def run():
########################################################################
# Register Prediction Start
########################################################################
aicrowd_helpers.execution_start()
########################################################################
# Gather Input and Output paths from environment variables
########################################################################
test_images_path, predictions_output_path = gather_input_output_path()
########################################################################
# Gather Image IDS
########################################################################
image_ids = gather_image_ids(test_images_path)
########################################################################
# Generate Predictions
########################################################################
evaluate(AICROWD_TEST_IMAGES_PATH, AICROWD_PREDICTIONS_OUTPUT_PATH)
########################################################################
# Register Prediction Complete
########################################################################
aicrowd_helpers.execution_success(
{"predictions_output_path": predictions_output_path})
def run():
########################################################################
# Register Prediction Start
########################################################################
aicrowd_helpers.execution_start()
########################################################################
# Load Tests Meta Data file
# and iterate over all its rows
#
# Each Row contains the following information :
#
# - hashed_id : a unique id for each test image
# - filename : filename of the image
# - country : Country where this image was taken
# - continent : Continent where this image was taken
########################################################################
OUTPUT_LINES = []
HEADER = ['hashed_id'] + VALID_SNAKE_SPECIES
OUTPUT_LINES.append(",".join(HEADER))
tests_df = pd.read_csv(AICROWD_TEST_METADATA_PATH)
for _idx, row in tests_df.iterrows():
image_id = row["hashed_id"]
country = row["country"]
continent = row["continent"]
filename = row["filename"]
filepath = os.path.join(AICROWD_TEST_IMAGES_PATH, filename)
predictions = get_random_prediction(image_id)
PREDICTION_LINE = [image_id] + [str(x) for x in predictions.tolist()]
OUTPUT_LINES.append(",".join(PREDICTION_LINE))
########################################################################
# Register Prediction
#
# Note, this prediction register is not a requirement. It is used to
# provide you feedback of how far are you in the overall evaluation.
# In the absence of it, the evaluation will still work, but you
# will see progress of the evaluation as 0 until it is complete
#
# Here you simply announce that you completed processing a set of
# image_ids
########################################################################
aicrowd_helpers.execution_progress({
"image_ids": [image_id] ### NOTE : This is an array of image_ids
})
# Write output
fp = open(AICROWD_PREDICTIONS_OUTPUT_PATH, "w")
fp.write("\n".join(OUTPUT_LINES))
fp.close()
########################################################################
# Register Prediction Complete
########################################################################
aicrowd_helpers.execution_success(
{"predictions_output_path": AICROWD_PREDICTIONS_OUTPUT_PATH})
def run():
########################################################################
# Register Prediction Start
########################################################################
aicrowd_helpers.execution_start()
########################################################################
# Gather Input and Output paths from environment variables
########################################################################
test_images_path, predictions_output_path = gather_input_output_path()
########################################################################
# Generate Predictions
########################################################################
cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
cfg.MODEL.WEIGHTS = model_path
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = threshold # set the testing threshold for this model
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 273
#cfg.MODEL.DEVICE = "cpu"
predictor = DefaultPredictor(cfg)
results = []
del cfg
for i in os.listdir(test_images_path):
img_path =test_images_path + "/" +str(i)
im = cv2.imread(img_path)
outputs = predictor(im)
instances = outputs["instances"].to(cpu_device)
fname = int(i.split('.')[0])
result = instances_to_coco_json(instances,fname)
if(len(result)!=0):
for ele in result:
matchId = ele['category_id']
ele['category_id'] = reverse_id_mapping[str(matchId)]
results.append(ele)
aicrowd_helpers.execution_progress({
"image_ids" : [fname]
})
# Write output
fp = open(predictions_output_path, "w")
fp.write(json.dumps(results))
fp.close()
########################################################################
# Register Prediction Complete
########################################################################
aicrowd_helpers.execution_success({
"predictions_output_path" : predictions_output_path
})
def run():
########################################################################
# Register Prediction Start
########################################################################
aicrowd_helpers.execution_start()
########################################################################
# Gather Input and Output paths from environment variables
########################################################################
test_images_path, predictions_output_path = gather_input_output_path()
########################################################################
# Gather Image IDS
########################################################################
image_ids = gather_image_ids(test_images_path)
########################################################################
# Generate Predictions
########################################################################
predictions = []
print("Number of images found:", len(image_ids))
for image_id in image_ids:
number_of_annotations = np.random.randint(0, MAX_NUMBER_OF_ANNOTATIONS)
for _idx in range(number_of_annotations):
print(image_id)
_annotation = single_annotation(image_id)
predictions.append(_annotation)
########################################################################
# Register Prediction
#
# Note, this prediction register is not a requirement. It is used to
# provide you feedback of how far are you in the overall evaluation.
# In the absence of it, the evaluation will still work, but you
# will see progress of the evaluation as 0 until it is complete
#
# Here you simply announce that you completed processing a set of
# image-ids
########################################################################
aicrowd_helpers.execution_progress({"image_ids": [image_id]})
# Write output
fp = open(predictions_output_path, "w")
fp.write(json.dumps(predictions))
fp.close()
########################################################################
# Register Prediction Complete
########################################################################
aicrowd_helpers.execution_success(
{"predictions_output_path": predictions_output_path})
def run():
aicrowd_helpers.execution_start()
#MAGIC HAPPENS BELOW
torch.backends.cudnn.benchmark = True
device = torch.device("cuda:0")
assert torch.cuda.is_available()
precrop, crop = bit_hyperrule.get_resolution_from_dataset(
'snakes_dataset') # verify
valid_tx = tv.transforms.Compose([
tv.transforms.Resize((crop, crop)),
tv.transforms.ToTensor(),
tv.transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)),
])
given_df = pd.read_csv(AICROWD_TEST_METADATA_PATH)
valid_set = SnakeDataset(AICROWD_TEST_IMAGES_PATH,
is_train=False,
transform=valid_tx,
target_transform=None,
csv_file=AICROWD_TEST_METADATA_PATH) # verify
valid_loader = torch.utils.data.DataLoader(valid_set,
batch_size=32,
shuffle=False,
num_workers=0,
pin_memory=True,
drop_last=False)
model = models.KNOWN_MODELS['BiT-M-R50x1'](
head_size=len(VALID_SNAKE_SPECIES), zero_head=True)
model = torch.nn.DataParallel(model)
optim = torch.optim.SGD(model.parameters(), lr=0.003, momentum=0.9)
model_loc = pjoin('models', 'initial.pth.tar')
checkpoint = torch.load(model_loc, map_location='cpu')
model.load_state_dict(checkpoint['model'])
model = model.to(device)
model.eval()
results = np.empty((0, 783), float)
for b, (x, y) in enumerate(
valid_loader): #add name to dataset, y must be some random label
with torch.no_grad():
x = x.to(device, non_blocking=True)
y = y.to(device, non_blocking=True)
logits = model(x)
softmax_op = torch.nn.Softmax(dim=1)
probs = softmax_op(logits)
data_to_save = probs.data.cpu().numpy()
results = np.concatenate((results, data_to_save), axis=0)
filenames = given_df['hashed_id'].tolist()
country_prob = pd.read_csv(
pjoin('metadata', 'probability_of_species_per_country.csv'))
country_name = country_prob[['Species/Country']]
country_dict = {name[0]: i for i, name in enumerate(country_name.values)}
given_country = given_df[['country']]
country_list = []
for country in given_country.values:
country_list.append(str(country[0]).lower().replace(
' ', '-')) # has to be a better way
adjusted_results = []
for i, result in enumerate(results):
probs = result
assert len(prob) == 783
try:
country_now = country_list[i]
country_location = country_dict[country_now]
country_prob_per_this_country = country_prob.loc[[
country_location
]].values[0][1:]
adjusted = country_prob_per_this_country * probs
adjusted_results.append(adjusted) # verify, we need list of list
except:
adjusted_results.append(probs)
assert len(adjusted_results) == len(results)
#normalize
normalized_results = adjusted_results / adjusted_results.sum(axis=1)[:,
None]
df = pd.DataFrame(data=normalized_results,
index=filenames,
columns=VALID_SNAKE_SPECIES)
df.index.name = 'hashed_id'
pd.to_csv(AICROWD_PREDICTIONS_OUTPUT_PATH, index=True)
aicrowd_helpers.execution_success(
{"predictions_output_path": AICROWD_PREDICTIONS_OUTPUT_PATH})
def run():
########################################################################
# Register Prediction Start
########################################################################
aicrowd_helpers.execution_start()
########################################################################
# Gather Input and Output paths from environment variables
########################################################################
test_images_path, predictions_output_path = gather_input_output_path()
########################################################################
# Gather Image Names
########################################################################
image_names = gather_image_names(test_images_path)
########################################################################
# Do your magic here to train the model
########################################################################
# Preprocess first here
src = (ImageList.from_folder(
path='fastai-data').split_by_rand_pct(0.0).label_from_folder()
) # any folder which has sub-folders will work
tfms = get_transforms(do_flip=True,
flip_vert=False,
max_rotate=10.0,
max_zoom=1.1,
max_lighting=0.2,
max_warp=0.2,
p_affine=0.75,
p_lighting=0.75) # some tfms
data = (src.transform(tfms, size=360,
resize_method=ResizeMethod.SQUISH).databunch(
bs=32, num_workers=0).normalize(imagenet_stats))
learn = Learner(
data, SnakeDetector(arch=models.resnet50), loss_func=L1Loss(
)) #temp data, we wont be using this, we will be using src_new
learn.split([learn.model.cnn[:6], learn.model.cnn[6:], learn.model.head])
state_dict = torch.load(
'fastai-data/models/snake-detection-model.pth') #our trained model
learn.model.load_state_dict(state_dict['model'])
if not os.path.exists('preprocessed-images'):
os.makedirs('preprocessed-images') #directory to store files
src_new = (ImageList.from_folder(
path=test_images_path).split_by_rand_pct(0.0).label_from_folder()
) # fetch given test images from data/images
for filename in src_new.items:
try:
im = cv2.imread(f"{filename}", cv2.IMREAD_COLOR)
im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
im = cv2.resize(im, (360, 360), interpolation=cv2.INTER_AREA)
im_height, im_width, _ = im.shape
orig_im = cv2.imread(f"{filename}", cv2.IMREAD_COLOR)
orig_im_height, orig_im_width, _ = orig_im.shape
to_pred = open_image(filename)
_, _, bbox = learn.predict(to_pred)
im_original = cv2.imread(f"{filename}", cv2.IMREAD_COLOR)
im_original = cv2.cvtColor(im_original, cv2.COLOR_BGR2RGB)
im_original.shape
im_original_width = im_original.shape[1]
im_original_height = im_original.shape[0]
bbox_new = bbox
bbox_new[0] = bbox_new[0] * im_original_width
bbox_new[2] = bbox_new[2] * im_original_width
bbox_new[1] = bbox_new[1] * im_original_height
bbox_new[3] = bbox_new[3] * im_original_height
x_min, y_min, x_max, y_max = map(int, bbox_new)
#cv2.rectangle(img, (x_min, y_min), (x_max, y_max), color=color, thickness=thickness)
im_original = im_original[
y_min:y_max, x_min:
x_max] #cropping is just slicing opencv uses h,w . which is y,x here
im_original = cv2.cvtColor(im_original, cv2.COLOR_BGR2RGB)
filename_str = str(filename)
to_save = filename_str.replace(
test_images_path, 'preprocessed-images'
) # original file is in /data/images/*.jpg -> store it at preprocessed-images/*.jpg and use preprocessed-images folder later
cv2.imwrite(to_save, im_original)
except:
pass
del learn
gc.collect()
model_name = 'efficientnet-b5'
image_size = EfficientNet.get_image_size(model_name)
model = EfficientNet.from_pretrained(model_name)
np.random.seed(13)
src = (ImageList.from_folder(
path='fastai-data').split_by_rand_pct(0.2).label_from_folder())
object_detection_results_path = os.getcwd(
) + "/preprocessed-images" #output of previous step is stored here.
src.add_test_folder(object_detection_results_path)
tfms = ([rotate(degrees=(-90, 90), p=0.8)], [])
bs = 8
data = (src.transform(tfms,
size=image_size,
resize_method=ResizeMethod.SQUISH).databunch(
bs=bs, num_workers=0).normalize(imagenet_stats))
model.add_module('_fc', nn.Linear(
2048,
data.c)) #Replace the final layer of b5 model with number of classes
loss_func = LabelSmoothingCrossEntropy() #following EfficientNet paper
RMSprop = partial(torch.optim.RMSprop) #Following EfficientNet paper
learn = Learner(data,
model,
loss_func=loss_func,
opt_func=RMSprop,
metrics=[accuracy,
FBeta(beta=1, average='macro')])
learn.split(
[[learn.model._conv_stem, learn.model._bn0, learn.model._blocks[:19]],
[learn.model._blocks[19:], learn.model._conv_head],
[learn.model._bn1, learn.model._fc]]) #for differential learning
learn.load(
'b5-seed-13-round-3'
) #best single model - 85.2 local cv. Try ensemble later. with 83.1 and 85.2 models
########################################################################
# Generate Predictions
########################################################################
preds, _ = learn.TTA(ds_type=DatasetType.Test) # Test time augmentation
probs_seed_13 = np.exp(preds) / np.exp(preds).sum(1)[:, None]
del learn
gc.collect() #garbage collect
model = EfficientNet.from_pretrained(model_name)
model.add_module('_fc', nn.Linear(2048, data.c))
learn = Learner(data,
model,
loss_func=loss_func,
opt_func=RMSprop,
metrics=[accuracy,
FBeta(beta=1, average='macro')]) #mew learner
learn.split(
[[learn.model._conv_stem, learn.model._bn0, learn.model._blocks[:19]],
[learn.model._blocks[19:], learn.model._conv_head],
[learn.model._bn1,
learn.model._fc]]) #not needed, but not takin chances
learn.load('b5-seed-15-round-7') #83.6, 83.1 localcv model
preds, _ = learn.TTA(ds_type=DatasetType.Test)
probs_seed_15 = np.exp(preds) / np.exp(preds).sum(1)[:, None]
probs = (probs_seed_13 + probs_seed_15) / 2
probs_np = probs.numpy()
df_test = pd.read_csv(
'given_submission_sample_file.csv', low_memory=False
) #use the given sample file to replace probabilites with our model predictions, This way, no need to worry about corrupted images
df_classes = pd.read_csv('class.csv', low_memory=False) #class mapping
data_dict = df_classes.set_index(
'class_idx')['original_class'].to_dict() #for look up
probs_np = probs.numpy()
df_testfile_mapping = pd.DataFrame(columns=['filename', 'map'])
df_testfile_mapping['filename'] = df_test['filename']
for i, row in df_testfile_mapping.iterrows():
row['map'] = i
data_dict_filename = df_testfile_mapping.set_index(
'filename'
)['map'].to_dict(
) # for lookup, returns the index where the filename is found in the given submission file
i = 0
for test_file in data.test_ds.items:
filename = (os.path.basename(test_file))
map_val = int(data_dict_filename[filename])
for c in range(0, 45):
df_test.loc[
map_val,
data_dict[int(data.classes[c].split("-")[1])]] = probs_np[i][c]
i += 1
#around 7 predictions causes assertion error, for now submit them as class-204
for i, row in df_test.iterrows():
sum_temp = row[1:46].sum()
low_limit = 1 - 1e-6
high_limit = 1 + 1e-6
if not (sum_temp >= low_limit and sum_temp <= high_limit):
for c in range(1, 46):
df_test.iloc[i, c] = 0.
df_test.loc[i, 'thamnophis_sirtalis'] = 1.
df_test.to_csv('generated-submission-3.csv', index=False)
copyfile('generated-submission-3.csv',
predictions_output_path) #save to output path
########################################################################
# Register Prediction Complete
########################################################################
aicrowd_helpers.execution_success(
{"predictions_output_path": predictions_output_path})
def run():
########################################################################
# Register Prediction Start
########################################################################
import os
aicrowd_helpers.execution_start()
os.environ['AICROWD_TEST_IMAGES_PATH'] = 'data/round1'
os.environ['AICROWD_PREDICTIONS_OUTPUT_PATH'] = 'random_prediction.csv'
########################################################################
# Gather Input and Output paths from environment variables
########################################################################
test_images_path, predictions_output_path = gather_input_output_path()
########################################################################
# Gather Image Names
########################################################################
image_names = gather_image_names(test_images_path)
########################################################################
# Do your magic here to train the model
########################################################################
import numpy as np
import os
import glob
import keras
from keras.models import load_model
import efficientnet.keras as efn
from efficientnet.keras import EfficientNetB5
model = load_model('model-224-123-16-1.178489-1.705530.hdf5')
counter2 = 0
df_data = []
df_count = []
lim = 100000
lim2 = 100000
IMAGE_folder = '/home/amaury2_pichat/data/snake/train'
for folder in os.listdir(IMAGE_folder):
counter = 0
counter2 = 0
if len(df_data) < lim:
for file in os.listdir(IMAGE_folder + '/' + folder):
if counter2 < lim2:
statinfo = os.stat(IMAGE_folder + '/' + folder + '/' +
file)
if statinfo.st_size != 0 and counter2 < lim2:
df_data.append((folder, file))
counter += 1
counter2 += 1
import pandas as pd
df_data = pd.DataFrame(df_data, columns=['Folder', 'id'])
# df_data['Folder']='' + df_data['Folder']
df_data['Classes'] = df_data['Folder']
df_data['Class'] = df_data['Classes']
df_data[
'Path'] = IMAGE_folder + '/' + df_data['Folder'] + '/' + df_data['id']
df_data.drop(['Classes', 'Folder'], axis=1, inplace=True)
from keras.preprocessing.image import ImageDataGenerator
IMAGE_SIZE = 224
valAug = ImageDataGenerator(rescale=1 / 255.0)
pred_gen = valAug.flow_from_dataframe(df_data,
x_col="Path",
y_col="Class",
shuffle=False,
target_size=(IMAGE_SIZE, IMAGE_SIZE),
batch_size=1,
class_mode='categorical')
LINES = []
with open('data/class_idx_mapping.csv') as f:
classes = ['filename']
for line in f.readlines()[1:]:
class_name = line.split(",")[0]
classes.append(class_name)
LINES.append(','.join(classes))
predictions = model.predict_generator(pred_gen,
verbose=1,
steps=len(pred_gen.filenames))
compteur = 0
for _file_path in pred_gen.filenames:
file_and_pred = _file_path[_file_path.rfind('\\') + 2:]
LINES.append(_file_path[_file_path.rfind('\\') + 2:] + "," +
",".join(str(x) for x in predictions[compteur]))
compteur += 1
#images_path = AICROWD_TEST_IMAGES_PATH + '/*.jpg'
#for _file_path in glob.glob(images_path):
# probs = softmax(np.random.rand(45))
# probs = list(map(str, probs))
# LINES.append(",".join([os.path.basename(_file_path)] + probs))
AICROWD_PREDICTIONS_OUTPUT_PATH = os.environ[
'AICROWD_PREDICTIONS_OUTPUT_PATH']
fp = open(AICROWD_PREDICTIONS_OUTPUT_PATH, "w")
fp.write("\n".join(LINES))
fp.close()
########################################################################
# Register Prediction Complete
########################################################################
aicrowd_helpers.execution_success(
{"predictions_output_path": predictions_output_path})
def run():
########################################################################
# Register Prediction Start
########################################################################
aicrowd_helpers.execution_start()
########################################################################
# Gather Input and Output paths from environment variables
########################################################################
test_images_path, predictions_output_path = gather_input_output_path()
########################################################################
# Gather Image Names
########################################################################
image_names = gather_image_names(test_images_path)
########################################################################
# Do your magic here to train the model
########################################################################
classes = get_snake_classes()
def softmax(x):
"""Compute softmax values for each sets of scores in x."""
e_x = np.exp(x - np.max(x))
return e_x / e_x.sum(axis=0)
########################################################################
# Generate Predictions
########################################################################
LINES = []
LINES.append(','.join(['filename'] + classes))
predictions = []
for image_name in image_names:
probs = softmax(np.random.rand(45))
probs = list(map(str, probs))
LINES.append(",".join([image_name] + probs))
########################################################################
# Register Prediction
#
# Note, this prediction register is not a requirement. It is used to
# provide you feedback of how far are you in the overall evaluation.
# In the absence of it, the evaluation will still work, but you
# will see progress of the evaluation as 0 until it is complete
#
# Here you simply announce that you completed processing a set of
# image_names
########################################################################
aicrowd_helpers.execution_progress({
"image_names" : [image_name]
})
# Write output
fp = open(predictions_output_path, "w")
fp.write("\n".join(LINES))
fp.close()
########################################################################
# Register Prediction Complete
########################################################################
aicrowd_helpers.execution_success({
"predictions_output_path" : predictions_output_path
})
def run():
########################################################################
# Register Prediction Start
########################################################################
aicrowd_helpers.execution_start()
########################################################################
# Load Tests Meta Data file
# and iterate over all its rows
#
# Each Row contains the following information :
#
# - `index` : Unique ID of each record
# - `intclinicaltrialid` : description to be added
# - `intdesignkeywordid` : description to be added
# - `strdesignkeyword` : description to be added
# - .... and so on
########################################################################
OUTPUT_LINES = []
HEADER = ['index'] + VALID_CLASSES
OUTPUT_LINES.append(",".join(HEADER))
tests_df = pd.read_csv(AICROWD_TEST_DATA_PATH, index_col=0)
for index_id, row in tqdm.tqdm(tests_df.iterrows()):
index_id = str(index_id)
intclinicaltrialid = row['intclinicaltrialid']
intdesignkeywordid = row['intdesignkeywordid']
##
## ... and so on
## TODO : Provide example re
predictions = get_random_prediction(index_id)
PREDICTION_LINE = [index_id] + [str(x) for x in predictions.tolist()]
OUTPUT_LINES.append(",".join(PREDICTION_LINE))
########################################################################
# Register Prediction
#
# Note, this prediction register is not a requirement. It is used to
# provide you feedback of how far are you in the overall evaluation.
# In the absence of it, the evaluation will still work, but you
# will see progress of the evaluation as 0 until it is complete
#
# Here you simply announce that you completed processing a set of
# index_ids
########################################################################
aicrowd_helpers.execution_progress({
"index_ids" : [index_id] ### NOTE : This is an array of index_ids
})
# Write output
fp = open(AICROWD_PREDICTIONS_OUTPUT_PATH, "w")
fp.write("\n".join(OUTPUT_LINES))
fp.close()
########################################################################
# Register Prediction Complete
########################################################################
aicrowd_helpers.execution_success({
"predictions_output_path" : AICROWD_PREDICTIONS_OUTPUT_PATH
})
# In the absence of it, the evaluation will still work, but you
# will see progress of the evaluation as 0 until it is complete
#
# Here you simply announce that you completed processing a set of
# image_names
########################################################################
aicrowd_helpers.execution_progress({
"image_names" : [image_name]
})
# Write output
fp = open(predictions_output_path, "w")
fp.write("\n".join(LINES))
fp.close()
########################################################################
# Register Prediction Complete
########################################################################
aicrowd_helpers.execution_success({
"predictions_output_path" : predictions_output_path
})
if __name__ == "__main__":
try:
run()
except Exception as e:
error = traceback.format_exc()
print(error)
aicrowd_helpers.execution_error(error)