def predict_target_by_paths(paths, augment_times=1):
util.set_img_format()
# sys.argv[0] = "--model=resnet50"
predict.args = predict.parse_args()
predict.model_module = util.get_model_class_instance()
predict.model = predict.model_module.load()
predict.classes_in_keras_format = util.get_classes_in_keras_format()
for path in paths:
predict.predict(dir=path, augment_times=augment_times)
def predict_target_by_dir(main_dir, augment_times=1):
util.set_img_format()
# sys.argv[0] = "--model=resnet50"
predict.args = predict.parse_args()
predict.model_module = util.get_model_class_instance()
predict.model = predict.model_module.load()
predict.classes_in_keras_format = util.get_classes_in_keras_format()
dirs = glob.glob(main_dir + "*")
global_summary = {"total": 0, "trues": 0, "falses": 0, "acc": 0}
iter = 0
for dir in dirs:
stats = predict.predict(dir + os.sep, iter, augment_times, False)
iter += 1
global_summary["total"] += stats["summary"]["total"]
global_summary["trues"] += stats["summary"]["trues"]
global_summary["falses"] += stats["summary"]["falses"]
global_summary["acc"] = float(
global_summary["trues"]) / global_summary["total"]
print("Global summary: {0}".format(global_summary))
for caffefile in glob.glob('*.caffemodel'):
m = re.search(r'\S+(\d+)_iter_(\d+).caffemodel', caffefile)
if m:
fold = int(m.group(1))
iter = int(m.group(2))
if fold not in models or models[fold][1] < iter:
models[fold] = (caffefile, iter)
#for each fold, collect the predictions
predictions = [] #a list of tuples
topresults = []
for fold in models:
(caffefile, iter) = models[fold]
testfile = prefix + 'test%d.types' % fold
pargs = predict.parse_args([
'-m', 'model.model', '-w', caffefile, '-d', args.data_root, '-i',
testfile
])
predictions += predict.predict(pargs)[0]
topresults += calctop.evaluate_fold(testfile, caffefile, 'model.model',
args.data_root)
#parse prediction lines
expaffs = []
predaffs = []
scores = []
labels = []
for p in predictions:
score = p[0]
predaff = p[1]
vals = p[2].split()
label = float(vals[0])
for caffefile in glob.glob('*.caffemodel'):
m = re.search(r'\S+(\d+)_iter_(\d+).caffemodel',caffefile)
if m:
fold = int(m.group(1))
iter = int(m.group(2))
if fold not in models or models[fold][1] < iter:
models[fold] = (caffefile,iter)
#for each fold, collect the predictions
predictions = [] #a list of tuples
topresults = []
for fold in models:
(caffefile, iter) = models[fold]
testfile = prefix+'test%d.types'%fold
pargs = predict.parse_args(['-m','model.model','-w',caffefile,'-d',args.data_root,'-i',testfile])
predictions += predict.predict(pargs)[0]
topresults += calctop.evaluate_fold(testfile,caffefile,'model.model',args.data_root)
#parse prediction lines
expaffs = []
predaffs = []
scores = []
labels = []
for p in predictions:
score = p[0]
predaff = p[1]
vals = p[2].split()
label = float(vals[0])
aff = float(vals[1])
scores.append(score)
def main():
args = parse_args()
print("cuda: %s" % CUDA)
evaluate(predict(args.test_data, *load_model(args)))