msb-public
/
PaddleSpeech
mirror of https://github.com/PaddlePaddle/PaddleSpeech
1
0
Code Issues Projects Releases Wiki Activity

add notebook test

Browse Source
pull/578/head
Hui Zhang 4 years ago
parent c607bff282
commit 20f1976899
4 changed files with 1477 additions and 202 deletions
Show Stats Download Patch File Download Diff File

375
.notebook/Linear_test.ipynb
Unescape View File

@ -0,0 +1,375 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "academic-surname",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/workspace/DeepSpeech-2.x/tools/venv/lib/python3.7/site-packages/paddle/fluid/layers/utils.py:26: DeprecationWarning: `np.int` is a deprecated alias for the builtin `int`. To silence this warning, use `int` by itself. Doing this will not modify any behavior and is safe. When replacing `np.int`, you may wish to use e.g. `np.int64` or `np.int32` to specify the precision. If you wish to review your current use, check the release note link for additional information.\n",
"Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations\n",
" def convert_to_list(value, n, name, dtype=np.int):\n"
]
}
],
"source": [
"import paddle\n",
"from paddle import nn"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "fundamental-treasure",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/workspace/DeepSpeech-2.x/tools/venv/lib/python3.7/site-packages/ipykernel/ipkernel.py:283: DeprecationWarning: `should_run_async` will not call `transform_cell` automatically in the future. Please pass the result to `transformed_cell` argument and any exception that happen during thetransform in `preprocessing_exc_tuple` in IPython 7.17 and above.\n",
" and should_run_async(code)\n"
]
}
],
"source": [
"L = nn.Linear(256, 2048)\n",
"L2 = nn.Linear(2048, 256)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "consolidated-elephant",
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import torch\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "moderate-noise",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"float64\n",
"Tensor(shape=[2, 51, 256], dtype=float32, place=CUDAPlace(0), stop_gradient=True,\n",
" [[[-0.03137276, 0.75036579, -0.62955737, ..., -0.39516482, 2.41965628, 0.19466873],\n",
" [ 0.55916852, 1.13357353, 0.28754908, ..., 0.28860641, 0.48257691, -1.07664418],\n",
" [-0.27433595, -0.05911482, 0.04942252, ..., 0.46596146, 1.24395037, -1.98374581],\n",
" ...,\n",
" [-0.45322138, 0.51459873, 0.28475651, ..., -0.90797561, -0.80436397, -2.30388594],\n",
" [ 0.20310247, 1.90435207, -1.02483511, ..., -1.59850407, -0.30733466, 0.49769276],\n",
" [-2.63085651, -0.52244109, 0.32019949, ..., 1.10662329, -0.55995786, -0.36770794]],\n",
"\n",
" [[-1.78831303, 2.24759626, 0.41386250, ..., -0.30020580, -0.16084948, 0.93251175],\n",
" [ 0.03264519, -0.92942363, 1.58523536, ..., 1.23681784, -0.94711000, 0.63553023],\n",
" [-0.19725564, -2.38587499, -0.29334834, ..., 0.83498263, -0.58492625, 0.58732986],\n",
" ...,\n",
" [-0.61646742, -1.02978027, 0.45410269, ..., 0.87052751, -0.20801133, 2.17943859],\n",
" [-0.67230755, -0.79410625, -0.13054833, ..., -1.18138039, -0.47578079, -0.22610545],\n",
" [ 2.57333422, 0.63872230, 0.70852041, ..., -0.44040251, -0.33339104, -0.24722832]]])\n",
"tensor([[[-0.0314, 0.7504, -0.6296, ..., -0.3952, 2.4197, 0.1947],\n",
" [ 0.5592, 1.1336, 0.2875, ..., 0.2886, 0.4826, -1.0766],\n",
" [-0.2743, -0.0591, 0.0494, ..., 0.4660, 1.2440, -1.9837],\n",
" ...,\n",
" [-0.4532, 0.5146, 0.2848, ..., -0.9080, -0.8044, -2.3039],\n",
" [ 0.2031, 1.9044, -1.0248, ..., -1.5985, -0.3073, 0.4977],\n",
" [-2.6309, -0.5224, 0.3202, ..., 1.1066, -0.5600, -0.3677]],\n",
"\n",
" [[-1.7883, 2.2476, 0.4139, ..., -0.3002, -0.1608, 0.9325],\n",
" [ 0.0326, -0.9294, 1.5852, ..., 1.2368, -0.9471, 0.6355],\n",
" [-0.1973, -2.3859, -0.2933, ..., 0.8350, -0.5849, 0.5873],\n",
" ...,\n",
" [-0.6165, -1.0298, 0.4541, ..., 0.8705, -0.2080, 2.1794],\n",
" [-0.6723, -0.7941, -0.1305, ..., -1.1814, -0.4758, -0.2261],\n",
" [ 2.5733, 0.6387, 0.7085, ..., -0.4404, -0.3334, -0.2472]]])\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/workspace/DeepSpeech-2.x/tools/venv/lib/python3.7/site-packages/ipykernel/ipkernel.py:283: DeprecationWarning: `should_run_async` will not call `transform_cell` automatically in the future. Please pass the result to `transformed_cell` argument and any exception that happen during thetransform in `preprocessing_exc_tuple` in IPython 7.17 and above.\n",
" and should_run_async(code)\n"
]
}
],
"source": [
"x = np.random.randn(2, 51, 256)\n",
"print(x.dtype)\n",
"px = paddle.to_tensor(x, dtype='float32')\n",
"tx = torch.tensor(x, dtype=torch.float32)\n",
"print(px)\n",
"print(tx)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cooked-progressive",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 5,
"id": "mechanical-prisoner",
"metadata": {},
"outputs": [],
"source": [
"data = np.load('enc_0_ff_out.npz', allow_pickle=True)\n",
"t_norm_ff = data['norm_ff']\n",
"t_ff_out = data['ff_out']\n",
"t_ff_l_x = data['ff_l_x']\n",
"t_ff_l_a_x = data['ff_l_a_x']\n",
"t_ff_l_a_l_x = data['ff_l_a_l_x']\n",
"t_ps = data['ps']"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "indie-marriage",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 7,
"id": "assured-zambia",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"True\n",
"True\n",
"True\n",
"True\n"
]
}
],
"source": [
"L.set_state_dict({'weight': t_ps[0].T, 'bias': t_ps[1]})\n",
"L2.set_state_dict({'weight': t_ps[2].T, 'bias': t_ps[3]})\n",
"\n",
"ps = []\n",
"for n, p in L.named_parameters():\n",
" ps.append(p)\n",
"\n",
"for n, p in L2.state_dict().items():\n",
" ps.append(p)\n",
" \n",
"for p, tp in zip(ps, t_ps):\n",
" print(np.allclose(p.numpy(), tp.T))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "committed-jacob",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "extreme-traffic",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "optimum-milwaukee",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 11,
"id": "viral-indian",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"True\n",
"True\n",
"True\n",
"True\n"
]
}
],
"source": [
"# data = np.load('enc_0_ff_out.npz', allow_pickle=True)\n",
"# t_norm_ff = data['norm_ff']\n",
"# t_ff_out = data['ff_out']\n",
"# t_ff_l_x = data['ff_l_x']\n",
"# t_ff_l_a_x = data['ff_l_a_x']\n",
"# t_ff_l_a_l_x = data['ff_l_a_l_x']\n",
"# t_ps = data['ps']\n",
"TL = torch.nn.Linear(256, 2048)\n",
"TL2 = torch.nn.Linear(2048, 256)\n",
"TL.load_state_dict({'weight': torch.tensor(t_ps[0]), 'bias': torch.tensor(t_ps[1])})\n",
"TL2.load_state_dict({'weight': torch.tensor(t_ps[2]), 'bias': torch.tensor(t_ps[3])})\n",
"\n",
"# for n, p in TL.named_parameters():\n",
"# print(n, p)\n",
"# for n, p in TL2.named_parameters():\n",
"# print(n, p)\n",
"\n",
"ps = []\n",
"for n, p in TL.state_dict().items():\n",
" ps.append(p.data.numpy())\n",
" \n",
"for n, p in TL2.state_dict().items():\n",
" ps.append(p.data.numpy())\n",
" \n",
"for p, tp in zip(ps, t_ps):\n",
" print(np.allclose(p, tp))"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "skilled-vietnamese",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[-0.25528666 -0.9090747 0.12996 ... 0.02552819 0.37376517\n",
" -0.558986 ]\n",
" [-0.45657372 0.23811203 0.33472425 ... 1.0797666 -0.7263612\n",
" 0.31549692]]\n",
"[[-0.25528657 -0.9090746 0.12996009 ... 0.02552832 0.37376505\n",
" -0.5589858 ]\n",
" [-0.45657367 0.23811209 0.33472428 ... 1.0797666 -0.7263612\n",
" 0.31549698]]\n",
"True\n",
"False\n"
]
}
],
"source": [
"y = L(px)\n",
"print(y.numpy())\n",
"\n",
"ty = TL(tx)\n",
"print(ty.data.numpy())\n",
"print(np.allclose(px.numpy(), tx.detach().numpy()))\n",
"print(np.allclose(y.numpy(), ty.detach().numpy()))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "incorrect-allah",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "prostate-cameroon",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 14,
"id": "governmental-surge",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[ 0.07453135 0.0698561 0.6273111 ... 0.5845924 -0.65527105\n",
" 0.5881643 ]\n",
" [ 0.3902049 -0.17455879 -1.1802813 ... -0.36912322 0.55681896\n",
" -0.11917676]]\n",
"[[ 0.07453132 0.06985616 0.62731117 ... 0.5845925 -0.65527105\n",
" 0.5881642 ]\n",
" [ 0.39020485 -0.17455864 -1.1802814 ... -0.3691232 0.556819\n",
" -0.11917675]]\n",
"True\n",
"False\n",
"True\n"
]
}
],
"source": [
"x = np.random.randn(2, 256)\n",
"px = paddle.to_tensor(x, dtype='float32')\n",
"tx = torch.tensor(x, dtype=torch.float32)\n",
"y = L(px)\n",
"print(y.numpy())\n",
"ty = TL(tx)\n",
"print(ty.data.numpy())\n",
"print(np.allclose(px.numpy(), tx.detach().numpy()))\n",
"print(np.allclose(y.numpy(), ty.detach().numpy()))\n",
"print(np.allclose(y.numpy(), ty.detach().numpy(), atol=1e-5))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "confidential-jacket",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "improved-civilization",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.7.0"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

229
.notebook/layer_norm_test.ipynb
Unescape View File

@ -0,0 +1,229 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 32,
"id": "academic-surname",
"metadata": {},
"outputs": [],
"source": [
"import paddle\n",
"from paddle import nn"
]
},
{
"cell_type": "code",
"execution_count": 33,
"id": "fundamental-treasure",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Parameter containing:\n",
"Tensor(shape=[256], dtype=float32, place=CUDAPlace(0), stop_gradient=False,\n",
" [1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.])\n",
"Parameter containing:\n",
"Tensor(shape=[256], dtype=float32, place=CUDAPlace(0), stop_gradient=False,\n",
" [0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.])\n"
]
}
],
"source": [
"L = nn.LayerNorm(256, epsilon=1e-12)\n",
"for p in L.parameters():\n",
" print(p)"
]
},
{
"cell_type": "code",
"execution_count": 34,
"id": "consolidated-elephant",
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n"
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "moderate-noise",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"float64\n"
]
}
],
"source": [
"x = np.random.randn(2, 51, 256)\n",
"print(x.dtype)"
]
},
{
"cell_type": "code",
"execution_count": 47,
"id": "cooked-progressive",
"metadata": {},
"outputs": [],
"source": [
"y = L(paddle.to_tensor(x, dtype='float32'))"
]
},
{
"cell_type": "code",
"execution_count": 48,
"id": "optimum-milwaukee",
"metadata": {},
"outputs": [],
"source": [
"import torch"
]
},
{
"cell_type": "code",
"execution_count": 49,
"id": "viral-indian",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Parameter containing:\n",
"tensor([1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
" 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
" 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
" 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
" 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
" 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
" 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
" 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
" 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
" 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
" 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
" 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
" 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
" 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1.,\n",
" 1., 1., 1., 1.], requires_grad=True)\n",
"Parameter containing:\n",
"tensor([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,\n",
" 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.],\n",
" requires_grad=True)\n"
]
}
],
"source": [
"TL = torch.nn.LayerNorm(256, eps=1e-12)\n",
"for p in TL.parameters():\n",
" print(p)"
]
},
{
"cell_type": "code",
"execution_count": 50,
"id": "skilled-vietnamese",
"metadata": {},
"outputs": [],
"source": [
"ty = TL(torch.tensor(x, dtype=torch.float32))"
]
},
{
"cell_type": "code",
"execution_count": 51,
"id": "incorrect-allah",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"False"
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"np.allclose(y.numpy(), ty.detach().numpy())"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "prostate-cameroon",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 52,
"id": "governmental-surge",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"True"
]
},
"execution_count": 52,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"x = np.random.randn(2, 256)\n",
"y = L(paddle.to_tensor(x, dtype='float32'))\n",
"ty = TL(torch.tensor(x, dtype=torch.float32))\n",
"np.allclose(y.numpy(), ty.detach().numpy())"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "confidential-jacket",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.7.0"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

160
.notebook/position_embeding_check.ipynb
Unescape View File

@ -0,0 +1,160 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 29,
"id": "designing-borough",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[ 0.0000000e+00 0.0000000e+00 0.0000000e+00 ... 0.0000000e+00\n",
" 0.0000000e+00 0.0000000e+00]\n",
" [ 8.4147096e-01 8.0196178e-01 7.6172036e-01 ... 1.2409373e-04\n",
" 1.1547816e-04 1.0746076e-04]\n",
" [ 9.0929741e-01 9.5814437e-01 9.8704624e-01 ... 2.4818745e-04\n",
" 2.3095631e-04 2.1492151e-04]\n",
" ...\n",
" [ 3.7960774e-01 7.4510968e-01 7.3418564e-01 ... 1.2036801e-02\n",
" 1.1201146e-02 1.0423505e-02]\n",
" [-5.7338190e-01 -8.9752287e-02 -4.1488394e-02 ... 1.2160885e-02\n",
" 1.1316618e-02 1.0530960e-02]\n",
" [-9.9920684e-01 -8.5234123e-01 -7.8794664e-01 ... 1.2284970e-02\n",
" 1.1432089e-02 1.0638415e-02]]\n",
"True\n",
"True\n"
]
}
],
"source": [
"import torch\n",
"import math\n",
"import numpy as np\n",
"\n",
"max_len=100\n",
"d_model=256\n",
"\n",
"pe = torch.zeros(max_len, d_model)\n",
"position = torch.arange(0, max_len,\n",
" dtype=torch.float32).unsqueeze(1)\n",
"toruch_position = position\n",
"div_term = torch.exp(\n",
" torch.arange(0, d_model, 2, dtype=torch.float32) *\n",
" -(math.log(10000.0) / d_model))\n",
"tourch_div_term = div_term.cpu().detach().numpy()\n",
"\n",
"\n",
"\n",
"torhc_sin = torch.sin(position * div_term)\n",
"torhc_cos = torch.cos(position * div_term)\n",
"print(torhc_sin.cpu().detach().numpy())\n",
"np_sin = np.sin((position * div_term).cpu().detach().numpy())\n",
"np_cos = np.cos((position * div_term).cpu().detach().numpy())\n",
"print(np.allclose(np_sin, torhc_sin.cpu().detach().numpy()))\n",
"print(np.allclose(np_cos, torhc_cos.cpu().detach().numpy()))\n",
"pe[:, 0::2] = torhc_sin\n",
"pe[:, 1::2] = torhc_cos\n",
"tourch_pe = pe.cpu().detach().numpy()"
]
},
{
"cell_type": "code",
"execution_count": 37,
"id": "swiss-referral",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"True\n",
"True\n",
"False\n",
"False\n",
"False\n",
"False\n"
]
}
],
"source": [
"import paddle\n",
"ppe = paddle.zeros([max_len, d_model])\n",
"position = paddle.arange(0, max_len,\n",
" dtype='float32').unsqueeze(1)\n",
"print(np.allclose(position.numpy(), toruch_position))\n",
"div_term = paddle.exp(\n",
" paddle.arange(0, d_model, 2, dtype='float32') *\n",
" -(math.log(10000.0) / d_model))\n",
"print(np.allclose(div_term.numpy(), tourch_div_term))\n",
"\n",
"\n",
"\n",
"p_sin = paddle.sin(position * div_term)\n",
"p_cos = paddle.cos(position * div_term)\n",
"print(np.allclose(np_sin, p_sin.numpy(), rtol=1.e-6, atol=0))\n",
"print(np.allclose(np_cos, p_cos.numpy(), rtol=1.e-6, atol=0))\n",
"ppe[:, 0::2] = p_sin\n",
"ppe[:, 1::2] = p_cos\n",
"print(np.allclose(p_sin.numpy(), torhc_sin.cpu().detach().numpy()))\n",
"print(np.allclose(p_cos.numpy(), torhc_cos.cpu().detach().numpy()))"
]
},
{
"cell_type": "code",
"execution_count": 34,
"id": "integrated-boards",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"False\n"
]
}
],
"source": [
"print(np.allclose(ppe.numpy(), pe.numpy()))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "flying-reserve",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "revised-divide",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.7.0"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

915
.notebook/u2_model.ipynb
View File

File diff suppressed because it is too large Load Diff
Write Preview
Loading…
Cancel
Save