def plotGaussian():
# Plotting the gaussian plots
import pandas as pd
from Simulated_DataSets.Gaussian_Mixture.generate_Gaussian import plotData
import numpy as np
import os
data_dir = '/work/sr365/multi_eval'
for dirs in os.listdir(data_dir):
print("entering :", dirs)
print("this is a folder?:", os.path.isdir(os.path.join(data_dir, dirs)))
print("this is a file?:", os.path.isfile(os.path.join(data_dir, dirs)))
if not os.path.isdir(os.path.join(data_dir, dirs)):
continue
for subdirs in os.listdir(os.path.join(data_dir, dirs)):
if 'gaussian' in subdirs:
for subfiles in os.listdir(os.path.join(data_dir, dirs, subdirs)):
if 'inference0' not in subfiles:
continue;
if 'Ypred' in subfiles:
filename = os.path.join(data_dir, dirs, subdirs, subfiles)
data_y = pd.read_csv(filename, header=None, sep=' ').values.astype('float')
if 'Backprop' in dirs:
data_y = np.argmax(data_y,axis=1)
data_y = np.ravel(data_y)
print("shape of data_y", np.shape(data_y))
if 'Xpred' in subfiles:
filename = os.path.join(data_dir, dirs, subdirs, subfiles)
data_x = pd.read_csv(filename, header=None, sep=' ').values
print("shape of data_x", np.shape(data_x))
plotData(data_x, data_y, save_dir=dirs+'generated_gaussian_inference0.png',eval_mode=True)
def evaluate_from_model(model_dir, multi_flag=False, eval_data_all=False):
"""
Evaluating interface. 1. Retreive the flags 2. get data 3. initialize network 4. eval
:param model_dir: The folder to retrieve the model
:param eval_data_all: The switch to turn on if you want to put all data in evaluation data
:return: None
"""
# Retrieve the flag object
print("Retrieving flag object for parameters")
if (model_dir.startswith("models")):
model_dir = model_dir[7:]
print("after removing prefix models/, now model_dir is:", model_dir)
flags = helper_functions.load_flags(os.path.join("models", model_dir))
flags.eval_model = model_dir # Reset the eval mode
# Set up the test_ratio
if flags.data_set == 'ballistics':
flags.test_ratio = 0.1
elif flags.data_set == 'sine_wave':
flags.test_ratio = 0.1
elif flags.data_set == 'robotic_arm':
flags.test_ratio = 0.1
# Get the data
train_loader, test_loader = data_reader.read_data(flags, eval_data_all=eval_data_all)
print("Making network now")
# Make Network
ntwk = Network(INN, flags, train_loader, test_loader, inference_mode=True, saved_model=flags.eval_model)
print(ntwk.ckpt_dir)
print("number of trainable parameters is :")
pytorch_total_params = sum(p.numel() for p in ntwk.model.parameters() if p.requires_grad)
print(pytorch_total_params)
# Evaluation process
print("Start eval now:")
if multi_flag:
ntwk.evaluate_multiple_time()
else:
pred_file, truth_file = ntwk.evaluate()
# Plot the MSE distribution
if flags.data_set != 'meta_material' and not multi_flag:
plotMSELossDistrib(pred_file, truth_file, flags)
print("Evaluation finished")
# If gaussian, plot the scatter plot
if flags.data_set == 'gaussian_mixture':
Xpred = helper_functions.get_Xpred(path='data/', name=flags.eval_model)
Ypred = helper_functions.get_Ypred(path='data/', name=flags.eval_model)
# Plot the points scatter
generate_Gaussian.plotData(Xpred, Ypred, save_dir='data/' + flags.eval_model.replace('/','_') + 'generation plot.png', eval_mode=True)