I dont know what need to be mergedMerge branch 'master' of github.com…

…:Frank-Xu-Huaze/Medium
franknb · Jun 7, 2020 · 18cd81b · 18cd81b
2 parents 8d18020 + 71227af
commit 18cd81b
Show file tree

Hide file tree

Showing 6 changed files with 466 additions and 0 deletions.
diff --git a/PlaidML_CNN/PlaidML_Fashion_mnist-NON-experimental-Plaid_ML-config.ipynb b/PlaidML_CNN/PlaidML_Fashion_mnist-NON-experimental-Plaid_ML-config.ipynb
@@ -0,0 +1,152 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Importing PlaidML. Make sure you follow this order\n",
+    "import plaidml.keras\n",
+    "plaidml.keras.install_backend()\n",
+    "import os\n",
+    "os.environ[\"KERAS_BACKEND\"] = \"plaidml.keras.backend\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import keras\n",
+    "from keras.models import Sequential\n",
+    "from keras.layers import Dense, Dropout, Flatten\n",
+    "from keras.layers import Conv2D, MaxPooling2D\n",
+    "from keras import backend as K\n",
+    "\n",
+    "# Download fashion dataset from Keras\n",
+    "fashion_mnist = keras.datasets.fashion_mnist\n",
+    "(x_train, y_train), (x_test, y_test) = keras.datasets.fashion_mnist.load_data()\n",
+    "\n",
+    "# Reshape and normalize the data\n",
+    "x_train = x_train.astype('float32').reshape(60000,28,28,1) / 255\n",
+    "x_test = x_test.astype('float32').reshape(10000,28,28,1) / 255"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "INFO:plaidml:Opening device \"metal_amd_radeon_pro_vega_ii_duo.1\"\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Build a CNN model. You should see \"INFO:plaidml:Opening device xxx\" after you run this chunk\n",
+    "model = keras.Sequential()\n",
+    "model.add(keras.layers.Conv2D(filters=64, kernel_size=2, padding='same', activation='relu', input_shape=(28,28,1))) \n",
+    "model.add(keras.layers.MaxPooling2D(pool_size=2))\n",
+    "model.add(keras.layers.Dropout(0.3))\n",
+    "model.add(keras.layers.Conv2D(filters=32, kernel_size=2, padding='same', activation='relu'))\n",
+    "model.add(keras.layers.MaxPooling2D(pool_size=2))\n",
+    "model.add(keras.layers.Dropout(0.3))\n",
+    "model.add(keras.layers.Flatten())\n",
+    "model.add(keras.layers.Dense(256, activation='relu'))\n",
+    "model.add(keras.layers.Dropout(0.5))\n",
+    "model.add(keras.layers.Dense(10, activation='softmax'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Compile the model\n",
+    "model.compile(optimizer='adam',\n",
+    "              loss=keras.losses.sparse_categorical_crossentropy,\n",
+    "              metrics=['accuracy'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "60000/60000 [==============================] - 8s 129us/step - loss: 0.5875 - acc: 0.7845\n",
+      "Epoch 2/10\n",
+      "60000/60000 [==============================] - 7s 116us/step - loss: 0.4101 - acc: 0.8508\n",
+      "Epoch 3/10\n",
+      "60000/60000 [==============================] - 7s 117us/step - loss: 0.3624 - acc: 0.8694\n",
+      "Epoch 4/10\n",
+      "60000/60000 [==============================] - 7s 116us/step - loss: 0.3353 - acc: 0.8763\n",
+      "Epoch 5/10\n",
+      "60000/60000 [==============================] - 7s 116us/step - loss: 0.3160 - acc: 0.8847\n",
+      "Epoch 6/10\n",
+      "60000/60000 [==============================] - 7s 116us/step - loss: 0.3002 - acc: 0.8887\n",
+      "Epoch 7/10\n",
+      "60000/60000 [==============================] - 7s 117us/step - loss: 0.2891 - acc: 0.8938\n",
+      "Epoch 8/10\n",
+      "60000/60000 [==============================] - 7s 116us/step - loss: 0.2801 - acc: 0.8972\n",
+      "Epoch 9/10\n",
+      "60000/60000 [==============================] - 7s 116us/step - loss: 0.2720 - acc: 0.8999\n",
+      "Epoch 10/10\n",
+      "60000/60000 [==============================] - 7s 116us/step - loss: 0.2639 - acc: 0.9022\n",
+      "\n",
+      " Test accuracy: 0.9108\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Fit the model on training set\n",
+    "model.fit(x_train, y_train,\n",
+    "          batch_size=64,\n",
+    "          epochs=10)\n",
+    "\n",
+    "# Evaluate the model on test set\n",
+    "score = model.evaluate(x_test, y_test, verbose=0)\n",
+    "# Print test accuracy\n",
+    "print('\\n', 'Test accuracy:', score[1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "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": "3.7.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/PlaidML_CNN/PlaidML_Fashion_mnist-experimental-Plaid_ML-config.ipynb b/PlaidML_CNN/PlaidML_Fashion_mnist-experimental-Plaid_ML-config.ipynb
@@ -0,0 +1,146 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Importing PlaidML. Make sure you follow this order\n",
+    "import plaidml.keras\n",
+    "plaidml.keras.install_backend()\n",
+    "import os\n",
+    "os.environ[\"KERAS_BACKEND\"] = \"plaidml.keras.backend\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import keras\n",
+    "from keras.models import Sequential\n",
+    "from keras.layers import Dense, Dropout, Flatten\n",
+    "from keras.layers import Conv2D, MaxPooling2D\n",
+    "from keras import backend as K\n",
+    "\n",
+    "# Download fashion dataset from Keras\n",
+    "fashion_mnist = keras.datasets.fashion_mnist\n",
+    "(x_train, y_train), (x_test, y_test) = keras.datasets.fashion_mnist.load_data()\n",
+    "\n",
+    "# Reshape and normalize the data\n",
+    "x_train = x_train.astype('float32').reshape(60000,28,28,1) / 255\n",
+    "x_test = x_test.astype('float32').reshape(10000,28,28,1) / 255"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "INFO:plaidml:Opening device \"opencl_amd_radeon_pro_vega_ii_duo_compute_engine.1\"\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Build a CNN model. You should see \"INFO:plaidml:Opening device xxx\" after you run this chunk\n",
+    "model = keras.Sequential()\n",
+    "model.add(keras.layers.Conv2D(filters=64, kernel_size=2, padding='same', activation='relu', input_shape=(28,28,1))) \n",
+    "model.add(keras.layers.MaxPooling2D(pool_size=2))\n",
+    "model.add(keras.layers.Dropout(0.3))\n",
+    "model.add(keras.layers.Conv2D(filters=32, kernel_size=2, padding='same', activation='relu'))\n",
+    "model.add(keras.layers.MaxPooling2D(pool_size=2))\n",
+    "model.add(keras.layers.Dropout(0.3))\n",
+    "model.add(keras.layers.Flatten())\n",
+    "model.add(keras.layers.Dense(256, activation='relu'))\n",
+    "model.add(keras.layers.Dropout(0.5))\n",
+    "model.add(keras.layers.Dense(10, activation='softmax'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Compile the model\n",
+    "model.compile(optimizer='adam',\n",
+    "              loss=keras.losses.sparse_categorical_crossentropy,\n",
+    "              metrics=['accuracy'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "60000/60000 [==============================] - 18s 294us/step - loss: nan - acc: 0.0999\n",
+      "Epoch 2/10\n",
+      "60000/60000 [==============================] - 10s 167us/step - loss: nan - acc: 0.1000\n",
+      "Epoch 3/10\n",
+      "60000/60000 [==============================] - 10s 167us/step - loss: nan - acc: 0.1000\n",
+      "Epoch 4/10\n",
+      "60000/60000 [==============================] - 10s 167us/step - loss: nan - acc: 0.1000\n",
+      "Epoch 5/10\n",
+      "60000/60000 [==============================] - 10s 168us/step - loss: nan - acc: 0.1000\n",
+      "Epoch 6/10\n",
+      "60000/60000 [==============================] - 10s 168us/step - loss: nan - acc: 0.1000\n",
+      "Epoch 7/10\n",
+      "60000/60000 [==============================] - 10s 168us/step - loss: nan - acc: 0.1000\n",
+      "Epoch 8/10\n",
+      "34624/60000 [================>.............] - ETA: 4s - loss: nan - acc: 0.0997"
+     ]
+    }
+   ],
+   "source": [
+    "# Fit the model on training set\n",
+    "model.fit(x_train, y_train,\n",
+    "          batch_size=64,\n",
+    "          epochs=10)\n",
+    "\n",
+    "# Evaluate the model on test set\n",
+    "score = model.evaluate(x_test, y_test, verbose=0)\n",
+    "# Print test accuracy\n",
+    "print('\\n', 'Test accuracy:', score[1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "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": "3.7.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/PlaidML_CNN/README.md b/PlaidML_CNN/README.md
@@ -0,0 +1,9 @@
+# README.md for PlaidML_Fashion_mnist.ipydb
+1. Create a python virtual environment using `venv` or `virtualenv`. For example, `virtualenv --python=python3 venv_name`
+2. From within the PlaidML_CNN directory, run `pip install -r requirements.txt`
+3. Setup PlaidML: You have two choices, experimental hardward and non-experimental hardware/software support. Notes for each I below, and I saved the results in the notebooks because, on my new Mac Pro, the experimental configuration was 0.1, compared to 0.9x for the non-experimental hardware configuration. 
+  - [Experimental Configuration Notes](./plaidML_experimental.md)
+  - [Non-Experimental Configuration Notes](./plaidML_non-experimental.md)
+4. Run `jupyter lab`
+5. Have fun!
+
diff --git a/PlaidML_CNN/plaidML_experimental.md b/PlaidML_CNN/plaidML_experimental.md
@@ -0,0 +1,76 @@
+# Notes on Experimental PlaidML Hardware Config
+
+Run this command to setup PlaidML: 
+
+```
+plaidml-setup
+```
+You should see this output:
+```
+PlaidML Setup (0.7.0)
+
+Thanks for using PlaidML!
+
+The feedback we have received from our users indicates an ever-increasing need
+for performance, programmability, and portability. During the past few months,
+we have been restructuring PlaidML to address those needs.  To make all the
+changes we need to make while supporting our current user base, all development
+of PlaidML has moved to a branch — plaidml-v1. We will continue to maintain and
+support the master branch of PlaidML and the stable 0.7.0 release.
+
+Read more here: https://github.com/plaidml/plaidml
+
+Some Notes:
+  * Bugs and other issues: https://github.com/plaidml/plaidml/issues
+  * Questions: https://stackoverflow.com/questions/tagged/plaidml
+  * Say hello: https://groups.google.com/forum/#!forum/plaidml-dev
+  * PlaidML is licensed under the Apache License 2.0
+
+
+Default Config Devices:
+   llvm_cpu.0 : CPU (via LLVM)
+   metal_amd_radeon_pro_vega_ii_duo.1 : AMD Radeon Pro Vega II Duo (Metal)
+   metal_amd_radeon_pro_vega_ii_duo.0 : AMD Radeon Pro Vega II Duo (Metal)
+
+Experimental Config Devices:
+   llvm_cpu.0 : CPU (via LLVM)
+   opencl_amd_radeon_pro_vega_ii_duo_compute_engine.1 : AMD AMD Radeon Pro Vega II Duo Compute Engine (OpenCL)
+   opencl_amd_radeon_pro_vega_ii_duo_compute_engine.0 : AMD AMD Radeon Pro Vega II Duo Compute Engine (OpenCL)
+   metal_amd_radeon_pro_vega_ii_duo.1 : AMD Radeon Pro Vega II Duo (Metal)
+   metal_amd_radeon_pro_vega_ii_duo.0 : AMD Radeon Pro Vega II Duo (Metal)
+
+Using experimental devices can cause poor performance, crashes, and other nastiness.
+
+```
+I was offered this choice, and went **bold** with a `y`
+```
+Enable experimental device support? (y,n)[n]:y
+
+
+
+Multiple devices detected (You can override by setting PLAIDML_DEVICE_IDS).
+Please choose a default device:
+
+   1 : llvm_cpu.0
+   2 : opencl_amd_radeon_pro_vega_ii_duo_compute_engine.1
+   3 : opencl_amd_radeon_pro_vega_ii_duo_compute_engine.0
+   4 : metal_amd_radeon_pro_vega_ii_duo.1
+   5 : metal_amd_radeon_pro_vega_ii_duo.0
+```
+
+You can see I chose one of the experimental devices on my new Mac Pro `CheeseGrater`
+
+```
+Default device? (1,2,3,4,5)[1]:2
+
+Selected device:
+    opencl_amd_radeon_pro_vega_ii_duo_compute_engine.1
+
+Almost done. Multiplying some matrices...
+Tile code:
+  function (B[X,Z], C[Z,Y]) -> (A) { A[x,y : X,Y] = +(B[x,z] * C[z,y]); }
+Whew. That worked.
+
+Save settings to /Users/gogginsS/.plaidml? (y,n)[y]:y
+Success!
+```