def batch_predict(configfile, targets):
config = ConfigParser.ConfigParser()
config.read(configfile)
model_name = config.get("net", "net")
model_def = os.path.join(model_dir, "%s.prototxt" % model_name)
pretrained = os.path.join(model_dir, "%s.caffemodel" % model_name)
mean = config.get("net", "mean")
dim = int(config.get("net", "image_dim"))
raw_scale = int(config.get("net", "raw_scale"))
net = caffe.Classifier(model_def, pretrained, channel_swap=(2,1,0), mean=np.load(mean), raw_scale=raw_scale, image_dims=(dim, dim), batch=1)
caffe.set_phase_test()
caffe.set_mode_gpu()
net2 = caffe.Net(config.get("train", "target_test"), config.get("train", "target_model"), 1)
with open(config.get("train", "target_list"), "rb") as f:
reverse_index = pickle.load(f)
layer_name = config.get("train", "target_layer")
count = 0
exec_times = []
prepare_times = []
for cur_idx, image_path in enumerate(targets):
im = caffe.io.load_image(image_path)
tic = time.time()
prepared = face_input_prepare_n(net, [im], False)
out = net.forward(end=layer_name, **{net.inputs[0]: prepared})
out2 = net2.forward_all(**{net2.inputs[0]: out[layer_name]})[net2.outputs[0]]
toc = time.time()
exec_times += [(toc - tic)]
i = out2[0].argmax()
if i == len(reverse_index):
print -1
else:
print reverse_index[i]
print 'Execution time(ms) mean:', np.mean(exec_times),'std:', np.std(exec_times, ddof = 1)
def batch_predict_accuracy(configfile, net, net2, video_name, _vgg_data, turker_labels):
config = ConfigParser.ConfigParser()
config.read(configfile)
layer_name = config.get("train", "target_layer")
with open(config.get("train", "target_list"), "rb") as f:
reverse_index = pickle.load(f)
wnidtotrace = wnid_traces_dict()
wptownid = word_prefix_to_wnid_dict()
wnidtolabel = wnid_to_label_dict()
# get the ancestors the word
label_to_trace = {}
for target_label in reverse_index:
caffe_wnid = getwnid(target_label)
trace = wnidtotrace[caffe_wnid]
label_to_trace[target_label] = trace
## Finish loading necessary models ##
print label_to_trace
top_5_vgg_count = 0
top_1_vgg_count = 0
top_1_sp_count = 0
exec_time = []
for keyframe_name in turker_labels:
keyframe_path = os.path.join('/mnt/frames/', video_name, keyframe_name)
# get accuracy for vgg
vgg_data = filter(lambda x: int(x['img_path'].split('/')[-1].split('.')[0]) == int(keyframe_name.split('.')[0]), _vgg_data)
vgg_words = vgg_data[0]['pred']['text']
# get vgg_word trace
top_1_vgg_labels = []
top_5_vgg_labels = []
for k, w in enumerate(vgg_words):
wnid = wptownid[w]
label = wnidtolabel[wnid]
if not (label in reverse_index):
label = -1
if k == 0:
top_1_vgg_labels += [label]
top_5_vgg_labels += [label]
#print vgg_words
#print turker_labels[keyframe_name]
#print top_1_vgg_labels
#print top_5_vgg_labels
vgg_top1_is_match = is_match_splabel(top_1_vgg_labels, label_to_trace, reverse_index, turker_labels[keyframe_name])
vgg_top5_is_match = is_match_splabel(top_5_vgg_labels, label_to_trace, reverse_index, turker_labels[keyframe_name])
if vgg_top1_is_match:
top_1_vgg_count += 1
if vgg_top5_is_match:
top_5_vgg_count += 1
#print turker_labels[keyframe_name]
#print 'top_5_vgg:', top_5_vgg_trace
#print 'top_1_vgg:', top_1_vgg_trace
# predict using specialized
im = caffe.io.load_image(keyframe_path)
layer_name = config.get("train", "target_layer")
tic = time.time()
prepared = face_input_prepare_n(net, [im], False)
out = net.forward(end=layer_name, **{net.inputs[0]: prepared})
out2 = net2.forward_all(**{net2.inputs[0]: out[layer_name]})[net2.outputs[0]]
toc = time.time()
exec_time += [toc - tic]
i = out2[0].argmax()
sp_labels = []
if i == len(reverse_index):
sp_labels += [-1]
else:
sp_labels += [reverse_index[i]]
#print sp_labels
sp_top1_is_match = is_match_splabel(sp_labels, label_to_trace, reverse_index, turker_labels[keyframe_name])
print vgg_top1_is_match, vgg_top5_is_match, sp_top1_is_match
if sp_top1_is_match:
top_1_sp_count += 1
#print vgg_top1_is_match, vgg_top5_is_match, sp_top1_is_match
print 'Top 5 vgg:', top_5_vgg_count/(len(turker_labels) * 1.0)
print 'Top 1 vgg:', top_1_vgg_count/(len(turker_labels) * 1.0)
print 'Top 1 sp:', top_1_sp_count/(len(turker_labels) * 1.0)
print 'SP exec time (ms):', np.mean(exec_time) * 1000, '+-', np.std(exec_time, ddof = 1) * 1000
return top_5_vgg_count, top_1_vgg_count, top_1_sp_count, len(turker_labels)
