From 0bc45f9bd907283b0ee5d081387ac1e4342fa5e0 Mon Sep 17 00:00:00 2001
From: Rishi Sharma <rishi.sharma@epfl.ch>
Date: Tue, 23 Nov 2021 14:58:06 +0100
Subject: [PATCH] Reset optimizer state after iterations - fix
---
main.ipynb | 58 ++++++++++++++++++-------
src/decentralizepy/node/Node.py | 1 +
src/decentralizepy/training/Training.py | 4 ++
3 files changed, 47 insertions(+), 16 deletions(-)
diff --git a/main.ipynb b/main.ipynb
index b785501..f3907f0 100644
--- a/main.ipynb
+++ b/main.ipynb
@@ -346,7 +346,7 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 2,
"metadata": {},
"outputs": [
{
@@ -385,19 +385,6 @@
"('sharing_class', 'Sharing')\n",
"{'dataset_package': 'decentralizepy.datasets.Femnist', 'dataset_class': 'Femnist', 'model_class': 'CNN', 'n_procs': 36, 'train_dir': 'leaf/data/femnist/per_user_data/train', 'test_dir': 'leaf/data/femnist/data/test', 'sizes': ''}\n"
]
- },
- {
- "ename": "IndexError",
- "evalue": "list index out of range",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mIndexError\u001b[0m Traceback (most recent call last)",
- "\u001b[0;32m/tmp/ipykernel_2255475/3991202644.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 27\u001b[0m \u001b[0;31m#f = Femnist(2, 'leaf/data/femnist/data/train', sizes=[0.6, 0.4])\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 28\u001b[0m \u001b[0mg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mGraph\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[0;32m---> 29\u001b[0;31m \u001b[0mg\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_graph_from_file\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"36_nodes.edges\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"edges\"\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 30\u001b[0m \u001b[0ml\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mLinear\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m36\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 31\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
- "\u001b[0;32m~/Gitlab/decentralizepy/src/decentralizepy/graphs/Graph.py\u001b[0m in \u001b[0;36mread_graph_from_file\u001b[0;34m(self, file, type, force_connect)\u001b[0m\n\u001b[1;32m 70\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mline\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mlines\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 71\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmap\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mint\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mline\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstrip\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[0;34m(\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[0;32m---> 72\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__insert_edge__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\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 73\u001b[0m \u001b[0;32melif\u001b[0m \u001b[0mtype\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m\"adjacency\"\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 74\u001b[0m \u001b[0mnode_id\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
- "\u001b[0;32m~/Gitlab/decentralizepy/src/decentralizepy/graphs/Graph.py\u001b[0m in \u001b[0;36m__insert_edge__\u001b[0;34m(self, x, y)\u001b[0m\n\u001b[1;32m 39\u001b[0m \u001b[0mThe\u001b[0m \u001b[0mdestination\u001b[0m \u001b[0mvertex\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 40\u001b[0m \"\"\"\n\u001b[0;32m---> 41\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madj_list\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my\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 42\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madj_list\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 43\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
- "\u001b[0;31mIndexError\u001b[0m: list index out of range"
- ]
}
],
"source": [
@@ -522,14 +509,53 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from decentralizepy.graphs.SmallWorld import SmallWorld\n",
"\n",
- "s = SmallWorld(36, 2, .5)"
+ "s = SmallWorld(36, 2, .5)\n",
+ "s.write_graph_to_file('36_nodes.edges')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "['/home/risharma/miniconda3/envs/decpy/lib/python3.9/site-packages/ipykernel_launcher.py',\n",
+ " '--ip=127.0.0.1',\n",
+ " '--stdin=9008',\n",
+ " '--control=9006',\n",
+ " '--hb=9005',\n",
+ " '--Session.signature_scheme=\"hmac-sha256\"',\n",
+ " '--Session.key=b\"eac5d2f8-c460-45f1-a268-1e4b46a6efd6\"',\n",
+ " '--shell=9007',\n",
+ " '--transport=\"tcp\"',\n",
+ " '--iopub=9009',\n",
+ " '--f=/tmp/tmp-21212479paJaUBJBN84.json']"
+ ]
+ },
+ "execution_count": 1,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "import sys\n",
+ "sys.argv"
]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
}
],
"metadata": {
diff --git a/src/decentralizepy/node/Node.py b/src/decentralizepy/node/Node.py
index 77c29d9..9643496 100644
--- a/src/decentralizepy/node/Node.py
+++ b/src/decentralizepy/node/Node.py
@@ -160,6 +160,7 @@ class Node:
self.sharing.step()
self.optimizer = optimizer_class(self.model.parameters(), **optimizer_params) # Reset optimizer state
+ self.trainer.reset_optimizer(self.optimizer)
rounds_to_test -= 1
diff --git a/src/decentralizepy/training/Training.py b/src/decentralizepy/training/Training.py
index 54de9d5..31daa65 100644
--- a/src/decentralizepy/training/Training.py
+++ b/src/decentralizepy/training/Training.py
@@ -43,6 +43,10 @@ class Training:
plt.imshow(np.transpose(npimg, (1, 2, 0)))
plt.show()
+ def reset_optimizer(self, optimizer):
+ self.optimizer = optimizer
+
+
def train(self, dataset):
"""
One training iteration
--
GitLab