MLXID/DeepLearning
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Remove redundant version config

Browse Source
This commit is contained in:
xie_x1
2026-05-13 14:29:21 +02:00
parent e04e783fb6
commit f06e301ca7
2 changed files with 28 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Configs/infer_1photon.yaml
+25 -5
View File
@@ -31,6 +31,24 @@ data:
NY: 101
file_range: [0, 48] # [0, 48)
roi: [0, 101, 0, 101]
KnifeEdge_2filters:
file_pattern: "2603MaxIV_Edge2Filters_12keV/1Photon_CS3_chunk{}.h5" ### 12 keV
NX: 101
NY: 101
file_range: [0, 16] # [0, 16)
roi: [0, 101, 0, 101]
FlatField_2filters:
file_pattern: "2603MaxIV_Flat2Filters_12keV/1Photon_CS3_chunk{}.h5" ### 12 keV
NX: 101
NY: 101
file_range: [0, 16] # [0, 16)
roi: [0, 101, 0, 101]
Uniformity_test:
file_pattern: "2603MaxIV_Flat2Filters_12keV/1Photon_CS3_chunk{}.h5" ### 12 keV
NX: 101
NY: 101
file_range: [0, 1]
roi: [0, 101, 0, 101]
energy: 12 # keV
normalize: false # for inference dataloaders
@@ -38,13 +56,15 @@ data:
num_workers: 16
model:
version: "251022"
base_dir: "/home/xie_x1/MLXID/DeepLearning/Results/"
experiment_name: "260408_1ph_12keV_v251022_03"
name: "singlePhoton251022_12keV_Noise0.13keV_E150_aug1.pth"
noise_keV: 0.13
# experiment_name: "260408_1ph_12keV_v251022_03"
# name: "singlePhoton251022_12keV_Noise0.13keV_E150_aug1.pth"
# experiment_name: "260511_1ph_12keV_v251022_00"
# name: "singlePhoton251022_12keV_Noise0.13keV_E150_aug1.pth"
experiment_name: "260512_1ph_12keV_v260511_06"
name: "singlePhoton260511_12keV_Noise0.13keV_E300_aug1.pth"
inference:
binning_factor: 10
chunk_size: 16 #
chunk_size: 16 #
num_aug_ops: 8 # TTA: test-time augmentation
Infer_1Photon.py
+3 -3
View File
@@ -60,7 +60,6 @@ def get_files_list(conf):
return files
def run_inference(model, data_loader, conf):
model.eval()
all_predictions = []
all_reference_points = data_loader.dataset.referencePoint
with torch.no_grad():
@@ -144,7 +143,7 @@ def save_results(ml_super_frame, count_frame, subpixel_dist,
plt.close()
np.save(output_dir / '1Photon_subpixel_Distribution.npy', subpixel_dist)
rms, mean = np.std(subpixel_dist), np.mean(subpixel_dist)
print(f"[Plotting]: Sub-pixel distribution: RMS/Mean: {rms/mean:.4f}")
print(f"[Plotting]: Sub-pixel distribution: RMS/Mean: {rms/mean:.4f}, expected value = {1/np.sqrt(mean):.4f} for uniform distribution")
print(f"Results saved to: {output_dir}")
@@ -153,7 +152,8 @@ if __name__ == "__main__":
output_dir = prepare_output_folder(conf)
### model loading
model = get_model_class(conf.model.version)().cuda()
model_version = conf.model.experiment_name.split('_v')[-1][:6]
model = get_model_class(model_version)().cuda()
model.load_state_dict(torch.load(f'{conf.model.base_dir}/{conf.model.experiment_name}/Models/{conf.model.name}', weights_only=True))
model.eval()