def predict(self):
print(self.file)
if not self.file and os.path.isfile(self.file):
return 0
tfms = tfms_from_model(
self.arch, self.sz,
aug_tfms=transforms_side_on,
max_zoom=1.1
)
data = ImageClassifierData.from_paths(
self.PATH, tfms=tfms,
bs=self.bs,
num_workers=4
)
learn = ConvLearner.pretrained(
self.arch, data,
precompute=True,
ps=0.5
)
learn.unfreeze()
learn.precompute = False
learn.load(self.MODEL)
image = open_image(self.file)
trn_tfms, val_tfms = tfms_from_model(self.arch, self.sz)
im = val_tfms(image)
preds = learn.predict_array(im[None])
return learn.data.classes[np.argmax(preds)]
def __init__(self, metadata):
# The temp folder does not exist initially
tmp_dir = metadata.basedir_path / 'tmp'
if not os.path.exists(tmp_dir):
os.mkdir(tmp_dir)
mc_csv = tmp_dir / 'mc.csv'
# Example annotation: bounding box + category id
# print(metadata.training.annotations[12])
# Generate and store the multi-class label csv file
self.save_csv(mc_csv, metadata.train.id_category_map,
metadata.train.id_filename_map,
metadata.train.annotations, metadata.train.annotations)
# Prepare the model
self.model = resnet34
self.image_size = 224
self.batch_size = 64
# Non-agumented transforms
self.non_aug_transforms = tfms_from_model(self.model,
self.image_size,
crop_type=CropType.NO)
# Automatically appends the second 'folder' param to the first - beware!
self.md = ImageClassifierData.from_csv(metadata.basedir_path,
metadata.train.image_subdir,
mc_csv,
tfms=self.non_aug_transforms,
bs=self.batch_size)
self.learner = ConvLearner.pretrained(self.model, self.md)
self.learner.opt_fn = optim.Adam
def __init__(self, event):
self.exit_event = event
self.last_notification_sent = 0
self.notification_threshold = 60 * 5
PATH = os.getcwd()
self.sz = 224
self.arch = resnet34
self.data = ImageClassifierData.from_paths(PATH,
tfms=tfms_from_model(
self.arch, sz))
self.learn = ConvLearner.pretrained(self.arch,
self.data,
precompute=True)
self.learn.load('224_all')
self.trn_tfms, self.val_tfms = tfms_from_model(self.arch, self.sz)
def main(imgdir, epochs):
log.info(f'Cuda available: {torch.cuda.is_available()}')
log.info(f'Cuda backend enabled: {torch.backends.cudnn.enabled}')
# model = resnet34
model = resnet50
tfms = tfms_from_model(resnet34,
IMAGE_SIZE,
aug_tfms=transforms_side_on,
max_zoom=1.1)
data = ImageClassifierData.from_paths(imgdir, tfms=tfms)
learn = ConvLearner.pretrained(model, data, precompute=True)
learn.sched.plot_lr()
def test_image_classifier_data_from_csv_unsorted(root_folder, csv_file,
data_folder):
val_idxs = [2, 3]
tfms = tfms_from_model(resnet34, 224)
path = str(root_folder)
folder = "tmp_data_folder"
csv_fname = Path(str(csv_file))
data = ImageClassifierData.from_csv(
path=Path(path),
folder=folder,
csv_fname=csv_fname,
val_idxs=val_idxs,
suffix=".png",
tfms=tfms,
)
val_fnames = ["8.png", "7.png"]
assert [os.path.split(o)[-1]
for o in data.val_ds.fnames.tolist()] == val_fnames
def __init__(self, modelfilename, verbose=False):
self.model = torch.load(modelfilename, map_location='cpu').eval()
_, self.val_tfms = tfms_from_model(resnet34, 224)
self.verbose = verbose
import torch
from flask_cors import CORS
from scipy.special import expit
import base64
app = Flask(__name__)
CORS(app)
model = torch.load('data/models/torch.resnet101-val-loss-29.914882',
map_location='cpu')
model.eval()
size = 224
trn_tfms, val_tfms = tfms_from_model(resnet101, size, crop_type=CropType.NO)
alphabet = list('abcdefghijklmnopqrstuvwxyz') + ['na']
itoa = {c: l for c, l in enumerate(alphabet)}
def bb_hw(bb):
ymin, xmin, ymax, xmax = bb
return np.array([xmin, ymin, xmax - xmin + 1, ymax - ymin + 1])
@app.route("/api/predict", methods=['POST'])
def make_predictions():
try:
content = request.get_json(force=True)
except HTTPException as e:
return jsonify({'error': 'Request data invalid'}), 400
parser.add_argument('--seed', type=int, default=1)
return parser.parse_args()
args = parse_args()
# --
# IO
# !! Copying from `fastai` for the time being
sys.path.append('/home/bjohnson/software/fastai')
from fastai.dataset import ImageClassifierData
from fastai.transforms import tfms_from_model, transforms_side_on
basenet.helpers.set_seeds(args.seed)
tfms = tfms_from_model(resnet34, 448, aug_tfms=transforms_side_on, max_zoom=1.1)
data = ImageClassifierData.from_paths('_data/cub_splits', tfms=tfms)
dataloaders = {
"train_fixed" : data.fix_dl,
"train" : data.trn_dl,
"val" : data.val_dl
}
# >>
# datasets = make_datasets(root='_data/cub_splits', img_size=224)
# dataloaders = make_dataloaders(datasets)
# <<
# >>
df_total_val, df_large_trn, df_large_val, df_medium_trn, df_medium_val, df_small_trn, df_small_val) = setup_dataset_dfs(LABELS_CSV, LABELS_BASELINE_CSV) ###################### ###################### Network setup ###################### # More settings arch = resnet34 sz=210 tfms = tfms_from_model(arch, sz, crop_type=CropType.NO) trn_tfms, val_tfms = tfms # Training settings bs = 14 seq_len = 10 # Datasets and Dataloaders trn_bds = BatchifiedDataset(df_small_trn, bs, seq_len, trn_tfms, PATH, IMAGES_FOLDER) val_bds = BatchifiedDataset(df_small_val, bs, seq_len, trn_tfms, PATH, IMAGES_FOLDER) trn_dl = FastaiDataLoader(trn_bds, batch_sampler=trn_bds.batch_sampler(shuffle=True)) val_dl = FastaiDataLoader(val_bds, batch_sampler=val_bds.batch_sampler()) # Model FC model_folder = "CNNtoFC"
ROOT = '/media/ssd/datasets/deep-driving-csv/'
PATH = "/media/ssd/datasets/deep-driving-csv/"
IMAGES_FOLDER = "images/"
LABELS_CSV = PATH + "labels.csv"
IMAGES_BASELINE_FOLDER = "images-baseline/"
LABELS_BASELINE_CSV = PATH + "labels-baseline.csv"
(df_baseline, df_total, df_total_tfm, df_total_trn, df_total_val, df_large_trn,
df_large_val, df_medium_trn, df_medium_val, df_small_trn,
df_small_val) = setup_dataset_dfs(LABELS_CSV, LABELS_BASELINE_CSV)
# ######################
# ###################### Network setup
# ######################
sz = 210
trn_tfms, _ = tfms_from_model(resnet34, sz, crop_type=CropType.NO)
trn_tfms.tfms.pop(1) # Remove cropping to keep it rectangular
def get_learner_cnn(model_name):
bs = 1
seq_len = 1
# Datasets and Dataloaders
trn_ds = BatchifiedDataset(df_large_trn, bs, seq_len, trn_tfms, PATH,
IMAGES_FOLDER)
val_ds = BatchifiedDataset(df_large_val, bs, seq_len, trn_tfms, PATH,
IMAGES_FOLDER)
trn_dl = FastaiDataLoader(trn_ds,
batch_sampler=trn_ds.batch_sampler(shuffle=True))
val_dl = FastaiDataLoader(val_ds, batch_sampler=val_ds.batch_sampler())
config = configparser.ConfigParser()
config.read('setup.cfg')
section = config.default_section
#pixel_spacing = config[section]['pixel_spacing']
model_weight_path = config[section]['model_weight_path']
sz = 224
bs = 128
model = resnet34
trn_tfms, val_tfms = tfms_from_model(model, sz)
preprocess = val_tfms
model = ConvnetBuilder(model, 2, False, False, pretrained=False).model
sd = torch.load(model_weight_path)
model.load_state_dict(sd)
model.eval();
if __name__ == "__main__":
img_pth = sys.argv[1]
output_file = sys.argv[2]
img = load_img(img_pth)
preprocessed_img = preprocess(img)
preprocessed_img = V(preprocessed_img).unsqueeze(0)
logprob = model(preprocessed_img)