Skip to content
Snippets Groups Projects
Commit a45b2b75 authored by Luc Giffon's avatar Luc Giffon
Browse files

CLuger now create output folder if it doesn't exist

parent 3f290169
Branches
No related tags found
No related merge requests found
Expand all Show whitespace changes
Inline Side-by-side
Showing
with 1273 additions and 24 deletions
main/experiments/benchmark_classification.py
+ 6
− 7
View file @ a45b2b75
......@@ -59,22 +59,22 @@ Kernel related:
"""
import logging
import sys
import time as t
import daiquiri
import docopt
import numpy as np
import tensorflow as tf
import docopt
import time as t
from tensorflow.python.keras.layers import Dense
import skluc.main.data.mldatasets as dataset
from skluc.main.data.transformation.VGG19Transformer import VGG19Transformer
from skluc.main.data.transformation.LeCunTransformer import LecunTransformer
from skluc.main.tensorflow_.kernel_approximation.nystrom_layer import DeepstromLayer
from skluc.main.tensorflow_.kernel_approximation.fastfood_layer import FastFoodLayer
from skluc.main.tensorflow_.utils import batch_generator
from skluc.main.data.transformation.VGG19Transformer import VGG19Transformer
from skluc.main.tensorflow_.kernel import tf_rbf_kernel, tf_linear_kernel, tf_chi_square_CPD, tf_chi_square_CPD_exp, \
tf_chi_square_PD, tf_sigmoid_kernel, tf_laplacian_kernel, tf_stack_of_kernels, tf_sum_of_kernels
from skluc.main.tensorflow_.kernel_approximation.fastfood_layer import FastFoodLayer
from skluc.main.tensorflow_.kernel_approximation.nystrom_layer import DeepstromLayer
from skluc.main.tensorflow_.utils import batch_generator
from skluc.main.utils import logger, compute_euristic_sigma, compute_euristic_sigma_chi2, memory_usage
......@@ -113,7 +113,6 @@ def print_result(global_acc_val=None, global_acc_test=None, training_time=None,
raise error
def get_gamma_value(arguments, dat, chi2=False):
if arguments["--gamma"] is None:
logger.debug("Gamma arguments is None. Need to compute it.")
......
main/experiments/graph_drawing/till_october_2018/transfert_few_data/vgg_svhn_from_cifar100_deepstrom_few_data.py
+ 9
− 8
View file @ a45b2b75
......@@ -5,6 +5,7 @@ import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import pathlib
from skluc.main.utils import logger
matplotlib.rcParams.update({'font.size': 14})
......@@ -25,7 +26,7 @@ min_acc = 0.00
max_acc = 1.05
# max_acc = 1.0
linewidth = 0.9
output_conv_dim = 512
output_conv_dims = {'block3_pool': 256 * 16, 'block5_conv4': 512 * 4, 'block5_pool': 512}
nb_classes = 10
real_nys_marker = "s"
......@@ -129,8 +130,8 @@ if __name__ == '__main__':
np_deepstrom_kernel_w_std_accuracy_test = np.std(all_accs_w, axis=0)
np_param_nbr_deepstrom_kernel_w = (
np.square(np.array(sorted(set(df_deepstrom_kernel_w["subsample_size"])))) + # m x m
np.array(
sorted(set(df_deepstrom_kernel_w["subsample_size"]))) * output_conv_dim + # m x d
# np.array(
# sorted(set(df_deepstrom_kernel_w["subsample_size"]))) * output_conv_dims[cut_layer] + # m x d
np.array(
sorted(list(set(df_deepstrom_kernel_w["subsample_size"])))) * nb_classes) # m x c
......@@ -153,8 +154,8 @@ if __name__ == '__main__':
np_param_nbr_deepstrom_kernel_k = (
np.square(np.array(sorted(set(df_deepstrom_kernel_k["subsample_size"])))) + # m x m
np.array(sorted(
set(df_deepstrom_kernel_k["subsample_size"]))) * output_conv_dim + # m x d
# np.array(sorted(
# set(df_deepstrom_kernel_k["subsample_size"]))) * output_conv_dims[cut_layer] + # m x d
np.array(sorted(
list(set(df_deepstrom_kernel_k["subsample_size"])))) * nb_classes) # m x c
......@@ -178,7 +179,7 @@ if __name__ == '__main__':
np.array([list(df_dense[df_dense["seed"] == seed_v]["accuracy_test"]) for seed_v in
seed_values]), axis=0)
ax.errorbar(
np.array(sorted([int(n) for n in np.unique(df_dense["repr_dim"])])) * output_conv_dim +
np.array(sorted([int(n) for n in np.unique(df_dense["repr_dim"])])) * output_conv_dims[cut_layer] +
np.array(sorted([int(n) for n in np.unique(df_dense["repr_dim"])])) * nb_classes,
np_dense_mean_accuracy_test,
np_dense_std_accuracy_test,
......@@ -197,7 +198,7 @@ if __name__ == '__main__':
np_deepfried_mean_accuracy_test.append(np.mean(df_deepfried_stack["accuracy_test"]))
np_deepfried_std_accuracy_test.append(np.std(df_deepfried_stack["accuracy_test"]))
nb_param_vals = [(output_conv_dim * 3 + output_conv_dim * nb_classes) * int(i) for i in sorted(set(df_deepfried["nb_layer_deepfried"].values))]
nb_param_vals = [(output_conv_dims[cut_layer] * 3 + output_conv_dims[cut_layer] * nb_classes) * int(i) for i in sorted(set(df_deepfried["nb_layer_deepfried"].values))]
ax.errorbar(nb_param_vals,
np_deepfried_mean_accuracy_test,
np_deepfried_std_accuracy_test,
......@@ -211,7 +212,7 @@ if __name__ == '__main__':
ax.set_xticks([1e4, 1e5, 1e6])
# if i == 2:
# ax.set_xlabel("# Parameters")
ax.set_xlabel("# Parameters")
ax.set_xlabel("# Learnable Parameters")
ax.legend(bbox_to_anchor=(0.5, -0.20), loc="upper center", ncol=2)
ax.set_xticklabels([1e4, 1e5, 1e6])
# else:
......
main/experiments/graph_drawing/till_october_2018/transfert_few_data_batchnorm/vgg_deepstrom_few_data_batchnorm.py
+ 9
− 8
View file @ a45b2b75
......@@ -5,6 +5,7 @@ import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import pathlib
from skluc.main.utils import logger
matplotlib.rcParams.update({'font.size': 14})
......@@ -25,7 +26,7 @@ min_acc = 0.00
max_acc = 1.05
# max_acc = 1.0
linewidth = 0.9
output_conv_dim = 512
output_conv_dims = {'block3_pool': 256 * 16, 'block5_conv4': 512 * 4, 'block5_pool': 512}
nb_classes = 10
real_nys_marker = "s"
......@@ -130,8 +131,8 @@ if __name__ == '__main__':
np_deepstrom_kernel_w_std_accuracy_test = np.std(all_accs_w, axis=0)
np_param_nbr_deepstrom_kernel_w = (
np.square(np.array(sorted(set(df_deepstrom_kernel_w["subsample_size"])))) + # m x m
np.array(
sorted(set(df_deepstrom_kernel_w["subsample_size"]))) * output_conv_dim + # m x d
# np.array(
# sorted(set(df_deepstrom_kernel_w["subsample_size"]))) * output_conv_dims[cut_layer] + # m x d
np.array(
sorted(list(set(df_deepstrom_kernel_w["subsample_size"])))) * nb_classes) # m x c
......@@ -154,8 +155,8 @@ if __name__ == '__main__':
np_param_nbr_deepstrom_kernel_k = (
np.square(np.array(sorted(set(df_deepstrom_kernel_k["subsample_size"])))) + # m x m
np.array(sorted(
set(df_deepstrom_kernel_k["subsample_size"]))) * output_conv_dim + # m x d
# np.array(sorted(
# set(df_deepstrom_kernel_k["subsample_size"]))) * output_conv_dims[cut_layer] + # m x d
np.array(sorted(
list(set(df_deepstrom_kernel_k["subsample_size"])))) * nb_classes) # m x c
......@@ -179,7 +180,7 @@ if __name__ == '__main__':
np.array([list(df_dense[df_dense["seed"] == seed_v]["accuracy_test"]) for seed_v in
seed_values]), axis=0)
ax.errorbar(
np.array(sorted([int(n) for n in np.unique(df_dense["repr_dim"])])) * output_conv_dim +
np.array(sorted([int(n) for n in np.unique(df_dense["repr_dim"])])) * output_conv_dims[cut_layer] +
np.array(sorted([int(n) for n in np.unique(df_dense["repr_dim"])])) * nb_classes,
np_dense_mean_accuracy_test,
np_dense_std_accuracy_test,
......@@ -198,7 +199,7 @@ if __name__ == '__main__':
np_deepfried_mean_accuracy_test.append(np.mean(df_deepfried_stack["accuracy_test"]))
np_deepfried_std_accuracy_test.append(np.std(df_deepfried_stack["accuracy_test"]))
nb_param_vals = [(output_conv_dim * 3 + output_conv_dim * nb_classes) * int(i) for i in sorted(set(df_deepfried["nb_layer_deepfried"].values))]
nb_param_vals = [(output_conv_dims[cut_layer] * 3 + output_conv_dims[cut_layer] * nb_classes) * int(i) for i in sorted(set(df_deepfried["nb_layer_deepfried"].values))]
ax.errorbar(nb_param_vals,
np_deepfried_mean_accuracy_test,
np_deepfried_std_accuracy_test,
......@@ -212,7 +213,7 @@ if __name__ == '__main__':
ax.set_xticks([1e4, 1e5, 1e6])
# if i == 2:
# ax.set_xlabel("# Parameters")
ax.set_xlabel("# Parameters")
ax.set_xlabel("# Learnable Parameters")
ax.legend(bbox_to_anchor=(0.5, -0.20), loc="upper center", ncol=2)
ax.set_xticklabels([1e4, 1e5, 1e6])
# else:
......
main/experiments/graph_drawing/till_october_2018/transfert_few_data_cifar100_from_cifar10/vgg_deepstrom_few_data_cifar100_from_cifar10.py
+ 2
− 1
View file @ a45b2b75
......@@ -5,6 +5,7 @@ import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import pathlib
from skluc.main.utils import logger
matplotlib.rcParams.update({'font.size': 14})
......@@ -17,7 +18,7 @@ pd.set_option('display.expand_frame_repr', False)
DATANAME = "CIFAR100"
DIRNAME = "/home/luc/Resultats/Deepstrom/october_2018/transfert_few_data"
DIRNAME = "/home/luc/Resultats/Deepstrom/october_2018/transfert_few_data_cifar100_from_cifar10"
FILENAME = "gathered_results.csv"
......
main/experiments/graph_drawing/till_october_2018/transfert_few_data_cifar10_from_cifar100/vgg_deepstrom_few_data_cifar10_from_cifar100.py 0 → 100644
+ 259
− 0
View file @ a45b2b75
import os
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import pathlib
from skluc.main.utils import logger
matplotlib.rcParams.update({'font.size': 14})
# pd.set_option('display.width', 1000)
pd.set_option('display.expand_frame_repr', False)
# DAT = ["SVHN"]
# DIR = ["/home/luc/Resultats/Deepstrom/october_2018/transfert_few_data_cifar100_from_cifar10"]
DATANAME = "SVHN"
DIRNAME = "/home/luc/Resultats/Deepstrom/october_2018/transfert_few_data_cifar10_from_cifar100"
FILENAME = "gathered_results.csv"
min_acc = 0.00
max_acc = 1.05
# max_acc = 1.0
linewidth = 0.9
output_conv_dims = {'block3_pool': 256 * 16, 'block5_conv4': 512 * 4, 'block5_pool': 512}
nb_classes = 10
real_nys_marker = "s"
learned_nys_marker = "x"
linearity_color = "g"
dense_marker = "v"
dense_color = "r"
deepfried_marker = "8"
deepfried_color = "b"
d_translate_kernel = {
"linear": "Linear",
"chi2_cpd": "Chi2",
"rbf": "Gaussian"
}
if __name__ == '__main__':
filepath = os.path.join(DIRNAME, FILENAME)
field_names = ["method_name",
"accuracy_val",
"accuracy_test",
"runtime_train",
"runtime_val",
"runtime_test",
"number_epoch",
"batch_size",
"repr_dim",
"second_layer_size",
"kernel_deepstrom",
"gamma_kernel",
"constante_sigmoid",
"nb_layer_deepfried",
"subsample_size",
"validation_size",
"seed",
"act",
"non_linearity",
"real_nystrom",
"repr_quality",
"train_size",
"dropout",
"dataset",
"real_deepfried",
"weights"
]
df = pd.read_csv(filepath, names=field_names)
df = df[df["accuracy_val"] != 'None']
df = df.apply(pd.to_numeric, errors="ignore")
df = df.drop_duplicates()
method_names = set(df["method_name"].values)
kernel_names = set(df["kernel_deepstrom"].values)
kernel_names.remove("None")
# kernel_names.remove("laplacian")
repr_dim = set(df["repr_dim"].values)
repr_dim.remove("None") # dtype: str
# repr_dim.remove("16")
nys_size = set(df["subsample_size"].values)
nys_size.remove("None")
nb_layers_deepfried = set(df["nb_layer_deepfried"].values)
nb_layers_deepfried.remove("None")
seed_values = set(df["seed"].values)
batch_size = 128
train_sizes = set(df["train_size"])
cut_layers = set(df["repr_quality"].values)
weights = set(df["weights"].values)
logger.debug("Nystrom possible sizes are: {}".format(nys_size))
logger.debug("Kernel functions are: {}".format(kernel_names))
logger.debug("Compared network types are: {}".format(method_names))
logger.debug("Tested representation dimension are: {}".format(repr_dim))
logger.debug(f"Tested cut layers: {cut_layers}")
means_deepstrom = {}
for weight in weights:
df_weight = df[df["weights"] == weight]
for t_size in sorted(list(train_sizes)):
df_tsize = df_weight[df_weight["train_size"] == t_size]
for cut_layer in cut_layers:
df_cut_layer = df_tsize[df_tsize["repr_quality"] == cut_layer]
# plot deepstrom
# ==============
df_deepstrom = df_cut_layer[df_cut_layer["method_name"] == "deepstrom"]
df_deepstrom["subsample_size"] = df_deepstrom["subsample_size"].astype(np.int)
df_deepstrom_sort = df_deepstrom.sort_values(by=["subsample_size"])
for k_name in sorted(kernel_names):
df_deepstrom_kernel = df_deepstrom_sort[df_deepstrom_sort["kernel_deepstrom"] == k_name]
f, ax = plt.subplots()
# get the results of learned nystrom
df_deepstrom_kernel_w = df_deepstrom_kernel[df_deepstrom_kernel["real_nystrom"] == False]
all_accs_w = np.array([
list(df_deepstrom_kernel_w[df_deepstrom_kernel_w["seed"] == seed_v]["accuracy_test"]) for
seed_v in seed_values
])
np_deepstrom_kernel_w_mean_accuracy_test = np.mean(all_accs_w, axis=0)
np_deepstrom_kernel_w_std_accuracy_test = np.std(all_accs_w, axis=0)
np_param_nbr_deepstrom_kernel_w = (
np.square(np.array(sorted(set(df_deepstrom_kernel_w["subsample_size"])))) + # m x m
# np.array(
# sorted(set(df_deepstrom_kernel_w["subsample_size"]))) * output_conv_dims[cut_layer] + # m x d
np.array(
sorted(list(set(df_deepstrom_kernel_w["subsample_size"])))) * nb_classes) # m x c
ax.errorbar(np_param_nbr_deepstrom_kernel_w,
np_deepstrom_kernel_w_mean_accuracy_test,
np_deepstrom_kernel_w_std_accuracy_test,
marker=learned_nys_marker, color=linearity_color,
label="Adaptative Deepström",
capsize=3)
# get the results of vanilla nystrom
df_deepstrom_kernel_k = df_deepstrom_kernel[df_deepstrom_kernel["real_nystrom"]]
if len(df_deepstrom_kernel_k):
all_accs_k = np.array([
list(df_deepstrom_kernel_k[df_deepstrom_kernel_k["seed"] == seed_v]["accuracy_test"]) for
seed_v in seed_values
])
np_deepstrom_kernel_k_mean_accuracy_test = np.mean(all_accs_k, axis=0)
np_deepstrom_kernel_k_std_accuracy_test = np.std(all_accs_k, axis=0)
np_param_nbr_deepstrom_kernel_k = (
np.square(np.array(sorted(set(df_deepstrom_kernel_k["subsample_size"])))) + # m x m
# np.array(sorted(
# set(df_deepstrom_kernel_k["subsample_size"]))) * output_conv_dims[cut_layer] + # m x d
np.array(sorted(
list(set(df_deepstrom_kernel_k["subsample_size"])))) * nb_classes) # m x c
ax.errorbar(np_param_nbr_deepstrom_kernel_k,
np_deepstrom_kernel_k_mean_accuracy_test,
np_deepstrom_kernel_k_std_accuracy_test,
marker=real_nys_marker, color=linearity_color,
label="Deepström",
capsize=3)
# plot dense
# ==========
df_dense = df_cut_layer[df_cut_layer["method_name"] == "dense"]
df_dense = df_dense[df_dense["train_size"] == t_size]
df_dense["repr_dim"] = df_dense["repr_dim"].astype(np.int)
df_dense = df_dense.sort_values(by=["repr_dim"])
np_dense_mean_accuracy_test = np.mean(
np.array([list(df_dense[df_dense["seed"] == seed_v]["accuracy_test"]) for seed_v in
seed_values]), axis=0)
np_dense_std_accuracy_test = np.std(
np.array([list(df_dense[df_dense["seed"] == seed_v]["accuracy_test"]) for seed_v in
seed_values]), axis=0)
ax.errorbar(
np.array(sorted([int(n) for n in np.unique(df_dense["repr_dim"])])) * output_conv_dims[cut_layer] +
np.array(sorted([int(n) for n in np.unique(df_dense["repr_dim"])])) * nb_classes,
np_dense_mean_accuracy_test,
np_dense_std_accuracy_test,
color=dense_color,
marker=dense_marker,
label="Fully Connected", capsize=3)
# # plot deepfried
# # ==============
df_deepfried = df_cut_layer[df_cut_layer["method_name"] == "deepfriedconvnet"]
np_deepfried_mean_accuracy_test = []
np_deepfried_std_accuracy_test = []
for l_nb in sorted(nb_layers_deepfried):
df_deepfried_stack = df_deepfried[df_deepfried["nb_layer_deepfried"] == l_nb]
if len(df_deepfried_stack):
np_deepfried_mean_accuracy_test.append(np.mean(df_deepfried_stack["accuracy_test"]))
np_deepfried_std_accuracy_test.append(np.std(df_deepfried_stack["accuracy_test"]))
nb_param_vals = [(output_conv_dims[cut_layer] * 3 + output_conv_dims[cut_layer] * nb_classes) * int(i) for i in sorted(set(df_deepfried["nb_layer_deepfried"].values))]
ax.errorbar(nb_param_vals,
np_deepfried_mean_accuracy_test,
np_deepfried_std_accuracy_test,
color=deepfried_color,
marker=deepfried_marker,
label="Adaptative DeepFriedConvnet", capsize=3)
ax.set_ylim(min_acc, max_acc)
ax.set_ylabel("Accuracy")
ax.set_xticks([1e4, 1e5, 1e6])
# if i == 2:
# ax.set_xlabel("# Parameters")
ax.set_xlabel("# Learnable Parameters")
ax.legend(bbox_to_anchor=(0.5, -0.20), loc="upper center", ncol=2)
ax.set_xticklabels([1e4, 1e5, 1e6])
# else:
# ax.set_xticklabels([])
ax.set_xscale("symlog")
ax_twin = ax.twiny()
ax_twin.set_xscale("symlog")
ax_twin.set_xlim(ax.get_xlim())
ax_twin.set_xticks(np_param_nbr_deepstrom_kernel_w)
# if i == 0:
ax_twin.set_xlabel("Subsample Size")
ax.set_title(
"{} Kernel - {} - Train size: {} - weights: {}".format(d_translate_kernel[k_name], DATANAME, t_size, weight),
y=1.2)
ax_twin.set_xticklabels(sorted(set(df_deepstrom_kernel_w["subsample_size"])))
# else:
# ax.set_title("Noyau {} - {} - Train size: {}".format(d_translate_kernel[k_name], DATANAME, t_size))
# ax_twin.set_xticklabels([])
f.set_size_inches(8, 6)
f.tight_layout()
f.subplots_adjust(bottom=0.3)
# f.show()
# exit()
# learnable: change legend
# ODIR = [
# "/home/luc/PycharmProjects/deepFriedConvnets/main/experiments/graph_drawing/paper/svhn/few_data/parameters/dropout_{}".format(
# str(drop_val).replace(".", "-"))]
# out_dir_path = ODIR[h]
out_name = "acc_param_tsize_{}_{}_{}".format(t_size, cut_layer, k_name)
base_out_dir = os.path.join(os.path.abspath(__file__.split(".")[0]), "images", f"{weight}", f"{cut_layer}")
pathlib.Path(base_out_dir).mkdir(parents=True, exist_ok=True)
out_path = os.path.join(base_out_dir, out_name)
logger.debug(out_path)
f.savefig(out_path)
main/experiments/parameter_files/october_2018/lazyfile_transfert_few_data_big_subsample_chi2.yml 0 → 100644
+ 21
− 0
View file @ a45b2b75
all:
deepstrom:
base:
epoch_numbers: {"-e": [100]}
batch_sizes: {"-s": [64]}
val_size: {"-v": [10000]}
seed: {"-a": "range(10)"}
quiet: ["-q"]
data_size: {"-t":[20, 50, 100, 200, 500, 1000, 2000]}
dataset: ["--svhn", "--cifar10"]
weights: {"-W": ["cifar100"]}
cut_layer: {"-B": ["block3_pool"]}
deepstrom:
network: ["deepstrom"]
base:
real_nys: ["-r", ""]
nys_size: {"-m": [256, 512, 1024]}
kernel: ["-C"]
main/experiments/parameter_files/october_2018/lazyfile_transfert_few_data_cifar10_from_cifar100_and_cifar10.yml 0 → 100644
+ 33
− 0
View file @ a45b2b75
all:
dense:
deepfried:
deepstrom:
base:
epoch_numbers: {"-e": [100]}
batch_sizes: {"-s": [64]}
val_size: {"-v": [10000]}
seed: {"-a": "range(5)"}
quiet: ["-q"]
data_size: {"-t":[50, 250, 500, 1000, 2000]}
dataset: ["--cifar10"]
weights: {"-W": ["cifar100", "cifar10"]}
cut_layer: {"-B": ["block3_pool", "block5_conv4", "block5_pool"]}
dense:
network: ["dense"]
base:
repr_dim: {"-D": [16, 64, 128, 1024]}
deepfried:
network: ["deepfriedconvnet"]
base:
nbstacks: {"-N": [1, 3, 5, 7]}
deepstrom:
network: ["deepstrom"]
base:
real_nys: ["-r", ""]
nys_size: {"-m": [16, 64, 128, 256, 512, 1024]}
kernel: ["-C", "-L", "-R"]
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment