def main(gpu, args):
rank = args.nr * args.gpus + gpu
dist.init_process_group(backend='nccl',
init_method='env://',
world_size=args.world_size,
rank=rank)
with open(args.config) as config_file:
params = json.load(config_file)
params['nodes'] = args.nodes
params['gpus'] = args.gpus
params['nr'] = args.nr
params['world_size'] = args.world_size
params['rank'] = rank
random.seed(params['seed'])
np.random.seed(params['seed'])
torch.manual_seed(params['seed'])
preproc = Preprocessor(sp_model=params['sp_model'])
params['vocab_size'] = preproc.vocab_size
logger = Logger(params['logfile'])
logger.write('Loading data...')
train_dataloader, eval_dataloader = prepare_dataset(
dataset_dir=params['dataset_dir'],
train_sets=params['train_sets'],
eval_sets=params['eval_sets'],
batch_size=params['batch_size'],
preproc=preproc,
world_size=args.world_size,
rank=rank)
logger.write('Model initialization...')
model, num_params = make_model(params)
logger.write(f'Total number of parameters: {num_params}')
torch.cuda.set_device(gpu)
model.cuda()
optimizer = torch.optim.Adadelta(model.parameters(),
lr=params['lr'],
eps=1e-8,
rho=0.95,
weight_decay=params['weight_decay'])
model, optimizer = amp.initialize(min_loss_scale=1.0,
models=model,
optimizers=optimizer,
opt_level=params['opt_level'])
model = DDP(model)
train(data=[train_dataloader, eval_dataloader, preproc],
model=model,
optimizer=optimizer,
logger=logger,
params=params)
def main(args):
sess = utils.create_session()
mymodel = make_model(sess, args.model_to_run, args.model_path, args.labels_path)
source_dirs = f'{args.source_dir}{args.mapping_labels_to_dirs[args.target_class]}'
filenames = []
predictions = []
for source_dir in glob(f'{source_dirs}/*'):
cd = ConceptDiscovery(
mymodel,
args.mapping_labels_to_dirs[args.target_class],
sess,
f'{source_dir}/')
try:
prediction, filename = cd.predict()
predictions.append(prediction)
filenames.append(filename[0])
except ValueError as e:
predictions.append(np.nan)
filenames.append(source_dir)
pass
sess.close()
num_predictions = len(predictions)
directory = [source_dirs.split('/')[-2]] * num_predictions
true_labels = [args.target_class] * num_predictions
predicted_labels = []
for prediction in predictions:
try:
predicted_labels.append(mymodel.id_to_label(prediction.tolist()[0].index(np.max(prediction))))
except AttributeError:
predicted_labels.append(np.nan)
prediction_probability = [np.max(prediction) for prediction in predictions]
df = pd.DataFrame({
'directory': directory,
'filename': filenames,
'true_label': true_labels,
'predicted_label': predicted_labels,
'prediction_probability': prediction_probability
})
save_filename = f"./baseline_predictions/{'_'.join(args.target_class.split(' '))}_baseline_predictions.csv"
save_filepath = Path(save_filename)
save_filepath.touch(exist_ok=True)
df.to_csv(save_filename, index=False)
def main(args, activations_dir, cavs_dir, random_concept='random_discovery'):
sess = utils.create_session()
mymodel = make_model(sess, args.model_to_run, args.model_path,
args.labels_path)
cd = ConceptDiscovery(mymodel, args.target_class, random_concept,
args.bottlenecks, sess, args.source_dir,
activations_dir, cavs_dir)
bn_activations = cd.get_img_activations(args.img_num, args.concept_num)
sess.close()
def main(args, img_path, true_label):
sess = utils.create_session()
mymodel = make_model(sess, args.model_to_run, args.model_path, args.labels_path)
filenames = []
predictions = []
baseline_prediction_probs = []
baseline_predictions = pd.read_csv(f"./baseline_prediction_samples/{true_label}baseline_prediction_samples.csv")
for img in glob(f'{img_path}/*'):
cd = ConceptDiscovery(
mymodel,
args.target_class,
sess,
f"./net_occlusion_heatmaps_delta_prob/{img.split('/')[-1].split('_')[0]}/{img.split('/')[-1]}/mask_dim_100/{img.split('/')[-1]}_image_cropped_to_mask/")
prediction, filename = cd.predict()
# No instances where true label != predicted label in sample
baseline_prediction_probs.append(baseline_predictions[baseline_predictions['filename'].str.contains(img.split('/')[-1])]['prediction_probability'].values[0])
try:
prediction, filename = cd.predict()
predictions.append(prediction)
filenames.append(filename[0])
except ValueError as e:
predictions.append(np.nan)
filenames.append(args.source_dir)
pass
sess.close()
true_labels = [true_label] * len(predictions)
predicted_labels = []
for prediction in predictions:
try:
predicted_labels.append(mymodel.id_to_label(prediction.tolist()[0].index(np.max(prediction))))
except AttributeError:
predicted_labels.append(np.nan)
if args.target_class == 'crane bird':
args.target_class = 'crane'
elif args.target_class == 'african grey':
args.target_class = 'African grey'
elif args.target_class == 'tank suit':
args.target_class = 'maillot'
true_label_predictions = []
true_label_prediction_delta = []
for prediction, baseline_prediction_probs in zip(predictions,baseline_prediction_probs):
try:
true_label_prediction_prob = prediction.tolist()[0][mymodel.label_to_id(args.target_class)]
true_label_predictions.append(true_label_prediction_prob)
true_label_prediction_delta.append(true_label_prediction_prob-baseline_prediction_probs)
except AttributeError:
true_label_predictions.append(np.nan)
prediction_probability = [np.max(prediction) for prediction in predictions]
df = pd.DataFrame({
'filename': filenames,
'true_label': true_labels,
'true_label_predictions': true_label_predictions,
'true_label_predictions_delta': true_label_prediction_delta,
'predicted_label': predicted_labels,
'prediction_probability': prediction_probability
})
save_filename = f"./net_heatmap_predictions/mask_dim_100/{'_'.join(true_label.split(' '))}_heatmap_predictions.csv"
save_filepath = Path(save_filename)
save_filepath.touch(exist_ok=True)
df.to_csv(save_filename, index=False)
def main(args):
sess = utils.create_session()
mymodel = make_model(sess, args.model_to_run, args.model_path,
args.labels_path)
filenames = []
predictions = []
for source_dir in glob(f'{args.source_dir}/*'):
cd = ConceptDiscovery(mymodel, None, None, None, sess,
f'{source_dir}/', None, None)
try:
prediction, filename = cd.predict()
predictions.append(prediction)
filenames.append(filename[0])
except ValueError as e:
predictions.append(np.nan)
filenames.append(source_dir)
pass
sess.close()
num_predictions = len(predictions)
directory = ['/'.join(args.source_dir.split('/')[:4])] * num_predictions
mask_dim = [args.source_dir.split('/')[-2].split('_')[-1]
] * num_predictions
true_labels = [args.target_class] * num_predictions
# For occluded image prediction need to find prediction accuracy of true label
predicted_labels = []
for prediction in predictions:
try:
predicted_labels.append(
mymodel.id_to_label(prediction.tolist()[0].index(
np.max(prediction))))
except AttributeError:
predicted_labels.append(np.nan)
if args.target_class == 'crane bird':
args.target_class = 'crane'
elif args.target_class == 'african grey':
args.target_class = 'African grey'
elif args.target_class == 'tank suit':
args.target_class = 'maillot'
true_label_predictions = []
for prediction in predictions:
try:
true_label_predictions.append(
prediction.tolist()[0][mymodel.label_to_id(args.target_class)])
except AttributeError:
true_label_predictions.append(np.nan)
prediction_probability = [np.max(prediction) for prediction in predictions]
df = pd.DataFrame({
'directory': directory,
'mask_dim': mask_dim,
'filename': filenames,
'true_label': true_labels,
'true_label_predictions': true_label_predictions,
'predicted_label': predicted_labels,
'prediction_probability': prediction_probability
})
# save_filename = f"./occluded_image_predictions/mask_dim_{mask_dim[0]}/{'_'.join(args.target_class.split(' '))}_image_{args.source_dir.split('/')[3]}_occluded_image_predictions.csv"
save_filename = 'occluded_image_predictions/mask_dim_100/cab_image_n02930766_23814_occluded_image_predictions.csv'
save_filepath = Path(save_filename)
save_filepath.touch(exist_ok=True)
df.to_csv(save_filename, index=False)