

Fix some minor errors

pull/1/head
bushuhui 6 years ago
parent
0a1fb99948
commit
48de820ea5
3 changed files with 218 additions and 223 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. +72
    -55
      6_pytorch/1_NN/linear-regression-gradient-descend.ipynb
  2. +66
    -63
      6_pytorch/1_NN/logistic-regression.ipynb
  3. +80
    -105
      6_pytorch/PyTorch_quick_intro.ipynb

+ 72
- 55
6_pytorch/1_NN/linear-regression-gradient-descend.ipynb
File diff suppressed because it is too large
View File


+ 66
- 63
6_pytorch/1_NN/logistic-regression.ipynb
File diff suppressed because it is too large
View File


+ 80
- 105
6_pytorch/PyTorch_quick_intro.ipynb View File

@@ -41,8 +41,8 @@
{
"data": {
"text/plain": [
"tensor([[1.2563e-37, 0.0000e+00, 5.7453e-44],\n",
" [0.0000e+00, nan, 4.5814e-41],\n",
"tensor([[3.7158e-37, 0.0000e+00, 5.7453e-44],\n",
" [0.0000e+00, nan, 4.5745e-41],\n",
" [1.3733e-14, 6.4076e+07, 2.0706e-19],\n",
" [7.3909e+22, 2.4176e-12, 1.1625e+33],\n",
" [8.9605e-01, 1.1632e+33, 5.6003e-02]])"
@@ -67,11 +67,11 @@
{
"data": {
"text/plain": [
"tensor([[0.7149, 0.6065, 0.8056],\n",
" [0.2450, 0.1942, 0.5305],\n",
" [0.6735, 0.7798, 0.6060],\n",
" [0.1072, 0.8325, 0.8617],\n",
" [0.5117, 0.2246, 0.4984]])"
"tensor([[0.4157, 0.7456, 0.9620],\n",
" [0.3965, 0.8182, 0.7723],\n",
" [0.3705, 0.9292, 0.0063],\n",
" [0.4054, 0.9137, 0.9611],\n",
" [0.8307, 0.0900, 0.6887]])"
]
},
"execution_count": 3,
@@ -128,11 +128,11 @@
{
"data": {
"text/plain": [
"tensor([[1.6605, 1.1155, 1.2724],\n",
" [0.6727, 0.6428, 1.0969],\n",
" [1.4898, 1.7437, 1.3258],\n",
" [0.8030, 1.5725, 1.4709],\n",
" [0.6847, 0.4828, 0.6183]])"
"tensor([[0.5021, 1.2500, 1.4749],\n",
" [0.6019, 0.9378, 1.7240],\n",
" [1.2752, 1.3837, 0.6832],\n",
" [1.2053, 1.4374, 1.5160],\n",
" [0.9404, 0.8743, 0.8164]])"
]
},
"execution_count": 5,
@@ -154,13 +154,11 @@
{
"data": {
"text/plain": [
"\n",
" 0.4063 0.7378 1.2411\n",
" 0.0687 0.7725 0.0634\n",
" 1.1016 1.4291 0.7324\n",
" 0.7604 1.2880 0.4597\n",
" 0.6020 1.0124 1.0185\n",
"[torch.FloatTensor of size 5x3]"
"tensor([[0.5021, 1.2500, 1.4749],\n",
" [0.6019, 0.9378, 1.7240],\n",
" [1.2752, 1.3837, 0.6832],\n",
" [1.2053, 1.4374, 1.5160],\n",
" [0.9404, 0.8743, 0.8164]])"
]
},
"execution_count": 6,
@@ -210,23 +208,23 @@
"output_type": "stream",
"text": [
"最初y\n",
"tensor([[0.9778, 0.9240, 0.0337],\n",
" [0.7461, 0.8548, 0.5141],\n",
" [0.5364, 0.9908, 0.1078],\n",
" [0.6880, 0.1675, 0.0010],\n",
" [0.9120, 0.5539, 0.2896]])\n",
"tensor([[0.0864, 0.5044, 0.5128],\n",
" [0.2054, 0.1196, 0.9517],\n",
" [0.9047, 0.4545, 0.6769],\n",
" [0.7999, 0.5236, 0.5549],\n",
" [0.1097, 0.7843, 0.1277]])\n",
"第一种加法，y的结果\n",
"tensor([[0.9778, 0.9240, 0.0337],\n",
" [0.7461, 0.8548, 0.5141],\n",
" [0.5364, 0.9908, 0.1078],\n",
" [0.6880, 0.1675, 0.0010],\n",
" [0.9120, 0.5539, 0.2896]])\n",
"tensor([[0.0864, 0.5044, 0.5128],\n",
" [0.2054, 0.1196, 0.9517],\n",
" [0.9047, 0.4545, 0.6769],\n",
" [0.7999, 0.5236, 0.5549],\n",
" [0.1097, 0.7843, 0.1277]])\n",
"第二种加法，y的结果\n",
"tensor([[1.7112, 1.2969, 0.3289],\n",
" [0.7841, 1.0128, 0.7596],\n",
" [1.1364, 1.1541, 0.8970],\n",
" [0.8831, 0.7063, 0.3158],\n",
" [1.5160, 1.3610, 0.8437]])\n"
"tensor([[0.5021, 1.2500, 1.4749],\n",
" [0.6019, 0.9378, 1.7240],\n",
" [1.2752, 1.3837, 0.6832],\n",
" [1.2053, 1.4374, 1.5160],\n",
" [0.9404, 0.8743, 0.8164]])\n"
]
}
],
@@ -252,22 +250,16 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\n",
" 0.2522\n",
" 0.7138\n",
" 0.6019\n",
" 0.3675\n",
" 0.5104\n",
"[torch.FloatTensor of size 5]"
"tensor([0.7456, 0.8182, 0.9292, 0.9137, 0.0900])"
]
},
"execution_count": 9,
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
@@ -288,7 +280,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 9,
"metadata": {},
"outputs": [
{
@@ -297,7 +289,7 @@
"tensor([1., 1., 1., 1., 1.])"
]
},
"execution_count": 8,
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@@ -309,7 +301,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 10,
"metadata": {},
"outputs": [
{
@@ -318,7 +310,7 @@
"array([1., 1., 1., 1., 1.], dtype=float32)"
]
},
"execution_count": 9,
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
@@ -330,7 +322,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 11,
"metadata": {},
"outputs": [
{
@@ -393,18 +385,18 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"tensor([[1.6605, 1.1155, 1.2724],\n",
" [0.6727, 0.6428, 1.0969],\n",
" [1.4898, 1.7437, 1.3258],\n",
" [0.8030, 1.5725, 1.4709],\n",
" [0.6847, 0.4828, 0.6183]], device='cuda:0')\n"
"tensor([[0.9177, 1.9956, 2.4369],\n",
" [0.9984, 1.7561, 2.4963],\n",
" [1.6457, 2.3129, 0.6895],\n",
" [1.6107, 2.3511, 2.4770],\n",
" [1.7711, 0.9643, 1.5050]], device='cuda:0')\n"
]
}
],
@@ -446,7 +438,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
@@ -455,7 +447,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 14,
"metadata": {
"scrolled": true
},
@@ -467,7 +459,7 @@
" [1., 1.]], requires_grad=True)"
]
},
"execution_count": 9,
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
@@ -480,7 +472,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 15,
"metadata": {
"scrolled": true
},
@@ -491,7 +483,7 @@
"tensor(4., grad_fn=<SumBackward0>)"
]
},
"execution_count": 10,
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
@@ -503,16 +495,16 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<SumBackward0 at 0x7fb610129c88>"
"<SumBackward0 at 0x7f85680bd710>"
]
},
"execution_count": 11,
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
@@ -523,7 +515,7 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
@@ -532,7 +524,7 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 18,
"metadata": {},
"outputs": [
{
@@ -542,7 +534,7 @@
" [1., 1.]])"
]
},
"execution_count": 13,
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
@@ -562,7 +554,7 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": 19,
"metadata": {},
"outputs": [
{
@@ -572,7 +564,7 @@
" [2., 2.]])"
]
},
"execution_count": 14,
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
@@ -584,7 +576,7 @@
},
{
"cell_type": "code",
"execution_count": 15,
"execution_count": 20,
"metadata": {
"scrolled": true
},
@@ -596,7 +588,7 @@
" [3., 3.]])"
]
},
"execution_count": 15,
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
@@ -608,7 +600,7 @@
},
{
"cell_type": "code",
"execution_count": 16,
"execution_count": 21,
"metadata": {},
"outputs": [
{
@@ -618,7 +610,7 @@
" [0., 0.]])"
]
},
"execution_count": 16,
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
@@ -630,7 +622,7 @@
},
{
"cell_type": "code",
"execution_count": 26,
"execution_count": 22,
"metadata": {},
"outputs": [
{
@@ -640,7 +632,7 @@
" [1., 1.]])"
]
},
"execution_count": 26,
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
@@ -659,7 +651,7 @@
},
{
"cell_type": "code",
"execution_count": 17,
"execution_count": 24,
"metadata": {},
"outputs": [
{
@@ -681,7 +673,7 @@
" [0.5403, 0.5403, 0.5403, 0.5403, 0.5403]])"
]
},
"execution_count": 17,
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
@@ -713,7 +705,7 @@
},
{
"cell_type": "code",
"execution_count": 27,
"execution_count": 25,
"metadata": {},
"outputs": [
{
@@ -775,7 +767,7 @@
},
{
"cell_type": "code",
"execution_count": 28,
"execution_count": 26,
"metadata": {},
"outputs": [
{
@@ -793,7 +785,7 @@
},
{
"cell_type": "code",
"execution_count": 29,
"execution_count": 27,
"metadata": {},
"outputs": [
{
@@ -827,7 +819,7 @@
},
{
"cell_type": "code",
"execution_count": 30,
"execution_count": 28,
"metadata": {
"scrolled": true
},
@@ -838,7 +830,7 @@
"torch.Size([1, 10])"
]
},
"execution_count": 30,
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
@@ -851,7 +843,7 @@
},
{
"cell_type": "code",
"execution_count": 31,
"execution_count": 29,
"metadata": {},
"outputs": [],
"source": [
@@ -877,7 +869,7 @@
},
{
"cell_type": "code",
"execution_count": 39,
"execution_count": 30,
"metadata": {
"scrolled": true
},
@@ -885,10 +877,10 @@
{
"data": {
"text/plain": [
"tensor(28.3834, grad_fn=<MseLossBackward>)"
"tensor(28.6268, grad_fn=<MseLossBackward>)"
]
},
"execution_count": 39,
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
}
@@ -920,7 +912,7 @@
},
{
"cell_type": "code",
"execution_count": 32,
"execution_count": 31,
"metadata": {},
"outputs": [
{
@@ -928,26 +920,9 @@
"output_type": "stream",
"text": [
"反向传播之前 conv1.bias的梯度\n",
"Variable containing:\n",
" 0\n",
" 0\n",
" 0\n",
" 0\n",
" 0\n",
" 0\n",
"[torch.FloatTensor of size 6]\n",
"\n",
"tensor([0., 0., 0., 0., 0., 0.])\n",
"反向传播之后 conv1.bias的梯度\n",
"Variable containing:\n",
"1.00000e-02 *\n",
" -4.2109\n",
" -2.7638\n",
" -5.8431\n",
" 1.3761\n",
" -2.4141\n",
" -1.2015\n",
"[torch.FloatTensor of size 6]\n",
"\n"
"tensor([-0.0368, 0.0240, 0.0169, 0.0118, -0.0122, -0.0259])\n"
]
}
],
@@ -990,7 +965,7 @@
},
{
"cell_type": "code",
"execution_count": 33,
"execution_count": 32,
"metadata": {},
"outputs": [],
"source": [


Write Preview
Loading…
Cancel
Save