diff --git a/tutorials/source_zh_cn/advance/network/control_flow.ipynb b/tutorials/source_zh_cn/advance/network/control_flow.ipynb index b496aec04c527584b148c7cd6900625409b9cacc..a7653fc425c17dfdd1e00bb96766db75834dfcdf 100644 --- a/tutorials/source_zh_cn/advance/network/control_flow.ipynb +++ b/tutorials/source_zh_cn/advance/network/control_flow.ipynb @@ -66,7 +66,7 @@ }, { "cell_type": "code", - "execution_count": 29, + "execution_count": 1, "metadata": {}, "outputs": [ { @@ -144,7 +144,7 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 2, "metadata": { "ExecuteTime": { "end_time": "2022-01-07T03:35:40.804471Z", @@ -200,7 +200,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 3, "metadata": { "ExecuteTime": { "end_time": "2022-01-07T03:35:40.922574Z", @@ -255,7 +255,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 4, "metadata": { "ExecuteTime": { "end_time": "2022-01-07T03:35:40.985953Z", @@ -330,7 +330,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 5, "metadata": { "ExecuteTime": { "end_time": "2022-01-07T03:35:41.051756Z", @@ -390,7 +390,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": {}, "outputs": [], "source": [ diff --git a/tutorials/source_zh_cn/advance/network/loss.ipynb b/tutorials/source_zh_cn/advance/network/loss.ipynb index 8f671c56bbd39dc0c2c1b8edbc23a6804d2a24d7..dc0fa8047d811732ab2e9be240427eefb083cd68 100644 --- a/tutorials/source_zh_cn/advance/network/loss.ipynb +++ b/tutorials/source_zh_cn/advance/network/loss.ipynb @@ -37,7 +37,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 1, "metadata": { "ExecuteTime": { "end_time": "2021-12-29T03:42:22.717822Z", @@ -100,7 +100,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 2, "metadata": { "ExecuteTime": { "end_time": "2021-12-29T03:42:22.729232Z", @@ -158,7 +158,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 3, "metadata": { "ExecuteTime": { "end_time": "2021-12-29T03:42:22.766767Z", @@ -209,14 +209,32 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": { "ExecuteTime": { "end_time": "2021-12-29T03:42:23.488075Z", "start_time": "2021-12-29T03:42:23.312491Z" } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch:[ 0/ 1], step:[ 1/ 10], loss:[ 9.128/ 9.128], time:129.267, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 2/ 10], loss:[ 9.771/ 9.450], time:0.578, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 3/ 10], loss:[10.412/ 9.770], time:0.623, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 4/ 10], loss:[12.535/10.461], time:2.648, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 5/ 10], loss:[ 8.608/10.091], time:0.844, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 6/ 10], loss:[11.945/10.400], time:4.566, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 7/ 10], loss:[ 7.768/10.024], time:0.850, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 8/ 10], loss:[ 7.319/ 9.686], time:0.877, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 9/ 10], loss:[ 7.356/ 9.427], time:0.914, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 10/ 10], loss:[ 5.024/ 8.987], time:0.777, lr:0.00500.\n", + "Epoch time: 155.354,per step time: 15.535,avg loss: 8.987\n" + ] + } + ], "source": [ "from mindspore import Model\n", "from mindspore import dataset as ds\n", @@ -257,25 +275,6 @@ "model.train(epoch=1, train_dataset=ds_train, callbacks=[LossMonitor(0.005)])" ] }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "```Text\n", - "Epoch:[ 0/ 1], step:[ 1/ 10], loss:[ 9.128/ 9.128], time:129.267, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 2/ 10], loss:[ 9.771/ 9.450], time:0.578, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 3/ 10], loss:[10.412/ 9.770], time:0.623, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 4/ 10], loss:[12.535/10.461], time:2.648, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 5/ 10], loss:[ 8.608/10.091], time:0.844, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 6/ 10], loss:[11.945/10.400], time:4.566, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 7/ 10], loss:[ 7.768/10.024], time:0.850, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 8/ 10], loss:[ 7.319/ 9.686], time:0.877, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 9/ 10], loss:[ 7.356/ 9.427], time:0.914, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 10/ 10], loss:[ 5.024/ 8.987], time:0.777, lr:0.00500.\n", - "Epoch time: 155.354,per step time: 15.535,avg loss: 8.987\n", - "```" - ] - }, { "cell_type": "markdown", "metadata": {}, @@ -406,14 +405,32 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": { "ExecuteTime": { "end_time": "2021-12-29T03:42:24.079033Z", "start_time": "2021-12-29T03:42:23.851418Z" } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch:[ 0/ 1], step:[ 1/ 10], loss:[ 9.128/ 9.128], time:129.267, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 2/ 10], loss:[ 9.771/ 9.450], time:0.578, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 3/ 10], loss:[10.412/ 9.770], time:0.623, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 4/ 10], loss:[12.535/10.461], time:2.648, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 5/ 10], loss:[ 8.608/10.091], time:0.844, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 6/ 10], loss:[11.945/10.400], time:4.566, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 7/ 10], loss:[ 7.768/10.024], time:0.850, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 8/ 10], loss:[ 7.319/ 9.686], time:0.877, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 9/ 10], loss:[ 7.356/ 9.427], time:0.914, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 10/ 10], loss:[ 5.024/ 8.987], time:0.777, lr:0.00500.\n", + "Epoch time: 155.354,per step time: 15.535,avg loss: 8.987\n" + ] + } + ], "source": [ "ds_train = create_multilabel_dataset(num_data=160)\n", "net = LinearNet()\n", @@ -433,25 +450,6 @@ "model.train(epoch=1, train_dataset=ds_train, callbacks=[LossMonitor(0.005)])" ] }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "```Text\n", - "Epoch:[ 0/ 1], step:[ 1/ 10], loss:[ 9.128/ 9.128], time:129.267, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 2/ 10], loss:[ 9.771/ 9.450], time:0.578, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 3/ 10], loss:[10.412/ 9.770], time:0.623, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 4/ 10], loss:[12.535/10.461], time:2.648, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 5/ 10], loss:[ 8.608/10.091], time:0.844, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 6/ 10], loss:[11.945/10.400], time:4.566, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 7/ 10], loss:[ 7.768/10.024], time:0.850, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 8/ 10], loss:[ 7.319/ 9.686], time:0.877, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 9/ 10], loss:[ 7.356/ 9.427], time:0.914, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 10/ 10], loss:[ 5.024/ 8.987], time:0.777, lr:0.00500.\n", - "Epoch time: 155.354,per step time: 15.535,avg loss: 8.987\n", - "```" - ] - }, { "cell_type": "markdown", "metadata": {}, diff --git a/tutorials/source_zh_cn/advance/network/parameter.ipynb b/tutorials/source_zh_cn/advance/network/parameter.ipynb index fd86cc705aab0576c4178289f248fc1c239ef884..a9020ebb9bc1c361a0e1196409fef2ae87ef6e7e 100644 --- a/tutorials/source_zh_cn/advance/network/parameter.ipynb +++ b/tutorials/source_zh_cn/advance/network/parameter.ipynb @@ -112,7 +112,7 @@ }, { "cell_type": "code", - "execution_count": 91, + "execution_count": 3, "metadata": {}, "outputs": [ { @@ -148,7 +148,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 4, "metadata": {}, "outputs": [ { @@ -178,7 +178,7 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -210,7 +210,7 @@ }, { "cell_type": "code", - "execution_count": 141, + "execution_count": 6, "metadata": {}, "outputs": [ { @@ -243,7 +243,7 @@ }, { "cell_type": "code", - "execution_count": 48, + "execution_count": 7, "metadata": {}, "outputs": [ { @@ -275,7 +275,7 @@ }, { "cell_type": "code", - "execution_count": 136, + "execution_count": 8, "metadata": {}, "outputs": [ { @@ -308,7 +308,7 @@ }, { "cell_type": "code", - "execution_count": 144, + "execution_count": 9, "metadata": {}, "outputs": [ { @@ -338,7 +338,7 @@ }, { "cell_type": "code", - "execution_count": 102, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -385,9 +385,29 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[[[[ 6.2076533e-01 8.7720710e-01 8.7720710e-01 ... 8.7720710e-01\n", + " 8.7720710e-01 2.7743810e-01]\n", + " [ 6.5210247e-01 7.0859784e-01 7.0859784e-01 ... 7.0859784e-01\n", + " 7.0859784e-01 -1.1080378e-01]\n", + " [ 6.5210247e-01 7.0859784e-01 7.0859784e-01 ... 7.0859784e-01\n", + " 7.0859784e-01 -1.1080378e-01]\n", + " ...\n", + " [ 1.1884158e+00 5.6527245e-01 5.6527245e-01 ... 5.6527245e-01\n", + " 5.6527245e-01 -6.5525830e-01]\n", + " [ 1.1884158e+00 5.6527245e-01 5.6527245e-01 ... 5.6527245e-01\n", + " 5.6527245e-01 -6.5525824e-01]\n", + " [ 1.6852863e+00 1.0636344e+00 1.0636344e+00 ... 1.0636345e+00\n", + " 1.0636345e+00 -9.2076123e-02]]]]\n" + ] + } + ], "source": [ "import numpy as np\n", "import mindspore.nn as nn\n", @@ -406,27 +426,6 @@ "print(output)" ] }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "```text\n", - "[[[[ 6.2076533e-01 8.7720710e-01 8.7720710e-01 ... 8.7720710e-01\n", - " 8.7720710e-01 2.7743810e-01]\n", - " [ 6.5210247e-01 7.0859784e-01 7.0859784e-01 ... 7.0859784e-01\n", - " 7.0859784e-01 -1.1080378e-01]\n", - " [ 6.5210247e-01 7.0859784e-01 7.0859784e-01 ... 7.0859784e-01\n", - " 7.0859784e-01 -1.1080378e-01]\n", - " ...\n", - " [ 1.1884158e+00 5.6527245e-01 5.6527245e-01 ... 5.6527245e-01\n", - " 5.6527245e-01 -6.5525830e-01]\n", - " [ 1.1884158e+00 5.6527245e-01 5.6527245e-01 ... 5.6527245e-01\n", - " 5.6527245e-01 -6.5525824e-01]\n", - " [ 1.6852863e+00 1.0636344e+00 1.0636344e+00 ... 1.0636345e+00\n", - " 1.0636345e+00 -9.2076123e-02]]]]\n", - "```" - ] - }, { "cell_type": "markdown", "metadata": {}, @@ -438,9 +437,29 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[[[[ 3.10382620e-02 4.38603461e-02 4.38603461e-02 ... 4.38603461e-02\n", + " 4.38603461e-02 1.38719045e-02]\n", + " [ 3.26051228e-02 3.54298912e-02 3.54298912e-02 ... 3.54298949e-02\n", + " 3.54298949e-02 -5.54019213e-03]\n", + " [ 3.26051228e-02 3.54298912e-02 3.54298912e-02 ... 3.54298912e-02\n", + " 3.54298912e-02 -5.54019120e-03]\n", + " ...\n", + " [ 4.38403059e-03 -3.60766202e-02 -3.60766202e-02 ... -3.60766277e-02\n", + " -3.60766277e-02 -2.95619294e-02]\n", + " [ 4.38403059e-03 -3.60766202e-02 -3.60766202e-02 ... -3.60766202e-02\n", + " -3.60766202e-02 -2.95619294e-02]\n", + " [ 1.33139016e-02 6.74417242e-05 6.74417242e-05 ... 6.74389303e-05\n", + " 6.74389303e-05 -2.27325857e-02]]]]\n" + ] + } + ], "source": [ "import numpy as np\n", "import mindspore.nn as nn\n", @@ -456,27 +475,6 @@ "print(output)" ] }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "```text\n", - "[[[[ 3.10382620e-02 4.38603461e-02 4.38603461e-02 ... 4.38603461e-02\n", - " 4.38603461e-02 1.38719045e-02]\n", - " [ 3.26051228e-02 3.54298912e-02 3.54298912e-02 ... 3.54298949e-02\n", - " 3.54298949e-02 -5.54019213e-03]\n", - " [ 3.26051228e-02 3.54298912e-02 3.54298912e-02 ... 3.54298912e-02\n", - " 3.54298912e-02 -5.54019120e-03]\n", - " ...\n", - " [ 4.38403059e-03 -3.60766202e-02 -3.60766202e-02 ... -3.60766277e-02\n", - " -3.60766277e-02 -2.95619294e-02]\n", - " [ 4.38403059e-03 -3.60766202e-02 -3.60766202e-02 ... -3.60766202e-02\n", - " -3.60766202e-02 -2.95619294e-02]\n", - " [ 1.33139016e-02 6.74417242e-05 6.74417242e-05 ... 6.74389303e-05\n", - " 6.74389303e-05 -2.27325857e-02]]]]\n", - "```" - ] - }, { "cell_type": "markdown", "metadata": {}, @@ -488,9 +486,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 13, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "[[[[12. 18. 18. ... 18. 18. 12.]\n", + " [18. 27. 27. ... 27. 27. 18.]\n", + " [18. 27. 27. ... 27. 27. 18.]\n", + " ...\n", + " [18. 27. 27. ... 27. 27. 18.]\n", + " [18. 27. 27. ... 27. 27. 18.]\n", + " [12. 18. 18. ... 18. 18. 12.]]]]\n" + ] + } + ], "source": [ "import numpy as np\n", "import mindspore.nn as nn\n", @@ -506,21 +518,6 @@ "print(output)" ] }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "```text\n", - "[[[[12. 18. 18. ... 18. 18. 12.]\n", - " [18. 27. 27. ... 27. 27. 18.]\n", - " [18. 27. 27. ... 27. 27. 18.]\n", - " ...\n", - " [18. 27. 27. ... 27. 27. 18.]\n", - " [18. 27. 27. ... 27. 27. 18.]\n", - " [12. 18. 18. ... 18. 18. 12.]]]]\n", - "```" - ] - }, { "cell_type": "markdown", "metadata": {}, @@ -534,7 +531,7 @@ }, { "cell_type": "code", - "execution_count": 129, + "execution_count": 14, "metadata": {}, "outputs": [ { diff --git a/tutorials/source_zh_cn/advance/train/metric.ipynb b/tutorials/source_zh_cn/advance/train/metric.ipynb index 175e4e2547a5e0a448feef291a6ea144ca64f828..361889c3068249d7879b8aca6276a509a32b565c 100644 --- a/tutorials/source_zh_cn/advance/train/metric.ipynb +++ b/tutorials/source_zh_cn/advance/train/metric.ipynb @@ -120,7 +120,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -170,7 +170,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ @@ -202,9 +202,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'MAE': 5.212465476989746}\n" + ] + } + ], "source": [ "ds_eval = create_dataset(num_data=100)\n", "\n", @@ -217,15 +225,6 @@ "output = model.eval(ds_eval)\n", "print(output)" ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "```Python\n", - "{'MAE': 5.212465476989746}\n", - "```" - ] } ], "metadata": { diff --git a/tutorials/source_zh_cn/advance/train/model.ipynb b/tutorials/source_zh_cn/advance/train/model.ipynb index 6c96a6cc6ff823df422975319b3c6023bdacce93..cf33ea1428092da7458f95812b94943e742a8a0e 100644 --- a/tutorials/source_zh_cn/advance/train/model.ipynb +++ b/tutorials/source_zh_cn/advance/train/model.ipynb @@ -109,7 +109,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "metadata": { "ExecuteTime": { "end_time": "2022-01-04T06:43:30.952190Z", @@ -117,7 +117,24 @@ }, "scrolled": true }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch:[ 0/ 1], step:[ 2/ 10], loss:[115.741/110.412], time:0.421 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 3/ 10], loss:[9.262/76.695], time:0.536 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 4/ 10], loss:[22.231/63.079], time:0.702 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 5/ 10], loss:[97.495/69.963], time:0.830 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 6/ 10], loss:[165.809/85.937], time:0.609 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 7/ 10], loss:[58.898/82.074], time:0.430 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 8/ 10], loss:[9.044/72.946], time:5.970 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 9/ 10], loss:[11.369/66.104], time:0.981 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 10/ 10], loss:[104.045/69.898], time:0.494 ms, lr:0.00500.\n", + "Epoch time: 181.851 ms, per step time: 18.185 ms, avg loss: 69.898\n" + ] + } + ], "source": [ "from mindvision.engine.callback import LossMonitor\n", "\n", @@ -125,24 +142,6 @@ "model.train(1, train_dataset, callbacks=[LossMonitor(0.005)], dataset_sink_mode=False)" ] }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "```Text\n", - "Epoch:[ 0/ 1], step:[ 2/ 10], loss:[115.741/110.412], time:0.421 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 3/ 10], loss:[9.262/76.695], time:0.536 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 4/ 10], loss:[22.231/63.079], time:0.702 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 5/ 10], loss:[97.495/69.963], time:0.830 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 6/ 10], loss:[165.809/85.937], time:0.609 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 7/ 10], loss:[58.898/82.074], time:0.430 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 8/ 10], loss:[9.044/72.946], time:5.970 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 9/ 10], loss:[11.369/66.104], time:0.981 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 10/ 10], loss:[104.045/69.898], time:0.494 ms, lr:0.00500.\n", - "Epoch time: 181.851 ms, per step time: 18.185 ms, avg loss: 69.898\n", - "```" - ] - }, { "cell_type": "markdown", "metadata": {}, @@ -158,29 +157,28 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": { "ExecuteTime": { "end_time": "2022-01-04T06:43:31.009605Z", "start_time": "2022-01-04T06:43:30.954322Z" } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'mae': 9.021200180053711}\n" + ] + } + ], "source": [ "eval_dataset = create_dataset(num_data=80) # 创建评估数据集\n", "eval_result = model.eval(eval_dataset) # 执行模型评估\n", "print(eval_result)" ] }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "```Text\n", - "{'mae': 9.021200180053711}\n", - "```" - ] - }, { "cell_type": "markdown", "metadata": {}, @@ -257,14 +255,32 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": { "ExecuteTime": { "end_time": "2022-01-04T06:43:31.051039Z", "start_time": "2022-01-04T06:43:31.043718Z" } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch:[ 0/ 1], step:[ 1/ 10], loss:[8.382/8.382], time:119.369 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 2/ 10], loss:[8.710/8.546], time:0.521 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 3/ 10], loss:[6.140/7.744], time:6.315 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 4/ 10], loss:[9.578/8.202], time:1.420 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 5/ 10], loss:[10.786/8.719], time:0.958 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 6/ 10], loss:[9.874/8.912], time:1.501 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 7/ 10], loss:[4.433/8.272], time:9.982 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 8/ 10], loss:[6.723/8.078], time:2.540 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 9/ 10], loss:[8.435/8.118], time:1.258 ms, lr:0.00500.\n", + "Epoch:[ 0/ 1], step:[ 10/ 10], loss:[7.085/8.015], time:1.419 ms, lr:0.00500.\n", + "Epoch time: 153.744 ms, per step time: 15.374 ms, avg loss: 8.015\n" + ] + } + ], "source": [ "import numpy as np\n", "import mindspore.dataset as ds\n", @@ -333,25 +349,6 @@ "model.train(epoch=1, train_dataset=multi_train_dataset, callbacks=[LossMonitor(0.005)])" ] }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "```Text\n", - "Epoch:[ 0/ 1], step:[ 1/ 10], loss:[8.382/8.382], time:119.369 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 2/ 10], loss:[8.710/8.546], time:0.521 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 3/ 10], loss:[6.140/7.744], time:6.315 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 4/ 10], loss:[9.578/8.202], time:1.420 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 5/ 10], loss:[10.786/8.719], time:0.958 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 6/ 10], loss:[9.874/8.912], time:1.501 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 7/ 10], loss:[4.433/8.272], time:9.982 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 8/ 10], loss:[6.723/8.078], time:2.540 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 9/ 10], loss:[8.435/8.118], time:1.258 ms, lr:0.00500.\n", - "Epoch:[ 0/ 1], step:[ 10/ 10], loss:[7.085/8.015], time:1.419 ms, lr:0.00500.\n", - "Epoch time: 153.744 ms, per step time: 15.374 ms, avg loss: 8.015\n", - "```" - ] - }, { "cell_type": "markdown", "metadata": {}, @@ -365,9 +362,27 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Epoch:[ 0/ 1], step:[ 1/ 10], loss:[6.055/6.055], time:111.966, lr:0.01000.\n", + "Epoch:[ 0/ 1], step:[ 2/ 10], loss:[3.870/4.963], time:2.944, lr:0.01000.\n", + "Epoch:[ 0/ 1], step:[ 3/ 10], loss:[2.912/4.279], time:2.560, lr:0.01000.\n", + "Epoch:[ 0/ 1], step:[ 4/ 10], loss:[2.473/3.828], time:1.305, lr:0.01000.\n", + "Epoch:[ 0/ 1], step:[ 5/ 10], loss:[3.031/3.668], time:1.549, lr:0.01000.\n", + "Epoch:[ 0/ 1], step:[ 6/ 10], loss:[4.278/3.770], time:0.837, lr:0.01000.\n", + "Epoch:[ 0/ 1], step:[ 7/ 10], loss:[4.222/3.834], time:0.680, lr:0.01000.\n", + "Epoch:[ 0/ 1], step:[ 8/ 10], loss:[3.250/3.761], time:0.720, lr:0.01000.\n", + "Epoch:[ 0/ 1], step:[ 9/ 10], loss:[3.961/3.784], time:0.719, lr:0.01000.\n", + "Epoch:[ 0/ 1], step:[ 10/ 10], loss:[3.874/3.793], time:6.948, lr:0.01000.\n", + "Epoch time: 138.377, per step time: 13.838, avg loss: 3.793\n" + ] + } + ], "source": [ "import mindspore.ops as ops\n", "from mindspore import Model\n", @@ -401,25 +416,6 @@ "model.train(epoch=1, train_dataset=multi_train_ds, callbacks=[LossMonitor(0.01)])" ] }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "```Text\n", - "Epoch:[ 0/ 1], step:[ 1/ 10], loss:[6.055/6.055], time:111.966, lr:0.01000.\n", - "Epoch:[ 0/ 1], step:[ 2/ 10], loss:[3.870/4.963], time:2.944, lr:0.01000.\n", - "Epoch:[ 0/ 1], step:[ 3/ 10], loss:[2.912/4.279], time:2.560, lr:0.01000.\n", - "Epoch:[ 0/ 1], step:[ 4/ 10], loss:[2.473/3.828], time:1.305, lr:0.01000.\n", - "Epoch:[ 0/ 1], step:[ 5/ 10], loss:[3.031/3.668], time:1.549, lr:0.01000.\n", - "Epoch:[ 0/ 1], step:[ 6/ 10], loss:[4.278/3.770], time:0.837, lr:0.01000.\n", - "Epoch:[ 0/ 1], step:[ 7/ 10], loss:[4.222/3.834], time:0.680, lr:0.01000.\n", - "Epoch:[ 0/ 1], step:[ 8/ 10], loss:[3.250/3.761], time:0.720, lr:0.01000.\n", - "Epoch:[ 0/ 1], step:[ 9/ 10], loss:[3.961/3.784], time:0.719, lr:0.01000.\n", - "Epoch:[ 0/ 1], step:[ 10/ 10], loss:[3.874/3.793], time:6.948, lr:0.01000.\n", - "Epoch time: 138.377, per step time: 13.838, avg loss: 3.793\n", - "```" - ] - }, { "cell_type": "markdown", "metadata": {}, @@ -433,14 +429,22 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": { "ExecuteTime": { "end_time": "2022-01-04T06:43:31.373188Z", "start_time": "2022-01-04T06:43:31.369046Z" } }, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "{'mae1': 5.182377433776855, 'mae2': 4.988385105133057}\n" + ] + } + ], "source": [ "import mindspore.nn as nn\n", "from mindspore.train.callback import LossMonitor\n", @@ -476,13 +480,6 @@ "print(result)" ] }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "{'mae1': 5.182377433776855, 'mae2': 4.988385105133057" - ] - }, { "cell_type": "markdown", "metadata": {}, diff --git a/tutorials/source_zh_cn/advance/train/save.ipynb b/tutorials/source_zh_cn/advance/train/save.ipynb index 6b93704274ddf7b3abf0bd7c78760a2364ab2ca0..edcfd011d6e876a642fa90dd925d00cfbd7f9524 100644 --- a/tutorials/source_zh_cn/advance/train/save.ipynb +++ b/tutorials/source_zh_cn/advance/train/save.ipynb @@ -146,9 +146,18 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Delete parameter from checkpoint: head.dense.weight\n", + "Delete parameter from checkpoint: head.dense.bias\n" + ] + } + ], "source": [ "from mindvision.classification.models import resnet50\n", "from mindspore import load_checkpoint, load_param_into_net\n", @@ -185,11 +194,6 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "```Text\n", - "Delete parameter from checkpoint: head.dense.weight\n", - "Delete parameter from checkpoint: head.dense.bias\n", - "```\n", - "\n", "## 模型导出\n", "\n", "MindSpore的`export`可以将网络模型导出为指定格式的文件，用于其他硬件平台的推理。`export`主要参数如下所示：\n", @@ -208,7 +212,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ @@ -234,7 +238,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, "outputs": [], "source": [ @@ -320,7 +324,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [