I'm running code to train a PPO policy on chess using PettingZoo:
import gym.vector.utils
import supersuit as ss
import stable_baselines3.ppo
import pettingzoo.classic
if __name__ == '__main__':
env = original_env = pettingzoo.classic.chess_v5.env()
env = pettingzoo.utils.turn_based_aec_to_parallel(env)
env = ss.pettingzoo_env_to_vec_env_v1(env)
env = ss.concat_vec_envs_v1(env, 8, num_cpus=4, base_class='stable_baselines3')
model = stable_baselines3.PPO(stable_baselines3.ppo.MultiInputPolicy, env,
tensorboard_log='my_logs')
model.learn(total_timesteps=100)
In the next to last line, you can see I'm outputting logs to TensorBoard, where I hope to see a nice graph. However, all I see is this:
I've used TensorBoard before and it worked. Why isn't it showing any progress now? Or even lack of progress?
Turns out I just needed to use a lower value for n_steps.
Related
I'm trying to use Tensorflow to Machine Learning to analyze an image and return the probability if is positive or negative based on a model created (extension .h5). I couldn't found a documentation exactly for that, or repository, so even a link to read will be awesome.
Link for the application: https://share.streamlit.io/felipelx/hackathon/IDC_Detector.py
Libraries that I'm trying to use.
import numpy as np
import streamlit as st
import tensorflow as tf
from keras.models import load_model
The function to load the model.
#st.cache(allow_output_mutation=True)
def loadIDCModel():
model_idc = load_model('models/IDC_model.h5', compile=False)
model_idc.summary()
return model_idc
The function to work the image, and what I'm trying to see: model.predict - I can see but is not updating the %, independent of the image the value is always the same.
if uploaded_file is not None:
# transform image to numpy array
file_bytes = tf.keras.preprocessing.image.load_img(uploaded_file, target_size=(96,96), grayscale = False, interpolation = 'nearest', color_mode = 'rgb', keep_aspect_ratio = False)
c.image(file_bytes, channels="RGB")
Genrate_pred = st.button("Generate Prediction")
if Genrate_pred:
model = loadMetModel()
input_arr = tf.keras.preprocessing.image.img_to_array(file_bytes)
input_arr = np.array([input_arr])
probability_model = tf.keras.Sequential([model, tf.keras.layers.Softmax()])
prediction = probability_model.predict(input_arr)
dict_pred = {0: 'Benigno/Normal', 1: 'Maligno'}
result = dict_pred[np.argmax(prediction)]
value = 0
if result == 'Benigno/Normal':
value = str(((prediction[0][0])*100).round(2)) + '%'
else:
value = str(((prediction[0][1])*100).round(2)) + '%'
c.metric('Predição', result, delta=value, delta_color='normal')
Thank you in advance to any help.
The first thing I'm noticing is that your function for loading the model is named loadIDCModel, but then the function you call for loading the model is loadMetModel. When I check your source code, though, it looks like you've already addressed this issue. I'd recommend updating your question to reflect this.
Playing around with your application, I think the issue is your model itself. I tried various images — images containing carcinomas, and even a picture of a cat — and each gave me a probability around 73%. The lowest score I got was 72.74%, and the highest was 73.11% (this one was the cat). It seems that the output percentage is varying slightly, hinting that rather than something being wrong in the code, your model itself is likely at fault. You might need to retrain your model, as it seems to have learned to always return a value of approximately 0.73.
I follow the official tutotial from microsoft: https://learn.microsoft.com/en-us/azure/synapse-analytics/machine-learning/tutorial-score-model-predict-spark-pool
When I execute:
#Bind model within Spark session
model = pcontext.bind_model(
return_types=RETURN_TYPES,
runtime=RUNTIME,
model_alias="Sales", #This alias will be used in PREDICT call to refer this model
model_uri=AML_MODEL_URI, #In case of AML, it will be AML_MODEL_URI
aml_workspace=ws #This is only for AML. In case of ADLS, this parameter can be removed
).register()
I got : No module named 'azureml.automl'
My Notebook
As per the repro from my end, the above code which you have shared works as excepted and I don't see any error message which you are experiencing.
I had even tested the same code on the newly created Apache spark 3.1 runtime and it works as expected.
I would request you to create a new cluster and see if you are able to run the above code.
I solved it. In my case it works best like this:
Imports
#Import libraries
from pyspark.sql.functions import col, pandas_udf,udf,lit
from notebookutils.mssparkutils import azureML
from azureml.core import Workspace, Model
from azureml.core.authentication import ServicePrincipalAuthentication
from azureml.core.model import Model
import joblib
import pandas as pd
ws = azureML.getWorkspace("AzureMLService")
spark.conf.set("spark.synapse.ml.predict.enabled","true")
Predict function
def forecastModel():
model_path = Model.get_model_path(model_name="modelName", _workspace=ws)
modeljob = joblib.load(model_path + "/model.pkl")
validation_data = spark.read.format("csv") \
.option("header", True) \
.option("inferSchema",True) \
.option("sep", ";") \
.load("abfss://....csv")
validation_data_pd = validation_data.toPandas()
predict = modeljob.forecast(validation_data_pd)
return predict
I'm trying to put together a demo of Neptune using Neptune workbench, but something's not working right. I've got this block set up:
from __future__ import print_function # Python 2/3 compatibility
from gremlin_python import statics
from gremlin_python.structure.graph import Graph
from gremlin_python.process.graph_traversal import __
from gremlin_python.process.strategies import *
from gremlin_python.driver.driver_remote_connection import DriverRemoteConnection
graph = Graph()
cluster_url = #my cluster
remoteConn = DriverRemoteConnection( f'wss://{cluster_url}:8182/gremlin','g')
g = graph.traversal().withRemote(remoteConn)
import uuid
tmp = uuid.uuid4()
tmp_id=str(id)
def get_id(name):
uid = uuid.uuid5(uuid.NAMESPACE_DNS, f"{name}.licensing.company.com")
return str(uid)
def add_sku(name):
tmp_id = get_id(name)
g.addV('SKU').property('id', tmp_id, 'name', name)
return name
def get_values():
return g.V().properties().toList()
The problem is that calling add_sku doesn't result in a vertex being added to the graph. Doing the same operation in a cell with gremlin magic works, and I can retrieve values through python, but I can't add vertices. Does anyone see what I'm missing here?
The Python code is not working because it is missing a terminal step (next() or iterate()) on the end of it which forces it to evaluate. If you add the terminal step it should work:
g.addV('SKU').property('id', tmp_id, 'name', name).next()
As you can guess by the title, the kernel always dies when using pd.read_parquet().
I already tried it with different sizes but it wont work.
here the code... (I am using jupyter (without anaconda, because it always takes to long to start) in Python 3.7 with a i5 & 16GB RAM)
outfp = PurePath(data_dir+'/interim/IVE_tickbidask.parq')
#df = df.head(10)
df.to_parquet(outfp)
from pathlib import PurePath, Path
import pandas as pd
data_dir = "../../../Adv_Fin_ML_Exercises-master/Adv_Fin_ML_Exercises-master/data"
infp=PurePath(data_dir+'/interim/IVE_tickbidask.parq')
df = pd.read_parquet(data_dir+'/interim/IVE_tickbidask.parq')
cprint(df)
What can i do to still make it work?
I had the same problem, adding engine = 'fastparquet' worked for me. Otherwise it defaults to engine = 'pyarrow' and that seems to make the kernel die.
I'm trying to run a test python code to use the traci library and it is returning "please declare environment SUMO_HOME".
I'm on Ubuntu 18.4.2 and Sumo 0.32.0.I solved this problem before by running
export SUMO_HOME=/home/gustavo/Downloads/sumo-0.32.0/tools/
,but this time it couldn't solve the problem. So I tried implementing a line inside the python file using the os library giving the same command but from the code itself:
os.system("export SUMO_HOME=/home/gustavo/Downloads/sumo-0.32.0/tool/")
And it also didn't work, so came here to ask for help. May any of you help me, please?
import os
import sys
import optparse
os.system("export SUMO_HOME=/home/gustavo/Downloads/sumo-0.32.0/tool/")
# we need to import some python modules from the $SUMO_HOME/tools directory
if 'SUMO_HOME' in os.environ:
tools = os.path.join(os.environ['SUMO_HOME=/home/gustavo/Downloads/sumo-0.32.0/tools/'], 'tools')
sys.path.append(tools)
else:
sys.exit("please declare environment variable 'SUMO_HOME'")
from sumolib import checkBinary # Checks for the binary in environ vars
import traci
def get_options():
opt_parser = optparse.OptionParser()
opt_parser.add_option("--nogui", action="store_true",
default=False, help="run the commandline version of sumo")
options, args = opt_parser.parse_args()
return options
# contains TraCI control loop
def run():
step = 0
while traci.simulation.getMinExpectedNumber() > 0:
traci.simulationStep()
print(step)
step += 1
traci.close()
sys.stdout.flush()
# main entry point
if __name__ == "__main__":
options = get_options()
# check binary
if options.nogui:
sumoBinary = checkBinary('sumo')
else:
sumoBinary = checkBinary('sumo-gui')
# traci starts sumo as a subprocess and then this script connects and runs
traci.start([sumoBinary, "-c", "demo.sumocfg",
"--tripinfo-output", "tripinfo.xml"])
run()
I expected for the steps to appear on the terminal.
The correct location is probably
export SUMO_HOME=/home/gustavo/Downloads/sumo-0.32.0
without the tools or tool suffix. It will not work from inside the python script with os.system but you could modify os.environ directly.
Furthermore you mixed up the call to os.environ in the script. It should read:
tools = os.path.join(os.environ['SUMO_HOME'], 'tools')
I swapped the if else part for another code :
try:
sys.path.append("/home/gustavo/Downloads/sumo-0.32.0/tools")
from sumolib import checkBinary
except ImportError:
sys.exit("please declare environment variable 'SUMO_HOME' as the root directory of your sumo installation (it should contain folders 'bin', 'tools' and 'docs')")
It solved the problem